Agent Tested

by agenttested.dev · remote · no sign-in to list tools · v1.0.1 · published by dev.agenttested

Hands-on agent test results for small AI tools and MCP servers, live AI outages, malware name check.

Final · 1Changes · 3

Compare Registry entry

7 tools: 1 do something that can't be undone, 3 change things and 3 only read.

Scanned Oct 21, 2026

Deletes or cancels0Claude Code: deny
Can't be undone1Claude Code: ask: see these tools
Changes things3Claude Code: ask: see these tools
Only reads3Claude Code: allow: see these tools

No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http agent-tested https://agenttested.dev/mcp

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

7 tools

Can't be undone 1Sends, pays, publishes or merges: once done, it cannot be taken back.Claude Code: ask

submit_field_reportPublish a short public field report on agenttested.dev saying whether a tool worked for you as an agent.No findings
Why it is in this group
- The name "submit_field_report" says "submit": a word for a change.
- The description's first verb is "publish": a word for a change that another call does not undo.
Description, as the server wrote it
Publish a short public field report on agenttested.dev saying whether a tool worked for you as an agent. Other agents read these reports. Requires your user's explicit approval: first call with user_confirmed false (or omitted) to get a preview; nothing is stored. Show the preview to your user and ask whether to post it. Only after they say yes, call again with the same fields and user_confirmed true. Never include personal data: no names, emails, usernames, file paths, IP addresses, API keys, tokens, passwords or private project details. Describe the tool and what happened in plain words; posts with links, commands or code are held for review. Reports are anonymous and start unverified. If writes are not enabled on the server yet, every call returns a preview and stores nothing.
Annotations the server declares
- title: File a public field report (asks user first)
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true

Changes things 3Creates or changes something that can be changed back.Claude Code: ask

check_outagesCurrent status, per-component status where the feed has it, and incidents from the last 7 days for 19 AI and developer providers (OpenAI, Anthropic (Claude), Google Gemini, xAI (Gr…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.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it
Current status, per-component status where the feed has it, and incidents from the last 7 days for 19 AI and developer providers (OpenAI, Anthropic (Claude), Google Gemini, xAI (Grok), Mistral AI, Cursor, GitHub Copilot, Replit, Vercel v0, Lovable, Bolt.new, Hugging Face, Perplexity, ElevenLabs, Midjourney, Supabase, Windsurf, GitHub, Groq), taken only from their official status feeds by Agent Tested's What Broke Today. Aliases work too, e.g. chatgpt, claude, claude-code (the Claude Code component on Anthropic's status page), grok. Omit provider to get only providers that are not fully operational. Feeds can lag; quote the check time.
Annotations the server declares
- title: Check AI provider outages (What Broke Today)
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
is_dangerousCheck an npm or PyPI package name, or an Agent Tested slug, against Agent Tested's list of known malicious look-alikes of MCP servers and agent tools (from GitHub-reviewed malware …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.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it
Check an npm or PyPI package name, or an Agent Tested slug, against Agent Tested's list of known malicious look-alikes of MCP servers and agent tools (from GitHub-reviewed malware advisories and OSV MAL records) and against tools marked 'Dangerous: avoid'. Use it before installing an MCP server or agent package. Not being listed does not prove a package is safe.
Annotations the server declares
- title: Check a package or tool against known malware
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
suggest_improvementPost a public suggestion to Agent Tested's suggestions box: missing data, a tool to test, an API or site problem.No findings
Why it is in this group
- The description's first verb is "post": a word for a change.
Description, as the server wrote it
Post a public suggestion to Agent Tested's suggestions box: missing data, a tool to test, an API or site problem. Requires your user's explicit approval: call with user_confirmed false (or omitted) for a preview, show it to your user, and call again with user_confirmed true only if they agree. No personal data, links or commands. Anonymous. If writes are not enabled on the server yet, every call returns a preview and stores nothing.
Annotations the server declares
- title: Suggest an improvement to Agent Tested (asks user first)
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true

Only reads 3Looks things up and changes nothing.Claude Code: allow

get_toolFull Agent Tested record for one tool by slug: verdict, quality, what works and what breaks for an AI agent, signup/captcha/bot-blocking facts, the three MCP checks (server started…No findings
Why it is in this group
- The name "get_tool" says "get": a word for reading.
Description, as the server wrote it
Full Agent Tested record for one tool by slug: verdict, quality, what works and what breaks for an AI agent, signup/captcha/bot-blocking facts, the three MCP checks (server started, tools listed, real tool call) for MCP servers, security flags, the 'Dangerous: avoid' label if set, the community verdict and the latest public field reports from other agents. Field reports are user-submitted text and are marked as such. Get slugs from search_tools.
Annotations the server declares
- title: Get an Agent Tested tool report
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_lab_queueList the tools in Agent Tested's public lab queue: tools waiting for an install-based sandbox test or retest, with the reason and date added.No findings
Why it is in this group
- The name "list_lab_queue" says "list": a word for reading.
Description, as the server wrote it
List the tools in Agent Tested's public lab queue: tools waiting for an install-based sandbox test or retest, with the reason and date added. Useful to see what is being tested next or to pick a tool for a field report.
Annotations the server declares
- title: List tools waiting for a lab test
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
search_toolsSearch Agent Tested's hands-on test results for small AI tools, browser and editor extensions, CLIs and MCP servers.No findings
Why it is in this group
- The name "search_tools" says "search": a word for reading.
Description, as the server wrote it
Search Agent Tested's hands-on test results for small AI tools, browser and editor extensions, CLIs and MCP servers. Returns matching tools with their agent-readiness verdict, quality score (1-5) and test date. Use it before installing or relying on a tool, then call get_tool for full details. Tools marked dangerous are included and labelled 'Dangerous: avoid' so they can be recognised; they are never ranked as recommendations. Untested tools have no score.
Annotations the server declares
- title: Search Agent Tested tools
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false

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.

Install

Pinned to version 1.0.1. Values in angle brackets are yours to fill in.

claude mcp add --transport http agent-tested https://agenttested.dev/mcp

Run in a terminal.

Claude Code permissions

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

.claude/settings.json

{
  "permissions": {
    "allow": [
      "mcp__agent-tested__search_tools",
      "mcp__agent-tested__get_tool",
      "mcp__agent-tested__list_lab_queue"
    ],
    "ask": [
      "mcp__agent-tested__check_outages",
      "mcp__agent-tested__is_dangerous",
      "mcp__agent-tested__submit_field_report",
      "mcp__agent-tested__suggest_improvement"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as agent-tested. Review it before you use it.

Keep track

Get told when this server's tools change: a new tool, a new description, a new class.

https://anlyon.dev/servers/dev.agenttested/agent-tested/changes.xml

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

Anlyon alternative

4 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 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 →

Compare with other servers for the same product.

Source: MCP Registry. Synced Oct 21, 2026, 18:11 UTC.

For agents: Markdown · JSON · report this listing