Skip to content

MCP servers › com.nomidmdm › nomid-mdm

MCP server · registry snapshot 2026-11-12 · last tested 2026-11-15

nomid-mdm MCP server

Registry name com.nomidmdm/nomid-mdm

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

Manage Android and VR device fleets: policies, kiosk mode, device commands and enrollment QR codes. — the publisher's description

1 of 2 record checks metRead-only · tools listed 2026-11-15version 1.0.2streamable HTTP32 tools

Summary

com.nomidmdm/nomid-mdm is a remote MCP server listed in the official MCP registry at version 1.0.2, under the namespace of the domain nomidmdm.com. On 2026-11-15 ProtocolProbe connected to it in read-only mode and read its inventory: 32 tools, 0 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  • not applicable: The version the registry lists can be installed and is not withdrawn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
32
Last tested
2026-11-15

Tool list size

28,104 tokens on Claude Opus 5.5

Added to every request that loads this server's tools (32 tools). Counted with Anthropic's token counter on 2026-11-15, from the tool list we read on 2026-11-15. 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 2026-11-15 (mcp.nomid.tech), 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 (1.0.2).

Add to your client

Observed fact

This server accepted a session without any credential and lists 5 tools whose name or declaration suggests they change data (send_device_command, send_destructive_command, apply_policy_proposal, create_policy, create_provisioning_qr_code). That is our reading of the names; we did not call them. Source: our connection, 2026-11-15.

How fresh this is

Live-tested
yes, a real session (not a text-only review)
Last tested
2026-11-15
Mode
read-only (no tool calls)
Latest version
1.0.2, published 2026-11-11 (registry, as of the 2026-11-12 snapshot)
First listed version
2026-11-07 (earliest version still in the registry; older removed versions would be earlier)
Version history
3 versions listed, 2026-11-07 to 2026-11-11; 3 in the 90 days before the 2026-11-12 snapshot.
Most recent 3 versions
  • 1.0.2 · 2026-11-11
  • 1.0.1 · 2026-11-10
  • 1.0.0 · 2026-11-07
(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

Version 1.0.0 (published 2026-11-07) → 1.0.2 (published 2026-11-11), between the registry lists of 2026-11-09 and 2026-11-12.

No release note: the registry entry links no GitHub repository.

Source: the official MCP Registry list on 2026-11-09 and on 2026-11-12; release notes from the GitHub Releases API, checked 2026-11-12.

What it is

What does this server offer?

Observed inventory
32tools
0resources
0prompts

None of its 32 tools are described as changing anything. For 32 the reading was uncertain, so no mark is shown.

  • get_company_plan

    “The company's own Nomid plan (FREE, PRO or ENTERPRISE), its term and billing cadence, its device limit (the Free plan's; paid plans have none), how many devices count as billable now and which device…”

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

    1 input
    • companystring“Optional: a `company` value from list_companies to run this in.”
  • list_companieson 41 other servers

    “List the companies this connection can work in, each with its `company` value, tenant and device counts (total, by status, and ACTIVE devices with no check-in for 7 days or more), plus totals across …”

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

    3 inputs
    • querystring“Optional.”
    • pageinteger“Zero-based page of the list, sorted by device count (most devices first).”
    • sizeinteger“Companies per page, 1-200.”
  • send_device_command

    “Send one command to real, physical devices, the command chosen with command: one device (assetId, its pathName from search_devices or get_device), several (assetIds, up to 50 pathNames) or every devi…”

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

    14 inputs, 1 required
    • commandstringrequired“The command to send, one of the lines of this tool's description.”
    • assetIdstring“The asset's path name - the unique identifier returned by search_devices/get_device as "pathName".”
    • assetIdsarray“Several devices instead of assetId: their pathNames, 2 to 50.”
    • devicesInPolicystring“Every device of this policy (its pathName from list_policies) that can take commands, instead of assetId; at most 50.”
    • messagestring“Message shown on the device's lock screen while it is in lost mode, e.g.”
    • phoneNumberstring“Contact phone number shown on the lock screen.”
    • emailstring“Contact email address shown on the lock screen.”
    • streetAddressstring“Contact street address shown on the lock screen.”
    • organizationstring“Organization name shown on the lock screen.”
    • titlestring“Plain-text notification title shown on the device.”
    • bodystring“Plain-text notification body shown on the device.”
    • packageNamestring“Package name of the installed app to open, e.g.”
    • policyIdstring“The new policy's path name - the unique identifier returned by list_policies as "pathName".”
    • companystring“Optional: a `company` value from list_companies to run this in.”
  • send_destructive_command

    “Send one command that cannot be undone to one real, physical device, the command chosen with command; these are never sent to several devices at once.”

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

    5 inputs, 2 required
    • commandstringrequired“The command to send, one of the lines of this tool's description.”
    • assetIdstringrequired“The asset's path name - the unique identifier returned by search_devices/get_device as "pathName".”
    • newPasswordstring“The new screen lock password the user chose.”
    • packageNamesarray“Package names of the apps, e.g.”
    • companystring“Optional: a `company` value from list_companies to run this in.”
  • count_devices

    “Count the authenticated company's devices, optionally narrowed by device status, assigned policy (or several, with "policies"), "lastSyncBefore" (each device's last sync, the portal's "Last sync", be…”

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

    8 inputs
    • statusstring“Filter by device status.”
    • policystring“Filter by the policy's path name (its unique short identifier, as returned by list_policies as "pathName" - not its human-readable display name).”
    • policiesarray“Count the devices of any of these policies (path names, as for "policy"), all in one call.”
    • lastSyncBeforestring“Only include devices whose last sync (the portal's "Last sync": their last contact with Nomid) is before this ISO-8601 instant (e.g.”
    • lastSeenBeforestring“Only include assets whose record was updated before this ISO-8601 instant (e.g.”
    • missingarray“Only devices that have none of these identifiers: "imei" (no IMEI: a Wi-Fi-only device, or one that never reported it) and/or "serialNumber" (no serial number).”
    • groupByarray“Break the count down: one group per combination of these values, largest first, each with its count ("model" is the device's model code, with its commercial "m…”
    • companystring“Optional: a `company` value from list_companies to run this in.”
  • “Diagnose a problem in one call, the problem chosen with area.”

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

    5 inputs, 1 required
    • areastringrequired“What to diagnose.”
    • assetIdstring“The asset's path name - the unique identifier returned by search_devices/get_device as "pathName".”
    • policyIdstring“Path name of the policy whose QR code was scanned, when known (the page's policy, or list_policies).”
    • serialNumberstring“Serial number of the device that fails to enroll, when the user gave it.”
    • companystring“Optional: a `company` value from list_companies to run this in.”
  • “Get full details for a single device (asset) in the authenticated company by its path name, including policy assignment, custom data, tags, hardware specifications and last known location.”

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

    2 inputs, 1 required
    • assetIdstringrequired“The asset's path name - the unique identifier returned by search_devices/get_device as "pathName".”
    • companystring“Optional: a `company` value from list_companies to run this in.”
  • get_fleet_summaryon 1 other server

    “Get a compact aggregate summary of the authenticated company's fleet: total device count, a breakdown by status, and the security-posture summary (secure/at-risk/compromised/unknown counts, encryptio…”

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

    1 input
    • companystring“Optional: a `company` value from list_companies to run this in.”
  • list_device_apps

    “Get the apps actually on one device (asset) in the authenticated company, from the app report the device last sent: package name, app name, version, state (INSTALLED, or REMOVED when it was uninstall…”

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

    5 inputs, 1 required
    • assetIdstringrequired“The asset's path name - the unique identifier returned by search_devices/get_device as "pathName".”
    • querystring“Optional case-insensitive text matched against the package name and the app name (e.g.”
    • includeSystemAppsboolean“Without a query, also list system apps (not user facing, not installed by the policy or the user).”
    • limitinteger“Maximum number of apps to return, sorted by name.”
    • companystring“Optional: a `company` value from list_companies to run this in.”
  • list_device_commands

    “Get the most recent commands sent to a device (asset) in the authenticated company, newest first: type, status, timestamps, a short outcome code and who sent it.”

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

    3 inputs, 1 required
    • assetIdstringrequired“The asset's path name - the unique identifier returned by search_devices/get_device as "pathName".”
    • limitinteger“Maximum number of commands to return, newest first.”
    • companystring“Optional: a `company` value from list_companies to run this in.”
  • list_device_user_logins

    “Get who logged in on the company's devices: the sessions of device users, newest first.”

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

    9 inputs
    • assetIdstring“Only sessions on this asset - its path name, as search_devices/get_device return it.”
    • serialNumberstring“Only sessions on the asset with this serial number.”
    • deviceUserIdstring“Only sessions of this device user, by its Nomid id (deviceUser.id in a result).”
    • externalUserIdstring“Only sessions of the EXTERNAL device user with this id from the customer's own system.”
    • openboolean“Only sessions still open (nobody logged out, not expired).”
    • fromstring“Only sessions that started at or after this ISO-8601 instant, e.g.”
    • tostring“Only sessions that started before this ISO-8601 instant.”
    • limitinteger“Maximum number of sessions to return, newest first.”
    • companystring“Optional: a `company` value from list_companies to run this in.”
  • read_device_document

    “Nomid staff only (Nomid system admins; refused for everyone else).”

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

    5 inputs, 1 required
    • assetIdstringrequired“The device's assetId (pathName), from search_devices.”
    • pathstring“Optional.”
    • packageNamestring“Optional, instead of path: that app's entry in the device's app report, with its keyedAppStates.”
    • fromIndexinteger“When a result carries nextFromIndex: pass it here for the rest.”
    • companystring“Optional: a `company` value from list_companies to run this in.”
Show 20 more tools
  • search_deviceson 8 other servers

    “Search the authenticated company's device fleet.”

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

    10 inputs
    • statusstring“Filter by device status.”
    • policystring“Filter by the policy's path name (its unique short identifier, as returned by list_policies as "pathName" - not its human-readable display name).”
    • lastSyncBeforestring“Only include devices whose last sync (the portal's "Last sync": their last contact with Nomid) is before this ISO-8601 instant (e.g.”
    • lastSeenBeforestring“Only include assets whose record was updated before this ISO-8601 instant (e.g.”
    • missingarray“Only devices that have none of these identifiers: "imei" (no IMEI: a Wi-Fi-only device, or one that never reported it) and/or "serialNumber" (no serial number).”
    • querystring“Free text to find a device by name, serial number, IMEI, model or tag.”
    • fieldsstring“"names" lists the matching devices as a table of name, pathName, policy and lastSync, up to 200 a page, with the exact total and nextPage.”
    • pageinteger“Zero-based page number.”
    • sizeinteger“Number of devices per page.”
    • companystring“Optional: a `company` value from list_companies to run this in.”
  • search_nomid_site

    “Search Nomid's public website (www.nomidmdm.com) for plans and pricing: the Free, Pro and Enterprise plans and their device limits, list prices per Android and VR device per month in USD, EUR and BRL…”

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

    3 inputs, 1 required
    • querystringrequired“What to look up, in the user's words, e.g.”
    • localestring“The language to answer in: en, es or pt (Brazil).”
    • companystring“Optional: a `company` value from list_companies to run this in.”
  • search_libraryon 39 other servers

    “Search the company's Nomid Library: its apps (private Android apps uploaded to Nomid, with package name, version and categories) or, with kind "links", its web links (VR library).”

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

    5 inputs
    • kindstring“What to search: apps (default) or links (web links of the VR library).”
    • querystring“Optional.”
    • categorystring“Optional, apps only.”
    • limitinteger“At most this many results, 1-50.”
    • companystring“Optional: a `company` value from list_companies to run this in.”
  • get_portal_link

    “Get the URL of a device, policy or library app in the Nomid portal, to show the user where to see or manage it, or of a fixed portal page (kind "page": the dashboard, the devices or policies list, th…”

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

    3 inputs, 2 required
    • kindstringrequired“What to link to: a device (asset), a policy, a library app, or a fixed portal page.”
    • idstringrequired“The identifier: the asset's or policy's path name (the "pathName" returned by search_devices, get_device and list_policies), the app's package name, or for a p…”
    • companystring“Optional: a `company` value from list_companies to run this in.”
  • apply_policy_proposal

    “Apply a policy change you proposed (propose_policy_change, create_policy, rollback_policy) by its proposalId.”

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

    3 inputs, 1 required
    • proposalIdstringrequired“The proposalId returned by propose_policy_change, create_policy or rollback_policy.”
    • confirmationstring“Ignored: Nomid no longer asks for a typed policy name.”
    • companystring“Optional: a `company` value from list_companies to run this in.”
  • propose_policy_change

    “Propose one change to an existing policy: pass policyId and exactly one of the parts below; for changes of several kinds, call it once per part.”

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

    8 inputs, 1 required
    • policyIdstringrequired“The policy's path name - the unique identifier returned by list_policies as "pathName".”
    • settingsarray“Part settings: the restrictions, security, connectivity, location, reporting and Play Store settings get_policy_settings lists.”
    • appsarray“Part apps: add, remove or change how apps are installed.”
    • homeScreenobject“Part homeScreen: kiosk mode, the Nomid launcher or the device's own home screen, and the dock.”
    • wallpaperobject“Part wallpaper: the wallpaper of the devices' home and lock screen: an image by URL or uploaded in the chat, the company default or none.”
    • detailsobject“Part details: the description, tags or policy group.”
    • editsarray“Part edits: anything else, such as Wi-Fi, passwords or fences, as JSON Pointer edits of get_policy_document.”
    • companystring“Optional: a `company` value from list_companies to run this in.”
  • create_policyon 2 other servers

    “Propose creating a new policy, optionally with setting changes.”

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

    4 inputs, 1 required
    • fromPolicyIdstring“Path name of the existing policy to copy (apps, settings, restrictions) - "pathName" from list_policies.”
    • displayNamestringrequired“Name of the new policy, as shown in the portal (at most 30 characters).”
    • changesarray“Settings to change, each at most once.”
    • companystring“Optional: a `company` value from list_companies to run this in.”
  • “Find where an app is, by package name or by name, in one call: whether it is in a policy (its source - Google Play, the Nomid Store Library, a secure web app - its install type and whether it is the …”

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

    4 inputs, 1 required
    • querystringrequired“The app's package name (com.example.app; a Play Store link also works) or part of its name ("Phone", "Aumet").”
    • policyIdstring“The policy to check, by path name (list_policies' "pathName").”
    • assetIdstring“A device to check (search_devices' "pathName"): whether its last app report lists the app installed.”
    • companystring“Optional: a `company` value from list_companies to run this in.”
  • find_policy_setting

    “Find a policy setting by the user's words: which fields of the policy it is, their current values (NOT_SET when the policy leaves a field out: it can still be set), where the portal's policy editor s…”

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

    3 inputs, 2 required
    • policyIdstringrequired“The policy's path name - the unique identifier returned by list_policies as "pathName".”
    • querystringrequired“The setting in the user's own words, any language ("keyboard microphone", "volume fixo em 50%", "papel de parede", "block USB").”
    • companystring“Optional: a `company` value from list_companies to run this in.”
  • get_policy_document

    “Get a policy's full configuration as JSON, or the part at a path: Wi-Fi networks (openNetworkConfigurations), passwords, restrictions, system updates, the launcher, time and geo fences, app configura…”

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

    4 inputs, 1 required
    • policyIdstringrequired“The policy's path name - the unique identifier returned by list_policies as "pathName".”
    • pathstring“Optional JSON Pointer to read one part, e.g.”
    • searchstring“Optional, when reading /phoneContacts, /libraryFiles or /vr: list only the attachable items whose name or id contains this text.”
    • companystring“Optional: a `company` value from list_companies to run this in.”
  • get_policy_proposal

    “Get a policy change proposal you made, by its proposalId: its change list, impact, status (PENDING, SUCCEEDED, FAILED, EXPIRED, ...), expiry and outcome.”

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

    2 inputs, 1 required
    • proposalIdstringrequired“The proposalId returned by propose_policy_change, create_policy or rollback_policy.”
    • companystring“Optional: a `company` value from list_companies to run this in.”
  • get_policy_revision_document

    “Read a policy's saved historical configuration by revision ID from list_policy_revisions, with secrets replaced by {"redacted": true}.”

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

    5 inputs, 2 required
    • policyIdstringrequired“The policy's path name - the unique identifier returned by list_policies as "pathName".”
    • revisionintegerrequired“The saved revision ID from list_policy_revisions, for this policy.”
    • pathstring“Optional JSON Pointer into the historical configuration, as in notShown.”
    • fromIndexinteger“When a result carries nextFromIndex, pass it here for the rest.”
    • companystring“Optional: a `company` value from list_companies to run this in.”
  • get_policy_settings

    “Get the settings of a policy that AI agents can change: for each one its id, label, group, current value, allowed values and whether changing it is high impact; plus the policy's version (the portal'…”

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

    2 inputs, 1 required
    • policyIdstringrequired“The policy's path name - the unique identifier returned by list_policies as "pathName".”
    • companystring“Optional: a `company` value from list_companies to run this in.”
  • get_policy_usage

    “Usage report of one policy (policyId) or of a whole policy group (policyGroup: every policy of it added up, one row per policy), over the last 7 or 30 complete days (UTC), for the devices on the poli…”

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

    4 inputs
    • policyIdstring“The policy's pathName (from list_policies), for one policy's usage.”
    • policyGroupstring“A policy group's name (as list_policies shows it under group) or path name, for every policy of the group added up.”
    • daysinteger“The period: the last 7 (default) or 30 complete days (UTC), today excluded.”
    • companystring“Optional: a `company` value from list_companies to run this in.”
  • list_policieson 12 other servers

    “List every policy defined in the authenticated company, or with query those matching it, with overview information (path name, display name, description, version, policy group, deviceCount).”

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

    2 inputs
    • querystring“Optional.”
    • companystring“Optional: a `company` value from list_companies to run this in.”
  • list_policy_revisions

    “List the saved revisions of a policy, newest first: revision number, when and by whom it was saved, and the policy version it produced.”

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

    3 inputs, 1 required
    • policyIdstringrequired“The policy's path name - the unique identifier returned by list_policies as "pathName".”
    • limitinteger“How many revisions to return, newest first (default 20).”
    • companystring“Optional: a `company` value from list_companies to run this in.”
  • rollback_policy

    “Propose rolling a policy back to one of its revisions (list_policy_revisions): its whole configuration - apps, settings, restrictions, networks - is restored, and its name goes back to the revision's…”

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

    3 inputs, 2 required
    • policyIdstringrequired“The policy's path name - the unique identifier returned by list_policies as "pathName".”
    • revisionintegerrequired“The revision to restore, from list_policy_revisions.”
    • companystring“Optional: a `company` value from list_companies to run this in.”
  • create_provisioning_qr_code

    “Create a QR code that enrolls a new or factory-reset Android device into this company under the given policy.”

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

    7 inputs, 1 required
    • policyIdstringrequired“Path name of the policy the device enrolls with - the "pathName" returned by list_policies.”
    • personalUsagestring“Company-owned device with a work profile that keeps the user's personal data separate (ALLOWED, also called COPE), company-owned fully managed device (DISALLOW…”
    • wifiSsidstring“Optional Wi-Fi network the device joins during setup.”
    • wifiPasswordstring“Password of wifiSsid.”
    • wifiSecuritystring“Security of wifiSsid.”
    • wifiHiddenboolean“Whether wifiSsid is a hidden network.”
    • companystring“Optional: a `company` value from list_companies to run this in.”
  • read_company_chats

    “Nomid staff only (Nomid system admins; refused for everyone else).”

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

    6 inputs
    • sessionIdinteger“Optional.”
    • fromTurninteger“With sessionId: the first turn to return (0-based).”
    • sincestring“List only: ISO-8601 instant; chats active at or after it.”
    • offsetinteger“List only: skip this many chats (most recently active first).”
    • limitinteger“List only: at most this many chats, most recently active first.”
    • companystring“Optional: a `company` value from list_companies to run this in.”
  • read_flagged_chats

    “Nomid staff only (Nomid system admins; refused for everyone else).”

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

    6 inputs
    • reviewIdinteger“Optional.”
    • fromTurninteger“With reviewId: the first turn to return (0-based).”
    • statusstring“List only: the review verdict to list.”
    • sincestring“List only: ISO-8601 instant; reviews made at or after it.”
    • offsetinteger“List only: skip this many matching reviews (newest first).”
    • limitinteger“List only: at most this many reviews, newest first.”

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 2026-11-15.

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 148
Tools with a description
100% of 32
Typical description length
1,116 characters

The tool set

Counted from the listing

Tools
32
Size of the list
about 20,071 tokens for an agent to load (characters ÷ 4)
Naming
31 of 32 names use snake_case

AI reading: easy to mix up

No pair found.

The AI items cover 0 of 32 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. 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 2026-11-15 (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://mcp.nomid.tech/emm/api/mcp
Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json
{
  "mcpServers": {
    "nomid-mdm": {
      "url": "https://mcp.nomid.tech/emm/api/mcp"
    }
  }
}
VS Code · .vscode/mcp.json
{
  "servers": {
    "nomid-mdm": {
      "type": "http",
      "url": "https://mcp.nomid.tech/emm/api/mcp"
    }
  }
}
VS Code (command line) · Bash or zsh terminal (macOS, Linux)
code --add-mcp '{"name":"nomid-mdm","type":"http","url":"https://mcp.nomid.tech/emm/api/mcp"}'
Claude Code
claude mcp add --transport http nomid-mdm https://mcp.nomid.tech/emm/api/mcp
Cline · cline_mcp_settings.json (Cline CLI: ~/.cline/data/settings/; in the editor: MCP Servers → Configure → Configure MCP Servers)
{
  "mcpServers": {
    "nomid-mdm": {
      "type": "streamableHttp",
      "url": "https://mcp.nomid.tech/emm/api/mcp",
      "disabled": false,
      "autoApprove": []
    }
  }
}
Gemini CLI · ~/.gemini/settings.json, or .gemini/settings.json in a project
{
  "mcpServers": {
    "nomid-mdm": {
      "httpUrl": "https://mcp.nomid.tech/emm/api/mcp"
    }
  }
}
OpenAI Codex · ~/.codex/config.toml, or .codex/config.toml in a trusted project
[mcp_servers.nomid-mdm]
url = "https://mcp.nomid.tech/emm/api/mcp"
Zed · Zed settings file (command: zed: open settings file)
{
  "context_servers": {
    "nomid-mdm": {
      "url": "https://mcp.nomid.tech/emm/api/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://mcp.nomid.tech/emm/api/mcp --transport http
  • Optional settings the entry also lists (left out above): Authorization.
  • 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

  • security.txt. No security.txt at https://mcp.nomid.tech/.well-known/ (HTTP 404, 2026-11-12). No security.txt at https://www.nomidmdm.com/.well-known/ (HTTP 404, 2026-11-12). Source: mcp.nomid.tech/.well-known/security.txt · read 2026-11-12.
  • A2A agent card. No A2A agent card at https://mcp.nomid.tech/.well-known/ (HTTP 404, 2026-11-12). No A2A agent card at https://www.nomidmdm.com/.well-known/ (HTTP 404, 2026-11-12). Source: mcp.nomid.tech/.well-known/agent-card.json · read 2026-11-12.

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 mcp.nomid.tech/emm/api/mcpSession openedmatchesour test · 2026-11-15
No credential declared as requiredOpened a session without any credentialmatchesour test · 2026-11-15

Tool list changes

Our reads compared · no tool called

Hosted endpoint mcp.nomid.tech/emm/api/mcp

1 of 1 comparison between consecutive reads showed a change (2 reads, 2026-11-12 to 2026-11-15; version 1.0.2).

Last change seen between our reads on 2026-11-12 (version 1.0.2) and 2026-11-15 (version 1.0.2). Changed without a new version: both reads list version 1.0.2.

Added (2):

find_policy_settingget_policy_usage

Changed (3):

create_provisioning_qr_code: description, input schemapropose_policy_change: description, input schemasend_destructive_command: description

Compared from the tool lists our read-only connection recorded, separately for each hosted endpoint and each package: each tool's name, title, description, input schema and annotations (the order of keys and of tools is ignored). We see a list only when we read it: a change is shown between the two reads where we first saw it, and anything after 2026-11-15 is not known yet. No tool was called. How it is compared

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.nomidmdm/nomid-mdm

Answered from the data above

Who publishes com.nomidmdm/nomid-mdm?

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

Does com.nomidmdm/nomid-mdm need an API key or sign-in?

It opened a session without any credential on 2026-11-15. The registry entry declares no required credential; no declaration is not a guarantee.

Has com.nomidmdm/nomid-mdm been security tested?

Partly. 3 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 · 2026-11-15
  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: not run · nothing to check it against
  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

3 exercised12 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). 3 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 · 3
  • 1Inventory
    tool-list
    Reads the declared tools, resources and prompts.exercised
  • 2Hidden instructions
    description-poisoning
    Looks for hidden instructions in tool descriptions.exercised
  • 18Sign-in metadata
    oauth-url-scheme
    Checks the published sign-in metadata for unsafe URLs.exercised
Not run, with the reason · 12
  • 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
  • 12Hidden content
    audience-hiding
    Checks resources that hide content from the user.This check needs content the server returns, and nothing was read or 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, 2026-11-15, 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. 1,499 msConnected after 0 redirects. No credential was sent or needed.
  3. Read the inventory: 32 tools, 0 resources, 0 prompts.
  4. 6,322 msFinished: 3 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
tools
our test · 2026-11-15
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.nomidmdm/nomid-mdm: MCP server record.” Data checked 2026-11-15. https://protocolprobe.com/mcp/servers/com.nomidmdm/nomid-mdm

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.nomidmdm/nomid-mdm)](https://protocolprobe.com/mcp/servers/com.nomidmdm/nomid-mdm)

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