MCP servers › ai.funkel › funkel

MCP server · registry snapshot 2026-10-23 · last tested 2026-10-23

ai.funkel/funkel

Run LinkedIn and email outreach: find leads, manage campaigns, and reply to prospects. — the publisher's description

1 of 2 record checks metRead-only · tools listed 2026-10-23Topic: commerce-and-marketing · AI-classifiedversion 1.0.0streamable HTTP51 tools

Summary

ai.funkel/funkel is a remote MCP server listed in the official MCP registry at version 1.0.0. On 2026-10-23 ProtocolProbe connected to it in read-only mode and read its inventory: 51 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not applicable: The version the registry lists can be installed and is not withdrawn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 · Is it safe to install?

Key facts

Runs: remote (hosted by the publisher)
Transport: streamable HTTP
Sign-in: none needed to open a session
Tools: 51
Described as changing data: 12 of 51 toolsAI-classified
Mainly works on: accounts and data in outside web services; email, chat or social accountsAI-classified
Topic: commerce-and-marketingAI-classified
Last tested: 2026-10-23

Add to your client

Observed fact

This server accepted a session without any credential and lists 20 tools whose name or declaration suggests they change data (create_note, create_reminder, save_preference, rename_list, control_operator_task and 15 more). That is our reading of the names; we did not call them. Source: our connection, 2026-10-23.

Worth knowing before you connect it

12 tools are described as changing something (create_note, create_reminder, save_preference, …): our AI model's reading of the descriptions, not something we tested, and the server opened a session without any credential. We did not call them.

Each line comes from a section below, with its source and date.

How fresh this is

Live-tested: yes, a real session (not a text-only review)
Last tested: 2026-10-23
Mode: read-only (no tool calls)
Latest version: 1.0.0, published 2026-10-16 (registry, as of the 2026-10-23 snapshot)
First listed version: 2026-10-16 (earliest version still in the registry; older removed versions would be earlier)
Registry data: snapshot 2026-10-23
Package and repository: checked 2026-10-22
Engine: mcp-runtime-engine@0.1.0 · sdk@1.32.0

Changes since the last refresh

New in the registry: not in the list of 2026-10-04, listed on 2026-10-23 with version 1.0.0 (published 2026-10-16).

Source: the official MCP Registry list on 2026-10-04 and on 2026-10-23.

What it is

What does this server offer?

Observed inventory

51tools

0resources

0prompts

What it mainly works on, as our AI model read its tool descriptions: accounts and data in outside web services; email, chat or social accounts.

12 of 51 tools are described as changing something (creating, editing, deleting, sending or running). For 11 the reading was uncertain, so no mark is shown.

list_appson 26 other serversreads or searches
“List the products/apps owned by the request scope's user.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
get_product_contexton 1 other serverreads or searches
“Read the selected product's name, site, description, ICP summary, language, Product Brain availability, and dashboard link.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
list_listson 13 other serversreads or searches
“List unarchived lead lists in the selected product.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs
- limitinteger“Page size (default 20; max 50)”
- offsetinteger“Page offset (default 0)”
get_liston 17 other serversreads or searches
“Read one unarchived list in the selected product and its exact member count.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
- list_idstringrequired“List id (UUID format, e.g.”
list_list_contactsreads or searches
“List contacts in one unarchived list in the selected product.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs, 1 required
- limitinteger“Page size (default 20; max 50)”
- list_idstringrequired“List id (UUID format, e.g.”
- offsetinteger“Page offset (default 0)”
get_scheduleon 26 other serversreads or searches
“List pending, approved, or failed scheduled actions in the selected product, optionally for one campaign.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs
- campaign_idstring“Optional campaign id (UUID format, e.g.”
- limitinteger“Page size (default 20; max 50)”
- offsetinteger“Page offset (default 0)”
get_scheduled_actionreads or searches
“Read one action in the selected product: campaign, lead, type, state, scheduled and executed timestamps.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
- action_idstringrequired“Scheduled action id (UUID format, e.g.”
list_reminderson 8 other serversreads or searches
“List open or done lead reminders in the selected product with exact total and bounded pages.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs
- limitinteger“Page size (default 20; max 50)”
- offsetinteger“Page offset (default 0)”
- statusstring“Reminder state”
list_insightson 4 other serversreads or searches
“List account-scoped and selected-product-scoped open insights.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs
- limitinteger“Page size (default 20; max 50)”
- offsetinteger“Page offset (default 0)”
get_insighton 4 other serversreads or searches
“Read one insight and its evidence for the selected product, or an explicitly account-scoped insight.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
- insight_idstringrequired“Insight id (UUID format, e.g.”
list_operator_tasksreads or searches
“List durable Operator tasks in the selected product.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs
- limitinteger“Page size (default 20; max 50)”
- offsetinteger“Page offset (default 0)”
get_operator_taskreads or searches
“Read one durable Operator task in the selected product with its step states, action states, safe summaries, version, and progress.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
- task_idstringrequired“Task id (UUID format, e.g.”

Show 39 more tools

get_accesson 2 other serversreads or searches
“Read current account access for Operator and campaign actions in the selected product.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
create_noteon 6 other serverscreates or changes datadescribed as changing data
“Create a scoped note or reminder after an explicit confirmation of the exact lead, body, and due date.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world no
6 inputs, 3 required
- bodystringrequired“Note or reminder text (max 5000 chars)”
- confirmation_tokenstring“One-use approval token; omit on first call”
- lead_idstringrequired“Lead id (UUID format, e.g.”
- reminder_atstring“Optional RFC3339 reminder due date”
- reminder_bodystring“Required when reminder_at is set”
- request_keystringrequired“Stable unique request identity (8-128 chars)”
create_reminderon 6 other serverscreates or changes datadescribed as changing data
“Create a scoped note or reminder after an explicit confirmation of the exact lead, body, and due date.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world no
5 inputs, 4 required
- bodystringrequired“Note or reminder text (max 5000 chars)”
- confirmation_tokenstring“One-use approval token; omit on first call”
- lead_idstringrequired“Lead id (UUID format, e.g.”
- reminder_atstringrequired“Required RFC3339 reminder due date”
- request_keystringrequired“Stable unique request identity (8-128 chars)”
save_preferenceon 1 other servercreates or changes datadescribed as changing data
“Save one selected-product Operator preference after explicit approval.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world no
4 inputs, 2 required
- confirmation_tokenstring“Approval token; omit on first call”
- keystringrequired“Preference key (1-100 chars; no secret names)”
- reasonstring“Why this preference should be saved”
- valuestringrequired“JSON value (max 600 bytes)”
rename_liston 1 other servercreates or changes datadescribed as changing data
“Rename one unarchived list in the selected product after explicit approval.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world no
5 inputs, 4 required
- confirmation_tokenstring“Approval token; omit on first call”
- descriptionstringrequired“New full description”
- expected_namestringrequired“Current list name”
- list_idstringrequired“List id (UUID format, e.g.”
- namestringrequired“New name (1-100 chars)”
control_operator_taskdescribed as changing data
“Pause, resume, cancel, or retry a durable Operator task after exact approval.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world yes
5 inputs, 3 required
- confirmation_tokenstring“One-use approval token; omit on first call”
- expected_versionintegerrequired“Current task version”
- operationstringrequired“Task transition”
- step_idstring“Required failed step id for retry (UUID format, e.g.”
- task_idstringrequired“Task id (UUID format, e.g.”
list_agentson 71 other serversreads or searches
“List the specialist agents in the product/app the request is scoped to.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
get_agent_sourcesreads or searches
“Read X and Hacker News listening settings for one owned agent, including sources not configured yet.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs, 1 required
- agent_idstringrequired“Owned agent ID (UUID format, e.g.”
- app_idstring“Product ID; required for MCP accounts with multiple products (UUID format, e.g.”
set_agent_source_listeningcreates or changes datadescribed as changing data
“Pause or resume only an existing X or Hacker News source on an agent.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world yes
6 inputs, 3 required
- agent_idstringrequired“Owned agent ID (UUID format, e.g.”
- app_idstring“Product ID; required for MCP accounts with multiple products (UUID format, e.g.”
- confirmation_tokenstring“One-use approval token, omit before approval”
- enabledbooleanrequired
- expected_updated_atstring“Version from get_agent_sources; optional on first call”
- sourcestringrequired“One source”
configure_agent_sourcecreates or changes datadescribed as changing data
“Configure X or Hacker News searches for one owned agent and set source listening.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world yes
8 inputs, 4 required
- agent_idstringrequired“Owned agent ID (UUID format, e.g.”
- app_idstring“Product ID; required for MCP accounts with multiple products (UUID format, e.g.”
- auto_resolve_linkedinboolean“Hacker News only; automatically resolve high-confidence leads through LinkedIn, which may use credits”
- confirmation_tokenstring“One-use approval token; omit before approval”
- enabledbooleanrequired“Whether source listening should be enabled after approval”
- expected_updated_atstring“Version from get_agent_sources; optional on first call”
- queriesarrayrequired“Exact search phrases to save, 1-10”
- sourcestringrequired“Source to configure”
list_campaignson 34 other serversreads or searches
“List the campaigns in the app the request is scoped to (excludes archived).”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
get_campaignon 23 other serversreads or searches
“Read one campaign in the selected product.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
- campaign_idstringrequired“Campaign id (UUID format, e.g.”
update_campaign_settingscreates or changes datadescribed as changing data
“Change a campaign's manual review, send window, or sender assignments in the selected product.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world no
6 inputs, 1 required
- account_assignmentsobject“Only supplied platforms change”
- campaign_idstringrequired“Owned campaign id from get_campaign (UUID format, e.g.”
- confirmation_tokenstring“One-use approval token; omit on first call”
- expected_updated_atstring“Exact updated_at from get_campaign; may be omitted for a server-filled first preview”
- review_modeboolean“Require manual review before outreach”
- scheduleobject“Full send window; all fields required when supplied”
get_daily_prioritiesreads or searches
“Rank up to four live operational starting points with source IDs and links.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
get_sender_healthon 1 other serverreads or searches
“Show account-wide connected sender health and separate readiness for campaign assignments in the selected product.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
get_analyticson 32 other serversreads or searches
“Return product- or campaign-scoped activity in a UTC lookback interval.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs
- campaign_idstring“Campaign id (required when scope='campaign') (UUID format, e.g.”
- days_backinteger“Lookback window in days (default 7)”
- scopestring“Aggregation level.”
find_leadson 3 other serversreads or searches
“Search leads in the app the request is scoped to.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
4 inputs, 1 required
- limitintegerrequired“Max number of leads to return (1..50)”
- searchstring“Optional keyword (matches name, company, or headline)”
- sourcestring“Lead source.”
- statusstring“Optional status filter (e.g.”
get_leadon 5 other serversreads or searches
“Return full detail for a single lead by id, INCLUDING the derived reply_state and opt_out flags.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs, 1 required
- lead_idstringrequired“Lead id (from a prior find_leads result) (UUID format, e.g.”
- sourcestring“Lead source.”
get_conversation_contexton 1 other serverreads or searches
“Return bounded conversation context for one lead or conversation in the request scope: lead profile, product/campaign context, last real messages, recent notes, open reminders, and Reply Assistant fo…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs
- conversation_idstring“Conversation id from inbox/follow-up context (UUID format, e.g.”
- lead_idstring“Lead id from find_leads/get_lead or a follow-up result (UUID format, e.g.”
- limitinteger“Number of recent messages to return (default 12, max 20)”
get_inbox_queuereads or searches
“List reply-needed conversations or due follow-ups in the selected product.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs, 1 required
- limitinteger“Maximum rows (default 20, max 50)”
- modestringrequired“Queue type”
- offsetinteger“Pagination offset (default 0)”
list_operator_filesreads or searches
“List up to 20 files uploaded to any of your Operator threads in the selected product.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
prepare_conversation_replycalculates or converts
“Prepare one exact local inbound reply.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs, 2 required
- attachment_idstring“Optional file ID from list_operator_files.”
- bodystringrequired“Full proposed body.”
- conversation_idstringrequired“Local conversation id (UUID format, e.g.”
send_conversation_replysends messagesdescribed as changing data
“Send one exact prepared reply to the latest inbound message after explicit human approval.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world yes
5 inputs, 2 required
- attachment_idstring“Exact prepared file ID when present (UUID format, e.g.”
- confirmation_tokenstring“One-use approval token; omit on first call”
- preparedobjectrequired“Exact prepare_conversation_reply result; all fields required by server validation”
- reply_as_confirmedboolean“Explicitly confirm using another rep's sender”
- request_keystringrequired“Stable unique request identity, 8-128 chars”
get_reply_attemptreads or searches
“Read one reply attempt by its stable request_key in the selected product.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
- request_keystringrequired“Stable request identity from send_conversation_reply, 8-128 characters”
list_preferencesreads or searches
“List up to 20 saved Operator preferences for the user and product in the request scope.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
search_external_leadsreads or searchesdescribed as changing data
“Search LinkedIn for fresh people leads from the request user's connected account.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
3 inputs, 1 required
- limitinteger“Max results to return (1..10).”
- querystringrequired“Free-text people search, e.g.”
- rolestring“Optional job-title filter, e.g.”
import_search_leads_to_listcreates or changes datadescribed as changing data
“Import lead rows from a prior search_external_leads session into a lead list.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world no
5 inputs, 1 required
- confirmation_tokenstring“Phase-2 token (omit on phase-1)”
- list_idstring“Existing lead list id to import into (UUID format, e.g.”
- list_namestring“Name for a new list to create during the confirmed import when list_id is omitted”
- provider_idsarray“Optional selected provider ids from the search result.”
- session_idstringrequired“Lead search session id returned by search_external_leads (UUID format, e.g.”
create_campaign_drafton 4 other serverscreates or changes datadescribed as changing data
“Create a draft campaign in the selected product.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world no
7 inputs, 1 required
- agent_idstring“Optional agent id (from a prior list_agents) that supplies leads to this campaign (UUID format, e.g.”
- app_namestring“App name (used in the confirm preview)”
- cold_outreach_modestring“Cold outreach mode (default 'invite')”
- confirmation_tokenstring“Phase-2 token (omit on phase-1)”
- list_idstring“Optional owned lead list id.”
- namestringrequired“Campaign name (1-100 chars)”
- workflow_stepsarray“Optional custom workflow steps”
update_campaign_workflow
“Update message content on existing steps in a draft or paused campaign.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world no
5 inputs, 4 required
- app_namestringrequired“App name used in the confirmation preview”
- campaign_idstringrequired“Campaign id from a prior list_campaigns result (UUID format, e.g.”
- campaign_namestringrequired“Campaign name used in the confirmation preview”
- confirmation_tokenstring“Phase-2 token (omit on phase-1)”
- workflow_messagesarrayrequired“Exact message content to persist; prefer message_order 1..N for ordinary campaign copy”
enable_campaignon 1 other server
“Enable (resume) a paused or draft campaign.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world yes
4 inputs, 3 required
- app_namestringrequired“App name (used in the confirm preview)”
- campaign_idstringrequired“Campaign id (from a prior list_campaigns) (UUID format, e.g.”
- campaign_namestringrequired“Campaign name (used in the confirm preview)”
- confirmation_tokenstring“Phase-2 token (omit on phase-1)”
draft_message
“Generate a personalised draft for one lead.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
3 inputs, 1 required
- lead_idstringrequired“Lead id (from a prior find_leads / get_lead) (UUID format, e.g.”
- referencestring“Optional specific hook (recent post, role transition, milestone) the user wants referenced”
- tonestring“Voice register”
create_liston 11 other servers
“Create a new lead list scoped to the request's app.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
2 inputs, 1 required
- descriptionstring“Optional one-sentence description of what the list is for”
- namestringrequired“Display name for the list (1-100 chars)”
draft_icp_edit
“Stage a proposed ICP edit for one agent.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs, 1 required
- agent_idstringrequired“Agent id (from a prior list_agents) (UUID format, e.g.”
- proposed_icp_descriptionstring“Free-text description of the new ICP”
- proposed_icp_filtersstring“Optional structured filters JSON (job_titles, industries, regions, etc.)”
pause_campaignon 3 other servers
“Pause an active campaign.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world yes
4 inputs, 3 required
- app_namestringrequired“App name (used in the confirm preview)”
- campaign_idstringrequired“Campaign id (from a prior list_campaigns) (UUID format, e.g.”
- campaign_namestringrequired“Campaign name (used in the confirm preview)”
- confirmation_tokenstring“Phase-2 token (omit on phase-1)”
enable_agent
“Enable (activate) a paused or draft agent so it begins discovering leads on its schedule.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world yes
4 inputs, 3 required
- agent_idstringrequired“Agent id (from a prior list_agents) (UUID format, e.g.”
- agent_namestringrequired“Agent name (used in the confirm preview)”
- app_namestringrequired“App name (used in the confirm preview)”
- confirmation_tokenstring“Phase-2 token (omit on phase-1)”
pause_agent
“Pause an active agent so it stops discovering new leads.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world yes
4 inputs, 3 required
- agent_idstringrequired“Agent id (from a prior list_agents) (UUID format, e.g.”
- agent_namestringrequired“Agent name (used in the confirm preview)”
- app_namestringrequired“App name (used in the confirm preview)”
- confirmation_tokenstring“Phase-2 token (omit on phase-1)”
approve_leads
“Approve or reject one or more discovered leads.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world yes
6 inputs, 2 required
- actionstringrequired“Decision applied to every lead in lead_ids”
- campaign_idstring“Required for action=approve; omitted for action=reject (UUID format, e.g.”
- campaign_namestring“Campaign name (used in the confirm preview)”
- confirmation_tokenstring“Phase-2 token (omit on phase-1)”
- countinteger“Number of leads in the batch (used in the confirm preview; mirrors len(lead_ids))”
- lead_idsarrayrequired“Discovered lead ids (from a prior find_leads result)”
update_icpon 1 other server
“Apply an ICP edit (description and/or filters JSON) to one agent.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world no
6 inputs, 1 required
- agent_idstringrequired“Agent id (from a prior list_agents) (UUID format, e.g.”
- agent_namestring“Agent name (used in the confirm preview)”
- confirmation_tokenstring“Phase-2 token (omit on phase-1)”
- icp_descriptionstring“New free-text ICP description (omit to leave unchanged)”
- icp_filtersobject“New structured filters object.”
- industry_inputsarray“Explicit raw industry intent from draft_icp_edit ready_to_execute_args.”
create_agenton 13 other servers
“Create a new draft agent under the request's scoped app.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world no
9 inputs, 1 required
- app_namestring“App name (used in the confirm preview)”
- confirmation_tokenstring“Phase-2 token (omit on phase-1)”
- icp_descriptionstring“Free-text ICP description for the new agent”
- icp_filtersobject“Optional structured ICP filters.”
- linkedin_account_idsarray“Local UUIDs of the workspace LinkedIn accounts selected for searches.”
- max_signalsinteger“Cap on enabled signals (default 15)”
- namestringrequired“Display name for the new agent (1-100 chars)”
- signalsarray“Exact agent discovery signals.”
- typestring“Agent type (default 'signal')”

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 2026-10-23.

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

Says what the tool does: 100% of 40 tools
Says what it returns: 100% of 40 tools
States limits, defaults or errors: 29% of 38 tools
Says when to use it: 100% of 7 tools
Items covered per tool: 3.3 of 4 on average

Counted from the listing

Parameters with a description: 99% of 156
Tools with a description: 100% of 51
Typical description length: 379 characters

The tool set

Counted from the listing

Tools: 51
Size of the list: about 12,782 tokens for an agent to load (characters ÷ 4)
Naming: 51 of 51 names use snake_case

AI reading: easy to mix up

No pair found.

The AI items cover 40 of 51 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 2026-10-23 (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://api.funkel.ai/mcp

Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json

{
  "mcpServers": {
    "funkel": {
      "url": "https://api.funkel.ai/mcp"
    }
  }
}

VS Code · .vscode/mcp.json

{
  "servers": {
    "funkel": {
      "type": "http",
      "url": "https://api.funkel.ai/mcp"
    }
  }
}

VS Code (command line) · Bash or zsh terminal (macOS, Linux)

code --add-mcp '{"name":"funkel","type":"http","url":"https://api.funkel.ai/mcp"}'

Claude Code

claude mcp add --transport http funkel https://api.funkel.ai/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://api.funkel.ai/mcp --transport http

The server runs on the operator's infrastructure; it may ask you to sign in when you first connect.
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). 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.

Does the registry listing match what we found?

Feature #6

The registry verifies a package once, when it is published, and does not re-check it. A difference below is about the listing, not a judgement of the publisher.

Registry says	We found	Result	Source · date
Remote endpoint api.funkel.ai/mcp	Session opened	matches	our test · 2026-10-23
No credential declared as required	Opened a session without any credential	matches	our test · 2026-10-23

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.
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 2026-10-22. 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. How each check works · Leaderboards

Common questions about ai.funkel/funkel

Answered from the data above

Is ai.funkel/funkel safe to install?

We do not rate servers as safe or unsafe. 1 of its 2 applicable record checks are met (facts from public records, each listed on this page). What the records show: 12 of its tools describe changing data (our AI model's reading of the descriptions). These are facts with their sources on this page, not a safety guarantee, and we did not run its tools.

Does ai.funkel/funkel need an API key or sign-in?

It opened a session without any credential on 2026-10-23. The registry entry declares no required credential; no declaration is not a guarantee.

Has ai.funkel/funkel 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. No security verdict is published before verification.

What can ai.funkel/funkel do?

It lists 51 tools. In our AI model's reading of their descriptions (two runs had to agree, nobody checked it by hand), they include tools that read or search, create or change data, send messages and calculate or convert. We did not call any tool, so this describes the text, not the behaviour.

Can ai.funkel/funkel change or delete data?

12 of its tools say in their description that they create, edit, delete, send or run something (our AI model's reading). We did not call any tool, so we cannot say what actually happens.

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.

Similar servers

Same topic · AI-read

com.mcparmory/klaviyoalso has tools that calculates or converts, creates or changes data, reads or searches, sends messagescompare with this one
com.mcparmory/shopify-adminalso has tools that calculates or converts, creates or changes data, reads or searches, sends messagescompare with this one
app.himalayas/mcpHimalayas Remote Jobsalso has tools that calculates or converts, creates or changes data, reads or searches, sends messagescompare with this one
dev.onpage/onpageOnPage.devalso has tools that calculates or converts, creates or changes data, reads or searches, sends messagescompare with this one
io.github.hermoso-ai/hermosoHermosoalso has tools that calculates or converts, creates or changes data, reads or searches, sends messagescompare with this one
com.adbutler/mcp-serverAdButleralso has tools that calculates or converts, creates or changes data, reads or searches, sends messagescompare with this one

Active servers whose topic is also “commerce-and-marketing” and that have at least one tool of the same kind; most kinds in common first, then most GitHub stars. The topic and the tool kinds are an AI model's reading of the publishers' descriptions, not checked by hand. Similar is not a recommendation.

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 · 2026-10-23

Inventory: exercised
Hidden instructions: exercised
Real execution: not run · our policy
Secret leak: not run · nothing to check it against
Internal addresses: not run · our policy
Unconfirmed changes: not run · our policy
Bad input: not run · our policy
Model requests: not run · nothing to check it against
Sensitive questions: not run · nothing to check it against
Folder boundary: not run · our policy
Log leaks: not run · nothing to check it against
Hidden content: not run · nothing to check it against
Fake assistant turns: not applicable
Token passthrough: not applicable
Token audience: not applicable
Sign-in redirect: not run · our policy
Consent handling: not testable from outside
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.

Exercised · 3

1Inventory
tool-listReads the declared tools, resources and prompts.exercised
2Hidden instructions
description-poisoningLooks for hidden instructions in tool descriptions.exercised
18Sign-in metadata
oauth-url-schemeChecks the published sign-in metadata for unsafe URLs.exercised

Not run, with the reason · 12

3Real execution
real-executionCalls a tool and checks what really happens.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
4Secret leak
canary-leakPlants 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
ssrfChecks 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; an operator can run this check on their own server with our self-test command.not run · our policy
6Unconfirmed changes
write-without-confirmationChecks 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; an operator can run this check on their own server with our self-test command.not run · our policy
7Bad input
error-handlingSends 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; an operator can run this check on their own server with our self-test command.not run · our policy
8Model requests
samplingChecks 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-dataChecks 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-boundaryChecks 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; an operator can run this check on their own server with our self-test command.not run · our policy
11Log leaks
logging-side-channelChecks 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-hidingChecks 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-redirectChecks 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-deputyChecks 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-turnChecks prompts that pose as the assistant's own words.The server exposes no prompts.not applicable
14Token passthrough
token-passthroughChecks 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-validationChecks 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, 2026-10-23, 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.

0 msStarted a read-only session with the server's remote endpoint
1,488 msConnected after 0 redirects. No credential was sent or needed.
Read the inventory: 51 tools, 0 resources, 0 prompts.
4,803 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

commerce-and-marketing

AI-classified · 2026-10-23

Pricing modelAI-classified

no value

No value: the AI answer was held back because the quoted text did not clearly support it.

Programming language

does not apply

no existing GitHub repository (server declares no repository link, so there is nothing to fetch)

Hosting type

remote (hosted by the publisher)

registry · 2026-10-23

MCP capability

tools

our test · 2026-10-23

Transport

streamable HTTP

registry · 2026-10-23

Required credentials

none declared

registry · 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 · 2026-10-23

Lifecycle status

active

registry · 2026-10-23

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

“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. “ai.funkel/funkel: MCP server record.” Data checked 2026-10-23. https://protocolprobe.com/mcp/servers/ai.funkel/funkel

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](https://protocolprobe.com/api/v1/badge/ai.funkel/funkel)](https://protocolprobe.com/mcp/servers/ai.funkel/funkel)

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.

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