Skip to content

MCP servers › com.upheron › upheron

MCP server · registry snapshot 2026-11-12 · last tested 2026-11-12

upheron MCP server

Registry name com.upheron/upheron

by upheron.com · domain (the registry's namespace rule)Website ↗

Uptime and vulnerability monitoring: check sites, manage monitors, incidents and status pages. — the publisher's description

1 of 2 record checks metRead-only · tools listed 2026-11-12version 1.2.0streamable HTTP59 tools

Summary

com.upheron/upheron is a remote MCP server listed in the official MCP registry at version 1.2.0, under the namespace of the domain upheron.com. On 2026-11-12 ProtocolProbe connected to it in read-only mode and read its inventory: 59 tools, 20 resources and 0 prompts.

Record checks

1 of 2 record checks met · 7 do not apply

  • met: Registry entry is active and says how to run it
  • not met: Source repository link opens
  • not applicable: Repository is not archived
  • not applicable: Code pushed to the repository in the 90 days before our check
  • not applicable: Repository publishes a security policy (SECURITY.md)
  • not applicable: Package names its licence with a standard (SPDX) identifier
  • not applicable: The version the registry lists can be installed and is not withdrawn
  • not applicable: npm package carries build provenance (attestation)
  • not applicable: No known critical or high advisory in the package or its dependencies
  • Not ranked by downloads: a remote server publishes no download figure
  • Not ranked by stars: no public GitHub repository

From public records, not a safety rating. Each check with its reason

Operate this server? Correct a fact · README badge · Run the checks yourself · Claim it

Key facts

Runs
remote (hosted by the publisher)
Transport
streamable HTTP
Your own values
none declared (not a guarantee)
Sign-in
none needed to open a session
Tools
59
Last tested
2026-11-12

Tool list size

26,451 tokens on Claude Opus 5.5

Added to every request that loads this server's tools (59 tools). Counted with Anthropic's token counter on 2026-11-12, from the tool list we read on 2026-11-12. Median across 28,560 counted servers: 2,657 tokens. How it is counted

How a client gets in

Connects without signing in

Read from the server's public metadata on 2026-11-12 (upheron.com), in our read-only connection; no tool was called. It may have changed since. How it is read

Tool list at the three APIs

Not sent yet for this version (1.2.0).

Add to your client

Observed fact

This server accepted a session without any credential and lists 21 tools whose name or declaration suggests they change data (post_incident_update, update_incident, write_postmortem, update_status_page_components, create_on_call_schedule and 16 more). That is our reading of the names; we did not call them. Source: our connection, 2026-11-12.

How fresh this is

Live-tested
yes, a real session (not a text-only review)
Last tested
2026-11-12
Mode
read-only (no tool calls)
Latest version
1.2.0, published 2026-11-12 (registry, as of the 2026-11-12 snapshot)
First listed version
2026-11-12 (earliest version still in the registry; older removed versions would be earlier)
Version history
4 versions listed, all on 2026-11-12; 4 in the 90 days before the 2026-11-12 snapshot.
Most recent 4 versions
  • 1.2.0 · 2026-11-12
  • 1.1.1 · 2026-11-12
  • 1.1.0 · 2026-11-12
  • 1.0.0 · 2026-11-12
(versions still listed in the registry only)
Registry data
snapshot 2026-11-12
Package and repository
checked 2026-11-12
Engine
mcp-runtime-engine@0.1.0 · sdk@1.32.0

Dead or stale signals

None found in the records we hold

Looked for and not found: deprecated in the registry. Does not apply: listed version cannot be installed or is withdrawn; repository link does not open; repository archived; no push in over 365 days. Each line is a dated fact from a public record. It does not say whether the server still works, and a record can change after the date shown.

Changes since the last refresh

New in the registry: not in the list of 2026-11-09, listed on 2026-11-12 with version 1.2.0 (published 2026-11-12).

Source: the official MCP Registry list on 2026-11-09 and on 2026-11-12.

What it is

What does this server offer?

Observed inventory
59tools
20resources
0prompts

None of its 59 tools are described as changing anything. For 59 the reading was uncertain, so no mark is shown.

  • check_websiteon 23 other servers

    “Checks whether a public website responds right now, from the monitoring service, without an account.”

    Publisher declares: read-only yes · open-world yes

    1 input, 1 required
    • urlstringrequired“A public website, such as example.com or https://example.com/path.”
  • “Plan and its monitor slots (standard in plan_monitors, premium in premium_monitors with their kinds), and the workspace's time zone (workspace.time_zone), which report days follow.”

    Publisher declares: read-only yes · open-world no

    Takes no inputs.

  • list_locationson 40 other servers

    “Location codes you can pass in a monitor's `locations`.”

    Publisher declares: read-only yes · open-world no

    Takes no inputs.

  • list_monitorson 29 other servers

    “Every monitor with its current status (pending, up, down, degraded), and interval.”

    Publisher declares: read-only yes · open-world no

    Takes no inputs.

  • “One monitor with uptime for 24 hours, 7 days and 30 days, its last 90 days, incident totals, its latest results with errors, recent incidents, and route traces from failing locations (Pro and Busines…”

    Publisher declares: read-only yes · open-world no

    1 input, 1 required
    • idstringrequired“Monitor ID from list_monitors.”
  • get_monitor_results

    “A monitor's most recent check results, newest first.”

    Publisher declares: read-only yes · open-world no

    2 inputs, 1 required
    • idstringrequired“Monitor ID from list_monitors.”
    • limitinteger“How many results to return.”
  • get_uptime_historyon 1 other server

    “A monitor's daily uptime, kept for as long as it exists: checks, successful, failed and average response time per UTC day, oldest first.”

    Publisher declares: read-only yes · open-world no

    3 inputs, 1 required
    • idstringrequired“Monitor ID from list_monitors.”
    • fromstring“First UTC day, YYYY-MM-DD.”
    • tostring“Last UTC day, YYYY-MM-DD.”
  • get_sla_report

    “Business plans: availability against an SLA target for a range of days in the workspace's time zone (time_zone in get_account; by default this month), with the downtime budget used and left, incident…”

    Publisher declares: read-only yes · open-world no

    4 inputs
    • fromstring“First day, YYYY-MM-DD, in the workspace's time zone.”
    • tostring“Last day, YYYY-MM-DD.”
    • targetnumber“SLA target in percent.”
    • monitor_idsarray“Only these monitors; by default all.”
  • get_error_budgets

    “Every monitor with an availability objective (slo_target over slo_window_days, set with update_monitor): its availability over the rolling window, the error budget in seconds, how much is used and le…”

    Publisher declares: read-only yes · open-world no

    Takes no inputs.

  • list_incidentson 17 other servers

    “Outages, newest first, with their status (open, acknowledged, resolved).”

    Publisher declares: read-only yes · open-world no

    Takes no inputs.

  • acknowledge_incidenton 4 other servers

    “Marks an open incident as being handled: its repeat alerts and escalation stop.”

    Publisher declares: read-only no · destructive no · idempotent yes · open-world no

    1 input, 1 required
    • idstringrequired“Incident ID from list_incidents.”
  • list_escalation_policieson 1 other server

    “Business plans: escalation policies, whose id a monitor's escalation_policy_id takes, and their steps.”

    Publisher declares: read-only yes · open-world no

    Takes no inputs.

Show 47 more tools
  • list_on_call_schedules

    “Business plans: on-call schedules with who is on call now, until when, and who is next.”

    Publisher declares: read-only yes · open-world no

    Takes no inputs.

  • “One incident with its timeline (detected, acknowledged, comments, status page updates, recovered), root cause and post-mortem, and the status pages its updates go to with their subscriber counts.”

    Publisher declares: read-only yes · open-world no

    1 input, 1 required
    • incident_idstringrequired“Incident ID from list_incidents.”
  • post_incident_updateon 1 other server

    “Publishes an update on every published status page that shows the incident's monitor and in their RSS and Atom feeds, and on Pro plans emails those pages' subscribers.”

    Publisher declares: read-only no · destructive no · idempotent no · open-world yes

    4 inputs, 3 required
    • incident_idstringrequired“Incident ID from list_incidents.”
    • statestringrequired“Where the work on the incident stands; the pages show it with the update.”
    • messagestringrequired“The update's text, as the pages' visitors read it.”
    • titlestring“Optional title on the pages, such as "Slow checkout".”
  • comment_on_incident

    “Adds a comment to the incident's timeline, seen only by the workspace (Pro plans).”

    Publisher declares: read-only no · destructive no · idempotent no · open-world no

    2 inputs, 2 required
    • incident_idstringrequired“Incident ID from list_incidents.”
    • messagestringrequired“The comment's text.”
  • open_incidenton 1 other server

    “Opens an incident for what the checks cannot see: a slow service, a problem a customer reported.”

    Publisher declares: read-only no · destructive no · idempotent no · open-world yes

    6 inputs, 1 required
    • titlestringrequired“What the dashboard, alerts and status pages call it.”
    • severitystring“How serious the problem is.”
    • monitor_idsarray“The monitors it affects (GET /monitors): its updates show on the published status pages that show any of them.”
    • statestring“The first update's state, investigating by default.”
    • messagestring“Optional first update for the visitors of the status pages that show the monitors.”
    • alertboolean“Alert the monitors' contacts once, and again when it is resolved.”
  • update_incidenton 4 other servers

    “Changes the title status pages show (public_title) or the root cause (Pro plans) of any incident, and the title, severity and monitors of one opened by hand.”

    Publisher declares: read-only no · destructive no · idempotent yes · open-world no

    6 inputs, 1 required
    • incident_idstringrequired“Incident ID from list_incidents.”
    • titlestring“What the dashboard, alerts and status pages call it.”
    • severitystring“How serious the problem is.”
    • monitor_idsarray“The monitors it affects (GET /monitors): its updates show on the published status pages that show any of them.”
    • public_titlestring or null“The title status pages show instead of the incident's own; null goes back to its own.”
    • root_causestring or null“What caused the incident (Pro plans); null clears it.”
  • resolve_incidenton 4 other servers

    “Resolves an incident opened with open_incident; the contacts it alerted hear so.”

    Publisher declares: read-only no · destructive no · idempotent yes · open-world yes

    2 inputs, 1 required
    • incident_idstringrequired“Incident ID from list_incidents.”
    • messagestring“Optional last update for the status pages that show the incident.”
  • write_postmortem

    “Writes a resolved incident's post-mortem: summary, impact, root cause and follow-ups (one per line), on Pro plans.”

    Publisher declares: read-only no · destructive no · idempotent yes · open-world yes

    6 inputs, 1 required
    • incident_idstringrequired“Incident ID from list_incidents.”
    • summarystring“What happened, in a few sentences.”
    • impactstring“Who and what was affected, and for how long.”
    • root_causestring“What caused the incident.”
    • follow_upsstring“What will be done so it does not happen again, one per line.”
    • publishedboolean“true shows the post-mortem on the status pages that show the incident; false takes it off.”
  • list_status_pageson 9 other servers

    “The workspace's status pages: their address (/status/{slug}), the monitors they show with the names visitors see, and their named groups of monitors in order.”

    Publisher declares: read-only yes · open-world no

    Takes no inputs.

  • update_status_page_components

    “Replaces the monitors a status page shows, in order, each optionally in a named group ("API", "EU region"); a group sits where its first monitor is and shows their worst state.”

    Publisher declares: read-only no · destructive no · idempotent yes · open-world no

    3 inputs, 1 required
    • status_page_idstringrequired“Status page ID from list_status_pages.”
    • componentsarray“The monitors the page shows, in order, each once.”
    • groupsarray“Groups' settings by name: collapsed, and id (from list_status_pages) to rename a group and keep its badges working.”
  • create_on_call_schedule

    “Business plans: a rotation through notification contacts (list_notification_contacts), handing off daily or weekly at a time in a time zone.”

    Publisher declares: read-only no · destructive no · idempotent no · open-world no

    6 inputs, 1 required
    • namestringrequired“The schedule's name.”
    • member_idsarray“Notification contacts (GET /alert-channels) in rotation order.”
    • rotationstring“How often on call passes to the next member.”
    • handoff_dayinteger“Weekly handoffs: the weekday, 1 for Monday.”
    • handoff_timestring“HH:MM on the schedule's own clock.”
    • time_zonestring“An IANA time zone.”
  • update_on_call_schedule

    “Business plans.”

    Publisher declares: read-only no · destructive no · idempotent yes · open-world no

    7 inputs, 1 required
    • schedule_idstringrequired“Schedule ID from list_on_call_schedules.”
    • namestring“The schedule's name.”
    • member_idsarray“Notification contacts (GET /alert-channels) in rotation order.”
    • rotationstring“How often on call passes to the next member.”
    • handoff_dayinteger“Weekly handoffs: the weekday, 1 for Monday.”
    • handoff_timestring“HH:MM on the schedule's own clock.”
    • time_zonestring“An IANA time zone.”
  • delete_on_call_schedule

    “Deletes a schedule no escalation policy uses.”

    Publisher declares: read-only no · destructive yes · idempotent yes · open-world no

    1 input, 1 required
    • schedule_idstringrequired“Schedule ID from list_on_call_schedules.”
  • add_on_call_override

    “Business plans: puts a contact on call in a schedule from starts_at to ends_at (up to 90 days), instead of the rotation.”

    Publisher declares: read-only no · destructive no · idempotent no · open-world no

    4 inputs, 4 required
    • schedule_idstringrequired“Schedule ID from list_on_call_schedules.”
    • alert_channel_idstringrequired“The notification contact on call instead of the rotation.”
    • starts_atstringrequired“When the override begins, as an ISO 8601 time.”
    • ends_atstringrequired“In the future, after starts_at and at most 90 days later.”
  • remove_on_call_override

    “Removes an override from a schedule (its id is in the schedule's overrides).”

    Publisher declares: read-only no · destructive yes · idempotent yes · open-world no

    2 inputs, 2 required
    • schedule_idstringrequired“Schedule ID from list_on_call_schedules.”
    • override_idstringrequired“The override's id, from the schedule's overrides in list_on_call_schedules.”
  • create_escalation_policyon 2 other servers

    “Business plans: ordered steps, each alerting contacts and whoever is on call in schedules, then waiting for an acknowledgement before the next.”

    Publisher declares: read-only no · destructive no · idempotent no · open-world no

    3 inputs, 2 required
    • namestringrequired“The policy's name.”
    • repeat_countinteger“Times the whole policy runs again when nobody acknowledges.”
    • stepsarrayrequired“In order; sending steps replaces them all.”
  • update_escalation_policyon 2 other servers

    “Business plans.”

    Publisher declares: read-only no · destructive no · idempotent yes · open-world no

    4 inputs, 1 required
    • policy_idstringrequired“Policy ID from list_escalation_policies.”
    • namestring“The policy's name.”
    • repeat_countinteger“Times the whole policy runs again when nobody acknowledges.”
    • stepsarray“In order; sending steps replaces them all.”
  • delete_escalation_policyon 2 other servers

    “Deletes a policy; its monitors go back to alerting their own contacts.”

    Publisher declares: read-only no · destructive yes · idempotent yes · open-world no

    1 input, 1 required
    • policy_idstringrequired“Policy ID from list_escalation_policies.”
  • list_maintenance_windowson 1 other server

    “Maintenance windows, latest first: times when failures open no incidents and send no alerts, for one monitor or all.”

    Publisher declares: read-only yes · open-world no

    Takes no inputs.

  • create_maintenance_windowon 2 other servers

    “Schedules maintenance for one monitor or all: no incidents or alerts while it lasts (suppress_alerts), and with announce the status pages that show it list it and tell their subscribers.”

    Publisher declares: read-only no · destructive no · idempotent no · open-world yes

    8 inputs, 3 required
    • namestringrequired“What the maintenance is, such as Database upgrade.”
    • monitor_idstring or null“The monitor under maintenance; leave out or null for every monitor.”
    • starts_atstringrequired“When it starts, ISO 8601; the first occurrence of a repeating window.”
    • ends_atstringrequired“When it ends, after starts_at.”
    • suppress_alertsboolean“false keeps the window on record without holding alerts back.”
    • announceboolean“Show the window on the status pages that show its monitor (every page of the workspace without a monitor), and tell their subscribers, one occurrence at a time.”
    • messagestring or null“What visitors are told about the maintenance.”
    • recurrenceobject or null“How the window repeats; `null` or left out for a single window.”
  • update_maintenance_windowon 1 other server

    “Changes a maintenance window or every occurrence of a repeating one.”

    Publisher declares: read-only no · destructive no · idempotent yes · open-world yes

    9 inputs, 1 required
    • window_idstringrequired“Maintenance window ID from list_maintenance_windows.”
    • namestring“What the maintenance is, such as Database upgrade.”
    • monitor_idstring or null“The monitor under maintenance; leave out or null for every monitor.”
    • starts_atstring“When it starts, ISO 8601; the first occurrence of a repeating window.”
    • ends_atstring“When it ends, after starts_at.”
    • suppress_alertsboolean“false keeps the window on record without holding alerts back.”
    • announceboolean“Show the window on the status pages that show its monitor (every page of the workspace without a monitor), and tell their subscribers, one occurrence at a time.”
    • messagestring or null“What visitors are told about the maintenance.”
    • recurrenceobject or null“How the window repeats; `null` or left out for a single window.”
  • change_maintenance_occurrence

    “Skips (skipped: true), moves (starts_at and ends_at) or changes the message of one occurrence of a repeating maintenance window, leaving the others as they are; restore: true undoes it.”

    Publisher declares: read-only no · destructive no · idempotent yes · open-world yes

    7 inputs, 2 required
    • window_idstringrequired“Maintenance window ID from list_maintenance_windows.”
    • occurrence_atstringrequired“The occurrence's start as the series gives it: occurrence_at from next_occurrences or occurrence_changes.”
    • skippedboolean“true skips this occurrence: no maintenance then, and its status pages' subscribers hear it is cancelled if they were told about it.”
    • starts_atstring“Moves this occurrence: its new start, with ends_at.”
    • ends_atstring“Its new end, after starts_at.”
    • messagestring or null“What visitors are told about this occurrence instead of the series' message.”
    • restoreboolean“true undoes every change to this occurrence.”
  • delete_maintenance_windowon 1 other server

    “Deletes a maintenance window, every occurrence of a repeating one included.”

    Publisher declares: read-only no · destructive yes · idempotent yes · open-world yes

    1 input, 1 required
    • window_idstringrequired“Maintenance window ID from list_maintenance_windows.”
  • get_audit_logon 13 other servers

    “Who changed what in the workspace, newest first: people, API tokens and agents, with the changed fields and IP (Business plan).”

    Publisher declares: read-only yes · open-world no

    6 inputs
    • resource_typestring“Only entries about this kind of thing, such as monitor, alert_channel, status_page, member or api_token.”
    • actionstring“Only this action, such as monitor.updated, or every action with a prefix, such as monitor.”
    • fromstring“First day, YYYY-MM-DD.”
    • tostring“Last day, YYYY-MM-DD.”
    • beforestring“The next value of the previous page, for older entries.”
    • limitinteger“Entries per page.”
  • create_monitoron 22 other servers

    “Creates a monitor in a free slot of the workspace's plan.”

    Publisher declares: read-only no · destructive no · idempotent yes · open-world yes

    41 inputs, 1 required
    • namestringrequired“Shown in alerts and on status pages.”
    • kindstring“What to check.”
    • urlstring“URL, or host[:port] for network checks.”
    • methodstring“The HTTP method of the check's request.”
    • interval_secondsinteger“Seconds between checks, no faster than the plan allows (300 on Free, 10 on Pro).”
    • timeout_msinteger“Milliseconds a check waits for the reply before it counts as failed.”
    • locationsarray“Location codes from GET /locations.”
    • expected_status_mininteger“The lowest HTTP status that counts as up.”
    • expected_status_maxinteger“The highest HTTP status that counts as up; at least `expected_status_min`.”
    • keywordstring“Text the response body must contain.”
    • request_headersobject“Sent with the check; stored encrypted and never returned.”
    • request_bodystring“The body sent with the check's request, such as JSON for a POST.”
    • check_optionsobject“Kind-specific options, such as `json_path`/`expected_value` for `api`, `steps` for transactions, `warn_days` for ssl.”
    • failure_thresholdinteger“Failed checks in a row before an incident opens.”
    • recovery_thresholdinteger“Successful checks in a row before the incident resolves.”
    • confirmation_thresholdinteger“Locations that must fail a check at the same time for it to count as failed.”
    • heartbeat_grace_secondsinteger“For heartbeat and webhook monitors.”
    • expiry_alertsboolean“`http` and `api` monitors: check the domain registration and (for HTTPS) the TLS certificate daily.”
    • vulnerability_alertsboolean“Every plan, `http` and `api` monitors: scan the website for the software it runs (weekly on Free, daily on paid plans) and alert on newly published vulnerabili…”
    • vulnerability_severitystring“The lowest severity that alerts.”
    • repository_urlstring or null“Pro and Business, `http` and `api` monitors with vulnerability alerts: the website's GitHub or GitLab repository (optionally …/tree/branch/folder), whose lockf…”
    • repository_tokenstring or null“Access token for a private `repository_url`: on GitHub a fine-grained token with read-only Contents, on GitLab `read_api`.”
    • chartsstring“Charts on public status pages: uptime bars (the last 90 days, or the whole history), the last 24 hours of response time, or both.”
    • ip_versionstring“Network and website checks: `auto` connects over IPv4, or IPv6 when the host has no IPv4 address; `ipv4` and `ipv6` use only that.”
    • port_scanboolean“Business plans, network and website checks: scan the common TCP ports of the host's verified addresses weekly (POST /monitors/{id}/ports/verify), and alert whe…”

    and 16 more not listed here.

  • preview_monitor_import

    “Reads the monitors of another service: UptimeRobot (a read-only API key, or its bulk upload CSV), Better Stack (a team-based API token), Uptime Kuma (its JSON backup) or a CSV file in UpHeron's forma…”

    Publisher declares: read-only yes · open-world yes

    3 inputs, 1 required
    • sourcestringrequired“Where the monitors come from: better_stack (API token), csv (UpHeron's CSV format or UptimeRobot's bulk upload template), uptime_kuma (the JSON backup of Uptim…”
    • filestring“The export file's text: a CSV for csv and uptimerobot, the backup JSON for uptime_kuma.”
    • api_keystring“For uptimerobot, a read-only API key (UptimeRobot: Integrations → API); for better_stack, a team-based API token (Better Stack: API tokens → Team-based tokens).”
  • import_monitorson 2 other servers

    “Creates the monitors the user chose from preview_monitor_import (send their `monitor` objects).”

    Publisher declares: read-only no · destructive no · idempotent yes · open-world no

    2 inputs, 1 required
    • sourcestring“The preview's source, recorded in the audit log.”
    • monitorsarrayrequired“The `monitor` objects of the preview's items to create, unchanged or edited (name, interval_seconds, status).”
  • update_monitoron 16 other servers

    “Changes a monitor's settings, within the plan's interval and location limits.”

    Publisher declares: read-only no · destructive no · idempotent yes · open-world no

    41 inputs, 1 required
    • idstringrequired“Monitor ID from list_monitors.”
    • namestring“Shown in alerts and on status pages.”
    • kindstring“What to check.”
    • urlstring“URL, or host[:port] for network checks.”
    • methodstring“The HTTP method of the check's request.”
    • interval_secondsinteger“Seconds between checks, no faster than the plan allows (300 on Free, 10 on Pro).”
    • timeout_msinteger“Milliseconds a check waits for the reply before it counts as failed.”
    • locationsarray“Location codes from GET /locations.”
    • expected_status_mininteger“The lowest HTTP status that counts as up.”
    • expected_status_maxinteger“The highest HTTP status that counts as up; at least `expected_status_min`.”
    • keywordstring“Text the response body must contain.”
    • request_headersobject“Sent with the check; stored encrypted and never returned.”
    • request_bodystring“The body sent with the check's request, such as JSON for a POST.”
    • check_optionsobject“Kind-specific options, such as `json_path`/`expected_value` for `api`, `steps` for transactions, `warn_days` for ssl.”
    • failure_thresholdinteger“Failed checks in a row before an incident opens.”
    • recovery_thresholdinteger“Successful checks in a row before the incident resolves.”
    • confirmation_thresholdinteger“Locations that must fail a check at the same time for it to count as failed.”
    • heartbeat_grace_secondsinteger“For heartbeat and webhook monitors.”
    • expiry_alertsboolean“`http` and `api` monitors: check the domain registration and (for HTTPS) the TLS certificate daily.”
    • vulnerability_alertsboolean“Every plan, `http` and `api` monitors: scan the website for the software it runs (weekly on Free, daily on paid plans) and alert on newly published vulnerabili…”
    • vulnerability_severitystring“The lowest severity that alerts.”
    • repository_urlstring or null“Pro and Business, `http` and `api` monitors with vulnerability alerts: the website's GitHub or GitLab repository (optionally …/tree/branch/folder), whose lockf…”
    • repository_tokenstring or null“Access token for a private `repository_url`: on GitHub a fine-grained token with read-only Contents, on GitLab `read_api`.”
    • chartsstring“Charts on public status pages: uptime bars (the last 90 days, or the whole history), the last 24 hours of response time, or both.”
    • ip_versionstring“Network and website checks: `auto` connects over IPv4, or IPv6 when the host has no IPv4 address; `ipv4` and `ipv6` use only that.”

    and 16 more not listed here.

  • pause_monitoron 9 other servers

    “Stops checking a monitor.”

    Publisher declares: read-only no · destructive no · idempotent yes

    1 input, 1 required
    • idstringrequired“Monitor ID from list_monitors.”
  • resume_monitoron 7 other servers

    “Starts checking a paused monitor again.”

    Publisher declares: read-only no · destructive no · idempotent yes

    1 input, 1 required
    • idstringrequired“Monitor ID from list_monitors.”
  • delete_monitoron 16 other servers

    “Deletes a monitor and its history.”

    Publisher declares: read-only no · destructive yes · idempotent yes

    1 input, 1 required
    • idstringrequired“Monitor ID from list_monitors.”
  • add_notification_contact

    “Adds an email address, chat channel, paging service, Jira project, webhook or phone number to alert on outages and recoveries.”

    Publisher declares: read-only no · destructive no · idempotent no · open-world yes

    6 inputs, 3 required
    • namestringrequired“Your name for the contact, such as "Ops email".”
    • kindstringrequired“Every plan alerts by email and through your own account with a texting provider, which bills you: `twilio` and `plivo` text or call, `vonage` and `telnyx` text…”
    • destinationstringrequired“Email address; webhook URL (slack, discord, teams, google_chat, mattermost, rocketchat, ntfy, webhook, zapier: its Catch Hook URL); Telegram chat ID; PagerDuty…”
    • tokenstring“Telegram bot token, Pushover application token, ntfy access token (optional), Jira API token, Twilio or Plivo Auth Token, Vonage API secret, Telnyx API key, or…”
    • error_typesarray or null“Alert about the outages of these kinds of errors only, and their recoveries; null or left out for every kind.”
    • optionsobject“opsgenie: `region` (us or eu, default us).”
  • confirm_notification_contact

    “Confirms an sms or voice contact, added before they were retired, with the 6-digit code it was texted or told in a call.”

    Publisher declares: read-only no · destructive no · idempotent yes · open-world no

    2 inputs, 2 required
    • idstringrequired“Contact ID from add_notification_contact or list_notification_contacts.”
    • codestringrequired“The 6-digit code the phone received.”
  • list_notification_contacts

    “Contacts that receive alerts, whether each is confirmed, and for phone contacts their latest text or call and whether it was delivered.”

    Publisher declares: read-only yes · open-world no

    Takes no inputs.

  • test_notification_contact

    “Sends a contact a test alert, at most 5 a minute for a workspace.”

    Publisher declares: read-only no · destructive no · idempotent no · open-world yes

    1 input, 1 required
    • idstringrequired“Contact ID from add_notification_contact or list_notification_contacts.”
  • get_vulnerabilitieson 2 other servers

    “For an http or api monitor with vulnerability_alerts on: the vulnerabilities and unsupported releases found in the website's software, actively exploited and most severe first, with the version that …”

    Publisher declares: read-only yes · open-world no

    1 input, 1 required
    • idstringrequired“Monitor ID from list_monitors.”
  • import_software

    “Tells the monitor what software the website and its server run, so their vulnerabilities are checked.”

    Publisher declares: read-only no · destructive no · idempotent yes · open-world no

    4 inputs, 2 required
    • idstringrequired“Monitor ID from list_monitors.”
    • contentstringrequired“The file's text, or the list.”
    • filenamestring“The file's name, such as package-lock.json or Dockerfile; tells the format.”
    • namestring“A label such as frontend/package.json, to keep two files with the same name apart.”
  • add_software

    “Adds one piece of software the website runs, by name (Debian, nginx, WordPress, Next.js…), package (npm:lodash, composer:vendor/package, pypi:django, wp-plugin:slug) or NVD product (cpe:vendor:produc…”

    Publisher declares: read-only no · destructive no · idempotent yes · open-world no

    3 inputs, 2 required
    • idstringrequired“Monitor ID from list_monitors.”
    • namestringrequired“Product name or package, such as "Debian" or "npm:lodash".”
    • versionstring“Installed version, such as 12 or 4.17.21.”
  • remove_software

    “Removes an entry from get_vulnerabilities' software list.”

    Publisher declares: read-only no · destructive yes · idempotent yes · open-world no

    2 inputs, 2 required
    • idstringrequired“Monitor ID from list_monitors.”
    • software_idstringrequired“The entry's id from get_vulnerabilities.”
  • mark_vulnerability_fixed

    “Records that the software behind a finding from get_vulnerabilities was upgraded: to `version`, or by default to the first version that fixes it (the finding's fix_version).”

    Publisher declares: read-only no · destructive no · idempotent yes · open-world no

    3 inputs, 2 required
    • idstringrequired“Monitor ID from list_monitors.”
    • finding_idstringrequired“The finding's id from get_vulnerabilities.”
    • versionstring“The version installed.”
  • “For a monitor with port_scan on (Business plans): which of its host's addresses are verified and how to verify the rest (a file each address serves, or reverse DNS under the host with a TXT record), …”

    Publisher declares: read-only yes · open-world no

    1 input, 1 required
    • idstringrequired“Monitor ID from list_monitors.”
  • verify_host

    “Looks for the proof of each of the host's addresses from get_ports: the file served at the address, or its reverse DNS (PTR) under the host resolving back to it with the TXT record in place.”

    Publisher declares: read-only no · destructive no · idempotent yes · open-world yes

    1 input, 1 required
    • idstringrequired“Monitor ID from list_monitors.”
  • get_website_changes

    “For a website or API monitor: its security headers grade with what each missing or weak header does and how to fix it, its DNS records (A, AAAA, CNAME, NS, MX, SPF, DMARC) and the networks its addres…”

    Publisher declares: read-only yes · open-world no

    1 input, 1 required
    • idstringrequired“Monitor ID from list_monitors.”
  • accept_page_change

    “Makes the page as it is now the new baseline of a monitor with content_watch, after get_website_changes shows a change you or the site's owner made on purpose.”

    Publisher declares: read-only no · destructive no · idempotent yes · open-world no

    1 input, 1 required
    • idstringrequired“Monitor ID from list_monitors.”
  • scan_ports

    “Scans the verified host's common TCP ports now instead of waiting for the weekly scan, at most once an hour.”

    Publisher declares: read-only no · destructive no · idempotent no · open-world yes

    1 input, 1 required
    • idstringrequired“Monitor ID from list_monitors.”
  • get_domain_watch

    “For an http or api monitor on Pro and Business plans: the website's registered domain, its subdomains from certificate transparency logs (crt.sh, which can be days or weeks behind) with where each po…”

    Publisher declares: read-only yes · open-world no

    1 input, 1 required
    • idstringrequired“Monitor ID from list_monitors.”
  • scan_website_software

    “Scans the monitor's website for the software it runs and checks it against the vulnerability sources now, instead of waiting for the next scan.”

    Publisher declares: read-only no · destructive no · idempotent yes · open-world yes

    1 input, 1 required
    • idstringrequired“Monitor ID from list_monitors.”

Each quoted sentence is the first sentence of the publisher’s own description. The kind of tool and the “changes data” mark are our AI model’s reading of that description, not something we tested: two differently worded runs had to agree, otherwise no label is shown, and nobody has checked them by hand. A tool without the “changes data” mark is described as only reading, searching or calculating, or the two runs did not agree. No tool was called. Read the publisher’s full description before relying on it. “Publisher declares” lists the hints the server itself sends with the tool (MCP annotations: read-only, destructive, idempotent, open-world); they are the publisher's claims, not checked by us. Inputs are the parameters in the tool's own input schema: name, declared type, whether it is required, and the first sentence of its description. Read 2026-11-12.

How well are its tools described?

Features #4 and #5

How clearly this server's own tool descriptions say what a tool does, and how consistent its tool list is. The first part is an AI model's yes/no reading of each description; the second part is counted. We do not turn it into a grade.

Descriptions

AI reading of each description

No AI reading was available for this server's tools (the two runs did not agree, or the listing was not reviewed).

Counted from the listing

Parameters with a description
100% of 220
Tools with a description
100% of 59
Typical description length
231 characters

The tool set

Counted from the listing

Tools
59
Size of the list
about 18,733 tokens for an agent to load (characters ÷ 4)
Naming
59 of 59 names use snake_case

AI reading: easy to mix up

No pair found.

The AI items cover 0 of 59 tools: for a tool where two differently worded runs disagreed, that item is left out. They were not checked by hand, and no tool was called. “Easy to mix up” means two tools whose names or descriptions overlap without saying how they differ; the AI found none, comparing tools within groups of 40. We do not rate whether the tool set is complete or whether side effects are spelled out, because our AI reading of those was not reliable enough.

How do I add it to my client?

Config from the registry entry

From the remote endpoint (Streamable HTTP)

We connected to this URL on 2026-11-12 (a read-only session: no tool was called).

Add to CursorAn install link in the format Cursor documents, holding the Cursor config below.

Claude Desktop or claude.ai
Settings → Connectors → Add custom connector, then paste:
https://upheron.com/mcp
Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json
{
  "mcpServers": {
    "upheron": {
      "url": "https://upheron.com/mcp"
    }
  }
}
VS Code · .vscode/mcp.json
{
  "servers": {
    "upheron": {
      "type": "http",
      "url": "https://upheron.com/mcp"
    }
  }
}
VS Code (command line) · Bash or zsh terminal (macOS, Linux)
code --add-mcp '{"name":"upheron","type":"http","url":"https://upheron.com/mcp"}'
Claude Code
claude mcp add --transport http upheron https://upheron.com/mcp
Cline · cline_mcp_settings.json (Cline CLI: ~/.cline/data/settings/; in the editor: MCP Servers → Configure → Configure MCP Servers)
{
  "mcpServers": {
    "upheron": {
      "type": "streamableHttp",
      "url": "https://upheron.com/mcp",
      "disabled": false,
      "autoApprove": []
    }
  }
}
Gemini CLI · ~/.gemini/settings.json, or .gemini/settings.json in a project
{
  "mcpServers": {
    "upheron": {
      "httpUrl": "https://upheron.com/mcp"
    }
  }
}
OpenAI Codex · ~/.codex/config.toml, or .codex/config.toml in a trusted project
[mcp_servers.upheron]
url = "https://upheron.com/mcp"
Zed · Zed settings file (command: zed: open settings file)
{
  "context_servers": {
    "upheron": {
      "url": "https://upheron.com/mcp"
    }
  }
}
Try it in the MCP Inspector · runs on your machine, opens in your browser · Node 22.19+
npx @modelcontextprotocol/inspector@2.11.0 --server-url https://upheron.com/mcp --transport http
  • Optional settings the entry also lists (left out above): X-API-Key.
  • The server runs on the operator's infrastructure; it may ask you to sign in when you first connect.
  • Zed's docs we read on 2026-10-26 describe remote servers by URL and do not name the transport.
  • The MCP Inspector lists the server's tools, resources and prompts; a tool you call there runs for real.

Built from the server's registry entry with each client's documented format (checked 2026-10-14; the Cursor link and the VS Code command 2026-10-19; the MCP Inspector command 2026-10-21; Cline, Gemini CLI, OpenAI Codex and Zed 2026-10-26). Values in < > are yours to fill in; this page never contains a key. Where the server needs a setting the entry does not declare, it can still fail to start.

What do the published files and outside lists say?

Read as text · nothing run · no tool called

Package files

  • MCP SDK in the package files. Not read yet: added with the next daily run.
  • Build workflow. Not read yet: added with the next daily run.

Outside lists

  • CVE records (NVD). No CVE record in the NVD feeds we read links this server's repository. Source: read 2026-11-12. This product uses the NVD API but is not endorsed or certified by the NVD.
  • GitHub advisories. No GitHub advisory names this entry's listed package. Source: read 2026-11-12. GitHub Advisory Database, CC BY 4.0
  • Docker MCP catalogue. Not in the Docker MCP catalogue on 2026-11-12. Source: read 2026-11-12.
  • Cline marketplace. Not in the Cline marketplace on 2026-11-12. Source: read 2026-11-12.

Own host

Read as text from published files and outside lists. Nothing was installed or run, and no tool was called. A fact, not a rating. How each fact is read

Does the registry listing match what we found?

Feature #6

The registry checks an entry when it is published (each new version), and nothing re-checks it on a schedule. A difference below is about the listing, not a judgement of the publisher.

Registry saysWe foundResultSource · date
Remote endpoint upheron.com/mcpSession openedmatchesour test · 2026-11-12
No credential declared as requiredOpened a session without any credentialmatchesour test · 2026-11-12

Choosing

Record checks

Public records · not a safety rating

1 of 2 record checks met · 7 do not apply

  • Not ranked by downloads: a remote server publishes no download figure
  • Not ranked by stars: no public GitHub repository
  • MetRegistry entry is active and says how to run itActive, with a package or a remote address.
  • Not metSource repository link opensThe registry entry gives no repository link.What changes this check: This check opens the repository link in the registry entry. GitHub's documentation describes changing a repository's visibility in its Settings, under Danger Zone, Change visibility. GitHub: setting repository visibility
  • Does not applyRepository is not archivedNo public GitHub repository to read.
  • Does not applyCode pushed to the repository in the 90 days before our checkNo public GitHub repository to read.
  • Does not applyRepository publishes a security policy (SECURITY.md)No public GitHub repository to read.
  • Does not applyPackage names its licence with a standard (SPDX) identifierRemote server: it ships no package.
  • Does not applyThe version the registry lists can be installed and is not withdrawnRemote server: it ships no package.
  • Does not applynpm package carries build provenance (attestation)Remote server: it ships no package.
  • Does not applyNo known critical or high advisory in the package or its dependenciesRemote server: it ships no package.

Read from public records only: the registry entry, npm/PyPI, GitHub and advisory databases, checked 2026-11-12. No tool was called. Only “met” and “not met” are counted, so the total differs between servers; a check that does not apply or that we could not run is listed, never counted against it. It is not a safety rating, and the same rules apply to every server. How each check works · Leaderboards · How we stay neutral

Common questions about com.upheron/upheron

Answered from the data above

Who publishes com.upheron/upheron?

The registry ties the namespace com.upheron to the domain upheron.com; only its owner can publish under it. These are facts from the registry and GitHub, not a rating.

Does com.upheron/upheron need an API key or sign-in?

It opened a session without any credential on 2026-11-12. The registry entry declares no required credential; no declaration is not a guarantee.

Has com.upheron/upheron been security tested?

Partly. 4 of the 15 checks that apply to it were exercised. It accepted a session without any credential and lists tools whose names suggest they change data. We did not call them. ProtocolProbe publishes no security verdict for a named server.

Found this page useful?

Anonymous · no sign-in

A quick, anonymous reaction — no account, no email. One per kind from your browser. The tally updates when the page is next refreshed, and it is only a rough count, never a safety rating or a measured number of people.

Compare with another server

Side by side: registry entry, our read-only session, the tools and the 18 classification fields. Same values as each page; no score.

Security testing

What did we test, and what did we leave out?

18 checks · features #1, #2

Open without sign-in

It accepted a session without any credential and lists tools whose names suggest they change data. We did not call them. No security score is given; a check we did not run is never counted as passed.

The 18 checks at a glanceour test · 2026-11-12
  1. Inventory: exercised
  2. Hidden instructions: exercised
  3. Real execution: not run · our policy
  4. Secret leak: not run · nothing to check it against
  5. Internal addresses: not run · our policy
  6. Unconfirmed changes: not run · our policy
  7. Bad input: not run · our policy
  8. Model requests: not run · nothing to check it against
  9. Sensitive questions: not run · nothing to check it against
  10. Folder boundary: not run · our policy
  11. Log leaks: not run · nothing to check it against
  12. Hidden content: exercised
  13. Fake assistant turns: not applicable
  14. Token passthrough: not applicable
  15. Token audience: not applicable
  16. Sign-in redirect: not run · our policy
  17. Consent handling: not testable from outside
  18. Sign-in metadata: exercised

4 exercised11 not run (reason given)3 not applicable

Each check ends in exactly one state: exercised, not run (with the reason), or not applicable (with the reason). 4 of the 15 checks that apply to it were exercised. We do not publish security-check outcomes for named servers. These 18 checks are separate from the record checks at the top of this page, which read public records only.

Exercised · 4
  • 1Inventory
    tool-list
    Reads the declared tools, resources and prompts.exercised
  • 2Hidden instructions
    description-poisoning
    Looks for hidden instructions in tool descriptions.exercised
  • 12Hidden content
    audience-hiding
    Checks resources that hide content from the user.exercised
  • 18Sign-in metadata
    oauth-url-scheme
    Checks the published sign-in metadata for unsafe URLs.exercised
Not run, with the reason · 11
  • 3Real execution
    real-execution
    Calls a tool and checks what really happens.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy
  • 4Secret leak
    canary-leak
    Plants a fake secret and checks whether it leaks.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
  • 5Internal addresses
    ssrf
    Checks whether a tool can be steered to internal addresses.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy
  • 6Unconfirmed changes
    write-without-confirmation
    Checks whether tools that change data act without asking.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy
  • 7Bad input
    error-handling
    Sends bad input and watches how the server answers.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy
  • 8Model requests
    sampling
    Checks whether the server asks the client's model to act for it.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
  • 9Sensitive questions
    elicitation-sensitive-data
    Checks whether the server asks users for sensitive data.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
  • 10Folder boundary
    root-boundary
    Checks whether the server reaches outside the folders it was given.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy
  • 11Log leaks
    logging-side-channel
    Checks whether log messages carry data they should not.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
  • 16Sign-in redirect
    open-redirect
    Checks the sign-in redirect for abuse.Testing the sign-in redirect means sending probes to the operator's sign-in service, which we do not do.not run · our policy
  • 17Consent handling
    confused-deputy
    Checks consent handling when one service acts for another.Depends on the operator's own consent screen, which differs per server and cannot be tested from outside.not testable from outside
Does not apply to this server · 3
  • 13Fake assistant turns
    fake-assistant-turn
    Checks prompts that pose as the assistant's own words.The server exposes no prompts.not applicable
  • 14Token passthrough
    token-passthrough
    Checks whether the server forwards a user's token to other services.The server opened a session without sign-in, so there is no token flow to check.not applicable
  • 15Token audience
    token-audience-validation
    Checks whether tokens meant for another service are accepted.The server opened a session without sign-in, so there is no token flow to check.not applicable

Source: our own test, 2026-11-12, mcp-runtime-engine@0.1.0. Which checks count and why follows our published scoring model.

What happened during the test?

Feature #8

The steps in order, as the test record holds them.

  1. 0 msStarted a read-only session with the server's remote endpoint
  2. 1,296 msConnected after 0 redirects. No credential was sent or needed.
  3. Read the inventory: 59 tools, 20 resources, 0 prompts.
  4. 11,215 msFinished: 4 checks exercised.

Reference

How is it classified?

18 fields

One value per field, each with its source. Fields written by AI models are marked. A field with no value says why.

TopicAI-classified
pending: added at the next monthly refresh
listed 2026-11-12; not classified yet
Pricing modelAI-classified
pending: added at the next monthly refresh
the website is not read yet
Programming language
does not apply
no existing GitHub repository (server declares no repository link, so there is nothing to fetch)
Hosting type
registry · 2026-11-12
MCP capability
resources, tools
our test · 2026-11-12
Transport
streamable HTTP
registry · 2026-11-12
Required credentials
none declared
registry · 2026-11-12 · no declaration is not a guarantee
Package registry
does not apply
remote-only server: no package is shipped, so there is no package registry
Freshness
0–30 days
registry updatedAt · 2026-11-12
Lifecycle status
registry · 2026-11-12
License class
does not apply
remote-only server: ships no package, so there is nothing to look up in a package registry
Integrity hash
does not apply
remote-only server: ships no package, so there is nothing to look up in a package registry
Signature / provenance
does not apply
remote-only server: ships no package, so there is nothing to look up in a package registry
Dependency advisories
does not apply
ships no package, so there are no dependencies to audit
Popularity
does not apply
remote-only server: ships no package, so there is nothing to look up in a package registry
Publisher signals
not stated
no readable GitHub owner to describe
Maintenance
does not apply
server declares no repository link, so there is nothing to fetch
Environment
the publisher's infrastructure
where it runs, from the hosting type · 2026-11-12

“Not stated” means the source did not state it; “does not apply” means it does not apply to this kind of server; “our limit” means our own lookup failed. A linked value opens the directory filtered to the same value.

Cite or correct this page

Sources and corrections

Suggested citation

ProtocolProbe. “com.upheron/upheron: MCP server record.” Data checked 2026-11-12. https://protocolprobe.com/mcp/servers/com.upheron/upheron

Figures are valid for the date shown. Our facts on this page are CC BY 4.0: reuse them with a link and the check date. Quoted text (the publisher’s descriptions, website quotes, tool names) is not ours to license.

As JSON: this record in the API · API documentation.

Badge for your README

ProtocolProbe: 1 of 2 record checks met

[![ProtocolProbe](https://protocolprobe.com/api/v1/badge/com.upheron/upheron)](https://protocolprobe.com/mcp/servers/com.upheron/upheron)

It shows this server's record-check count: facts from public records, no tool called. It is not a security rating or a pass. It links here and updates after each data reload.

Something wrong, or is this yours?

If a fact here is wrong, tell us and we will re-check it. If you operate this server, you can run our checks on it yourself with the free self-test command; we call no server’s tools ourselves for anything shown here, except for a server whose operator has claimed it and given permission (that server's page says so).

Write to hello@protocolprobe.com · corrections log · methodology