Skip to content

Clutch.co MCP server

co.clutch/mcpclutch.costreamable-httpv1.0.3Scanned

Trusted B2B service providers with verified client reviews

5 tools: 1 can delete or cancel things, 1 change things and 3 only read.

Tools: 1 delete, 0 irreversible, 1 write, 3 read.
  • Reads private data · 0
  • Reads text others write · 5
  • Can send data out · 1
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

1 tool here can delete or cancel things. Govern it.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the Clutch.co MCP server can do

The Clutch.co MCP server is published by clutch.co, a domain the MCP Registry verified. It has 5 tools. It can delete or cancel things (1 tool: send_message_to_provider) and create or change data (1 tool: recommend_service_providers). 3 tools only read.

5 tools bring in text other people can write (get_provider_info, get_service_provider_reviews, recommend_service_providers and 2 more); 1 tool can send data out of your system (send_message_to_provider).

None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 12, 2026, version 1.0.3.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

5 tools

Deletes or cancels 1Claude Code: deny
  • send_message_to_providerReach out to a service provider to get a quote, discuss project needs, explore a partnership, find a job, etc.Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "send_message_to_provider" says "send": a word for sending, and what is sent cannot be taken back.
    • The server marks it destructive (destructiveHint: true).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • outboundThe name "send_message_to_provider" says "send": it sends or publishes something to other people.
    Description, as the server wrote it
    Reach out to a service provider to get a quote, discuss project needs, explore a partnership, find a job, etc. This tool sends the SAME message to one or more providers via `provider_ids` in a SINGLE call - do not call it multiple times. Never invent provider IDs and never ask the user to supply them. Message composition: - If the user provides a ready-made message, send it as-is without modifications. - If the user describes their intent without providing a message, compose one on their behalf based on their requirements and the conversation context. Keep the composed message concise and grounded strictly in the information provided by the user — do not add details that were not mentioned. - The same message and subject are sent to every provider in the call, so do not include any provider-specific information. Before calling with a composed message: - Show the user the recipients (provider names) and the full message text, and wait for their explicit confirmation. Call this tool only after the user confirms. - If the user asks for changes, show the revised message and wait for confirmation again. - Pass the confirmed message exactly as shown to the user, without modifications. Examples: - "Message the top 3 about my web development project" -> provider_ids=[<id_1>, <id_2>, <id_3>] (IDs of the top 3 providers shown earlier), compose message based on context, subject="Get a quote / discuss my project needs" - "Request a quote from all of these providers" -> provider_ids=[<all provider IDs shown above>], subject="Get a quote / discuss my project needs" - "Send to WebFX and Acme: I saw your profile and I'm interested in joining your team" -> provider_ids=[<webfx_id>, <acme_id>], message="I saw your profile and I'm interested in joining your team", subject="Find a job" The user must be logged in to Clutch to use this tool.

    Annotations the server declares

    • title: Send message to service providers
    • readOnlyHint: false
    • destructiveHint: true
    • openWorldHint: true
Changes things 1Claude Code: ask
  • recommend_service_providersUse this tool when the user is looking for service providers (companies, agencies, consultants, contractors, vendors) and describes requirements such as service type, industry, loc…Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Use this tool when the user is looking for service providers (companies, agencies, consultants, contractors, vendors) and describes requirements such as service type, industry, location, budget and pricing, company size, or specific focus areas (technologies/specialties). The tool returns a ranked list of providers that best match the criteria, including basic profile info and review/rating signals for comparison. Use `offset`/`limit` for pagination. Only the top 20 providers of a query are available: `offset` and `limit` that reach past them are trimmed, and an `offset` at or beyond that point returns no providers. Examples: - "Give me top web development companies for small businesses in the healthcare industry" -> service="Web Development", industry="Healthcare", client_type="Small Business( <$10M)" - "I need to improve SEO of my online store" -> service="SEO" - "I need SEO agencies that specialize in Shopify and have at least 10 reviews" -> service="SEO", focus_areas=["Shopify"], min_reviews=10

    Annotations the server declares

    • title: Recommend Service Providers
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: true
Only reads 3Show 3 read-only tools
  • get_provider_infoUse this tool whenever the user names a specific company (agency, consultant, contractor, vendor) and asks anything about it: who they are, how good they are, their rating or how m…Reads text others writeNo findings

    Why it is in this group

    • The name "get_provider_info" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Use this tool whenever the user names a specific company (agency, consultant, contractor, vendor) and asks anything about it: who they are, how good they are, their rating or how many reviews they have, whether they are Clutch verified or certified. Clutch profile data is not part of your general knowledge: call the tool even for companies you already know. Do not use it to find providers by criteria such as service, industry, location or budget: use `recommend_service_providers`. Do not use it to read individual reviews: use `get_service_provider_reviews`. Returns the provider's Clutch profile: rating and review counts, locations, description, pricing, Clutch Guarantee status, and Clutch Certifications. Examples: - "What do you know about Acme?" -> company_name="Acme" - "Tell me about Acme" -> company_name="Acme" - "What's Acme's rating?" -> company_name="Acme" - "Is Acme Clutch Certified?" -> company_name="Acme"

    Annotations the server declares

    • title: Get Provider Info
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: true
  • get_service_packagesUse this tool when the user wants to see service packages with fixed pricing and scope for a specific type of service.Reads text others writeNo findings

    Why it is in this group

    • The name "get_service_packages" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Use this tool when the user wants to see service packages with fixed pricing and scope for a specific type of service. This tool returns standardized packages offered by service providers, including pricing tiers, deliverables, and delivery timelines. Do NOT use this tool for custom project questions (e.g. "How much would it cost to build a custom app?"). It only returns providers' pre-defined, fixed-price packages, not a quote tailored to a specific project; use recommend_service_providers for those needs instead. Examples: - "Show me SEO packages" -> service="SEO" - "What web design packages can I get for $5,000?" -> service="Web Design", budget=5000 - "Marketing packages from agencies in New York" -> service="Digital Marketing", location="New York" Use `page`/`limit` for pagination.

    Annotations the server declares

    • title: List Service Packages
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: true
  • get_service_provider_reviewsUse this tool when the user asks to see client reviews for a specific service provider (company).Reads text others writeNo findings

    Why it is in this group

    • The name "get_service_provider_reviews" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • untrusted-inputThe name "get_service_provider_reviews" says "get" and "review": it reads comments, which other people can write.
    • untrusted-inputThe description's first sentence says "review": it reads comments, which other people can write.
    Description, as the server wrote it
    Use this tool when the user asks to see client reviews for a specific service provider (company). It returns detailed reviews that include project information, pricing, scope, client feedback, ratings, and more. Optionally filter reviews by a specific service.

    Annotations the server declares

    • title: Get Service Provider's Reviews
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: true

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write5
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out1
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 20, 2026, 18:32 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
2
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
https://bot.clutch.co/.well-known/oauth-protected-resource/mcp
Authorization servers
https://account.clutch.co/
Legacy HTTP+SSE transport
no
Dynamic client registration
yes
Client ID metadata documents
no
  • HighThe whole server

    The endpoint served tools/list without credentials, and the list has 2 tools that change things (1 destructive, 1 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://bot.clutch.co/mcp: tools/list returned 5 tools to an anonymous client, including send_message_to_provider (destructive), recommend_service_providers (write)

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

No check matched anything in these tool definitions. That is not a safety guarantee.

History

Changes to its tool definitions and to its remote endpoint, newest first.

No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.

Install

Pinned to version 1.0.3. Values in angle brackets are yours to fill in.

claude mcp add --transport http clutch https://bot.clutch.co/mcp
claude mcp add --transport http clutch https://bot.clutch.co/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__clutch__get_provider_info",
      "mcp__clutch__get_service_provider_reviews",
      "mcp__clutch__get_service_packages"
    ],
    "ask": [
      "mcp__clutch__recommend_service_providers"
    ],
    "deny": [
      "mcp__clutch__send_message_to_provider"
    ]
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as clutch. Review it before you use it.

Capability tags behind 5 rules
  • mcp__clutch__get_provider_info untrusted-input
  • mcp__clutch__get_service_provider_reviews untrusted-input
  • mcp__clutch__recommend_service_providers untrusted-input
  • mcp__clutch__send_message_to_provider untrusted-input, outbound
  • mcp__clutch__get_service_packages untrusted-input

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/co.clutch/mcp/verify?hash=f2f3a6e382b54d05c1e27680276a644b46a43461a7e5fe7f1a98c35ed3637502" | jq -e '.changed == false'

Pinned hash f2f3a6e382b5, from Nov 12, 2026, 09:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/co.clutch/mcp/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for co.clutch/mcp
[![Anlyon Radar](https://radar.anlyon.com/badge/co.clutch/mcp.svg)](https://radar.anlyon.com/servers/co.clutch/mcp)

Source: MCP Registry. Synced Oct 21, 2026, 17:46 UTC.

Clutch.co MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the Clutch.co MCP server safe?

No scan can promise that. What its definitions show: 5 tools, 2 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the Clutch.co MCP server delete data?

Yes. 1 tool can delete, cancel or revoke something: send_message_to_provider.

Can the Clutch.co MCP server do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the Clutch.co MCP server have?

5 tools: 1 destructive, 1 write, 3 read. send_message_to_provider, recommend_service_providers, get_provider_info, get_service_provider_reviews and get_service_packages.

Does the Clutch.co MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the Clutch.co MCP server send data to outside services?

1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): send_message_to_provider.

Has the Clutch.co MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 12, 2026.