Skip to content

AgentoolRank MCP server

com.agentoolrank/agent-toolsagentoolrank.comstreamable-httpv1.1.1Scanned

Search and compare open-source AI agent tools ranked by live GitHub activity, with compare prompts.

9 tools: 5 change things and 4 only read.

Tools: 0 delete, 0 irreversible, 5 write, 4 read.
  • Reads private data · 4
  • Reads text others write · 1
  • Can send data out · 1
  • No findings

Sign-in required, no OAuth metadata. Remote posture

Anlyon alternative

5 of these tools change something. Run those as governed actions.

Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.

Anlyon Radar does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.

Import an OpenAPI spec →

What the AgentoolRank MCP server can do

The AgentoolRank MCP server is published by agentoolrank.com, a domain the MCP Registry verified. It has 9 tools. It can create or change data (5 tools: submit_tool, recommend_directories, next_directory, report_result and 1 more), but cannot delete data. 4 tools only read.

4 tools read private data (search_tools, get_tool, get_alternatives and 1 more); 1 tool brings in text other people can write (get_submission_status); 1 tool can send data out of your system (submit_tool). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.

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

Last scanned Oct 29, 2026, version 1.1.1.

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.

9 tools

Changes things 5Claude Code: ask
  • my_progress[Launch directories] Use this after report_result or to resume a session; requires the Submit Kit key.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    [Launch directories] Use this after report_result or to resume a session; requires the Submit Kit key. Returns product_type, cap, sites, progress_page and counts: issued (total handed out), unreported, submitted, listed_reported, rejected, failed and skipped. Outstanding sites have status 'issued' in sites. Remaining allowance is cap minus issued, not a returned field or a guarantee of matching directories. Not for AgentoolRank listing review status — that is get_submission_status.
  • next_directory[Launch directories] Use this when working through launch directories with a required Submit Kit key.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    [Launch directories] Use this when working through launch directories with a required Submit Kit key. Returns exactly one next directory when available; submit there, then call report_result. May return report_first or done instead. At most 3 unreported sites, up to 50 per key; product_type is bound on first issuance. For a free overview list, use recommend_directories.
  • recommend_directories[Launch directories] Use this when you need a free overview of the best-fit launch directories for a product_type: top 5, no key required, with conditions and submission steps.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    [Launch directories] Use this when you need a free overview of the best-fit launch directories for a product_type: top 5, no key required, with conditions and submission steps. An optional valid Submit Kit key ($29) returns the full overview and directories to avoid. To work through the full list one directory at a time with a Submit Kit key, use next_directory instead.
  • report_result[Launch directories] Use this when recording an outcome for a domain issued by next_directory, not submitting a tool to AgentoolRank.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    [Launch directories] Use this when recording an outcome for a domain issued by next_directory, not submitting a tool to AgentoolRank. Requires the same Submit Kit key, that domain and status: submitted, listed, rejected, failed or skipped; listing_url and note are optional. Records the outcome and clears that site's unreported slot. Reporting 'listed' is only a lead: it counts toward listing rate only after our daily check finds it live.
  • submit_tool[Tool directory] List an AI agent tool (framework, coding agent, MCP server, memory/RAG, evals, browser agent...) on AgentoolRank for free.Can send data outNo findings

    Why it is in this group

    • The name "submit_tool" says "submit": a word for a change.

    What it can reach

    • outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
    Description, as the server wrote it
    [Tool directory] List an AI agent tool (framework, coding agent, MCP server, memory/RAG, evals, browser agent...) on AgentoolRank for free. The free listing is queued; the response lists every paid option (price, days to go live, checkout_url for your human to pay) and recommends the cheapest one that fits max_budget_usd / deadline_days. Returns submission_id + status_token for get_submission_status, and message_for_human: a summary to forward to your human.
Only reads 4Show 4 read-only tools
  • get_alternatives[Tool directory] Use this when you need alternatives to a known AI agent tool, not launch directories.Reads private dataNo findings

    Why it is in this group

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

    What it can reach

    • private-dataThe description's first sentence says "directory": it reads files.
    Description, as the server wrote it
    [Tool directory] Use this when you need alternatives to a known AI agent tool, not launch directories. Pass slug, the tool identifier returned by search_tools (for example, dify), not a URL or directory domain. Returns the source tool slug and its recorded alternatives with GitHub stats for comparison.
  • get_submission_status[Tool directory] Use this when checking the AgentoolRank review status of a tool you submitted via submit_tool.Reads private dataReads text others writeNo findings

    Why it is in this group

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

    What it can reach

    • private-dataThe description's first sentence says "directory": it reads files.
    • untrusted-inputThe description's first sentence says "review": it reads comments, which other people can write.
    Description, as the server wrote it
    [Tool directory] Use this when checking the AgentoolRank review status of a tool you submitted via submit_tool. Requires submission_id and status_token from that submission; returns review status, queue position and listing URL when available. Not for launch-directory progress — that is my_progress.
  • get_tool[Tool directory] Get details for one tool by slug (from search_tools): GitHub stats, capabilities, best-for, limitations and alternatives.Reads private dataNo findings

    Why it is in this group

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

    What it can reach

    • private-dataThe description's first sentence says "directory": it reads files.
    Description, as the server wrote it
    [Tool directory] Get details for one tool by slug (from search_tools): GitHub stats, capabilities, best-for, limitations and alternatives.
  • search_tools[Tool directory] Search open-source AI agent tools (frameworks, coding agents, memory, RAG, observability, MCP servers) ranked by GitHub activity.Reads private dataNo findings

    Why it is in this group

    • The name "search_tools" says "search": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "directory": it reads files.
    Description, as the server wrote it
    [Tool directory] Search open-source AI agent tools (frameworks, coding agents, memory, RAG, observability, MCP servers) ranked by GitHub activity. Returns stars, 30-day star growth, capabilities and alternatives.

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.

4 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 outbound tool breaks every one.

Reads private data4
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write1
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.
deny to break every path
{
  "permissions": {
    "deny": [
      "mcp__agent-tools__submit_tool"
    ]
  }
}

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.

Sign-in required, no OAuth metadata

Looked at Nov 20, 2026, 18:33 UTC, unchanged since Nov 6, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
503
tools/list served without credentials
no
Tools that change things, listed without credentials
0
Protocol version
not observed
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed

The probe stopped: initialize answered HTTP 503.

Posture changes

  1. Nov 6, 2026
    • HTTP status of an anonymous initialize: 200 to 503
    • tools/list served without credentials: yes to no
    • Tools that change things, listed without credentials: 5 to 0
    • Protocol version: 2025-06-18 to none

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.

  1. PostureRemote posture changed. HTTP status of an anonymous initialize: 200 -> 503; tools/list served without credentials: yes -> no; Tools that change things, listed without credentials: 5 -> 0 (and 1 more).View diff
    • HTTP status of an anonymous initialize: 200 to 503
    • tools/list served without credentials: yes to no
    • Tools that change things, listed without credentials: 5 to 0
    • Protocol version: 2025-06-18 to none

Install

Pinned to version 1.1.1. Values in angle brackets are yours to fill in.

claude mcp add --transport http agent-tools https://agentoolrank.com/api/mcp
claude mcp add --transport http agent-tools https://agentoolrank.com/api/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__agent-tools__search_tools",
      "mcp__agent-tools__get_tool",
      "mcp__agent-tools__get_alternatives",
      "mcp__agent-tools__get_submission_status"
    ],
    "ask": [
      "mcp__agent-tools__submit_tool",
      "mcp__agent-tools__recommend_directories",
      "mcp__agent-tools__next_directory",
      "mcp__agent-tools__report_result",
      "mcp__agent-tools__my_progress"
    ],
    "deny": []
  }
}

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 agent-tools. Review it before you use it.

Capability tags behind 5 rules
  • mcp__agent-tools__search_tools private-data
  • mcp__agent-tools__get_tool private-data
  • mcp__agent-tools__get_alternatives private-data
  • mcp__agent-tools__submit_tool outbound
  • mcp__agent-tools__get_submission_status private-data, 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/com.agentoolrank/agent-tools/verify?hash=9882259c6cdfd9394c5644a9b7da2e57cfb879cc92bcb9cb97657d9de9884ccb" | jq -e '.changed == false'

Pinned hash 9882259c6cdf, from Oct 29, 2026, 02:18 UTC.

Watch

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

https://radar.anlyon.com/servers/com.agentoolrank/agent-tools/changes.xml

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

Badge

Anlyon Radar badge for com.agentoolrank/agent-tools
[![Anlyon Radar](https://radar.anlyon.com/badge/com.agentoolrank/agent-tools.svg)](https://radar.anlyon.com/servers/com.agentoolrank/agent-tools)

Source: MCP Registry · repository. Synced Oct 21, 2026, 17:48 UTC.

AgentoolRank MCP server: questions and answers

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

Is the AgentoolRank MCP server safe?

No scan can promise that. What its definitions show: 9 tools, 5 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 AgentoolRank MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the AgentoolRank 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 AgentoolRank MCP server have?

9 tools: 5 write, 4 read. submit_tool, recommend_directories, next_directory, report_result, my_progress, search_tools, get_tool, get_alternatives and 1 more.

Does the AgentoolRank MCP server need sign-in or OAuth?

Its remote endpoint did not answer the last anonymous look.

Does the AgentoolRank 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): submit_tool.

Has the AgentoolRank MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Oct 29, 2026.