List your agent

Agent Tested

MCP server · hosted · v1.0.0 · dev.agenttested/agent-tested
Online · tested 18m agoNEW · 54m agoSeen in the registry 9m ago

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

What it does

Agent Tested is an MCP server, a connector that lets an AI assistant use it as a tool. It is hosted: an assistant connects to it over the internet, nothing to install.

From the publisher's description, Electra Index matched it to one capability: security scanning. That makes it a candidate for tasks such as review pull requests or scan code for vulnerabilities.

Facts come from the Official MCP Registry, as declared by the publisher. Capabilities are matched automatically (low confidence) and are not a test of the tool.

At a glance

Hosted (remote)YES
Local installNO
Version1.0.0
PriceNot in the registry
First seen21 Oct 2026
Last checked9m ago

How to connect

As declared in the Official MCP Registry · hosted endpoint tested by Electra Index 18m ago (live check)

Hosted endpoint

  • https://agenttested.dev/mcp streamable-http

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

MCP settings (Claude Desktop, Cursor and other MCP clients)

{
  "mcpServers": {
    "agent-tested": {
      "url": "https://agenttested.dev/mcp"
    }
  }
}

Live check

Electra Index connected to the hosted endpoint 18m ago

ONLINE Agent Tested answered an MCP connection on 21 Oct 2026 and introduced itself as agent-tested 1.0.0 (MCP protocol 2025-06-18).

7 tools offered to AI assistants

  • search_tools · 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 r
  • get_tool · 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 fl
  • check_outages · Current status and incidents from the last 7 days for 17 big AI providers (OpenAI, Anthropic, Gemini, xAI, Mistral, Cursor, GitHub Copilot, Replit, v0, Lovable, Bolt, Hugging Face, Perplexity, ElevenLabs, Midjourney, Supabase, Windsurf), ta
  • is_dangerous · 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 'Da
  • list_lab_queue · 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.
  • submit_field_report · 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 pre
  • suggest_improvement · 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 c

What "online" means: the server answered an MCP connection at the time of the check. It is not a guarantee of security, quality or continuous uptime. How we test: we open an MCP session and ask for the tool list, as an AI assistant would. We never run a tool and never send a key. Checked every few days. Method

Tasks it helps with

Share of each task's required capabilities it covers
Review pull requests
Security Scanning
50%
Scan code for vulnerabilities
Security Scanning
50%

Similar tools

Listed for the same task: review pull requests
  • diffpilotREMOTELOCAL
    MCP server for PR code review, commit messages, changelogs, and secret detection
  • Code review as an MCP server — structured reviews with OWASP security scanning
  • StrixREMOTELOCAL
    AI pentesting: run scans, triage vulnerabilities, review PRs, manage schedules and assets
  • PeriscopeREMOTELOCAL
    MCP broker into your live Neovim/diver config: LSP, formatters, linters, DAP, MATE attention
  • CIRCL Vulnerability-Lookup — aggregated vulnerability records
  • SkillTotalREMOTELOCAL
    Deterministic security scan of MCP servers, agent skills and npm/PyPI packages. Runs locally

Ready-made AI agents

An MCP server is a connector you add to your own assistant. These are finished products that do the same job for you:

Facts & evidence

Each fact shows where it was seen and when.
FactValueEvidenceSourceLast confirmed
Hosted endpointhttps://agenttested.dev/mcpDECLAREDSRC-001 Official MCP Registry9m ago
Local install (package)noDECLAREDSRC-001 Official MCP Registry9m ago
Remote access (hosted)yesDECLAREDSRC-001 Official MCP Registry9m ago
Websitehttps://agenttested.devDECLAREDSRC-001 Official MCP Registry9m ago
Registry statusactiveDECLAREDSRC-001 Official MCP Registry9m ago
Version1.0.0DECLAREDSRC-001 Official MCP Registry9m ago
MCP serveryesDECLAREDSRC-001 Official MCP Registry9m ago

Change history

  • NEW21 Oct 2026
    first seen in the index

Is this page accurate?

Flag it and our robot re-checks the official source. Reports never change a score.

Questions about Agent Tested

How do I connect Agent Tested?

Use the hosted endpoint https://agenttested.dev/mcp in your assistant's MCP settings. The exact settings are in "How to connect" above, as declared in the Official MCP Registry.

What tools does Agent Tested offer?

When Electra Index connected on 21 Oct 2026, it listed 7 tools: search_tools, get_tool, check_outages, is_dangerous, list_lab_queue, submit_field_report, suggest_improvement. The full list is in "Live check" above.

Is Agent Tested online?

Yes. Its hosted endpoint answered an MCP connection from Electra Index 18m ago.

What can I use Agent Tested for?

Based on its description, it is most relevant to: review pull requests, scan code for vulnerabilities.