Agent Reliability MCP Server

by agentreliability Your server? Claim it

answering

Agent Reliability is answering right now. Last checked 2 min ago. It exposes 8 tools. Last commit 30 Aug 2026.

Testing, benchmarking and auditing autonomous AI agents — methods, harnesses, evidence

Uptime history 10 days of history

10 days agonow

100.0%

Uptime 24h

92 of 92 checks

Tools

read from the server

1306 ms

Response time

average over 24h

Stars

last commit 30 Aug 2026

Nothing serious here today

Today is the operative word: we check Agent Reliability every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 2 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add agent-reliability --transport http https://agentreliability.dev/mcp?via=manifest

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "agent-reliability": {
      "url": "https://agentreliability.dev/mcp?via=manifest"
    }
  }
}

~/.codex/config.toml

[mcp_servers.agent-reliability]
url = "https://agentreliability.dev/mcp?via=manifest"

.cursor/mcp.json

{
  "mcpServers": {
    "agent-reliability": {
      "url": "https://agentreliability.dev/mcp?via=manifest"
    }
  }
}

.vscode/mcp.json

{
  "mcpServers": {
    "agent-reliability": {
      "url": "https://agentreliability.dev/mcp?via=manifest"
    }
  }
}

Available tools 8

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

answer

answer

Answer a question from the corpus. Returns the matched object's claims with sources and confidence — never an unsourced answer. Use this when the user asked a question in words; use search when you want to see the candidates yourself.

entity

get_entity

Fetch one knowledge object by id, with its claims and the sources each claim cites. Use this once search, answer or get_topic has given you an id.

latest

get_latest

Most recently verified knowledge objects (freshness signal). Use this to judge how current the corpus is, or to see what changed since you last read it.

overview

get_overview

Corpus overview: what this instance knows, counts by type, published tags, freshness. Use this first when you land here and do not yet know whether this corpus can answer your question.

get_related

Graph neighbours of an object: outgoing and incoming relations, each with its relation type. Use this after get_entity to widen an answer with adjacent objects.

search

Full-text search over the knowledge graph. Matching ignores accents and apostrophes, so query in the user's own words; every hit carries its relevance score and the fields it matched. Use this whenever you have a question rather than an id, then follow up with get_entity.

sources

get_sources

The instance's whole source registry, or just the sources cited by one object. Use this to check what a claim rests on, or to judge the corpus before trusting it.

topic

get_topic

List the knowledge objects carrying a tag (topics are content-backed tags). Use this to browse a known topic; use search when you have a question rather than a tag, and get_overview to see which tags exist.

Endpoints

URL	Transport	State	Latency	Checked
https://agentreliability.dev/mcp?via=manifest	streamable-http	answering	2095 ms	2 min ago

Alternatives to Agent Reliability

same job, measured the same way

Wcag Accessibility

by aditya-ariosity

A WCAG accessibility testing MCP for AI agents, Codex, Claude Code, and automated UI audits.

79 installs/wk local only

Colter

by mfbahc

Colter audits product pages for AI shopping agents and returns fixes, tests, and Evidence Packs.

97 installs/wk local only

Obyte MCP

by taump

Query Obyte mainnet and testnet: balances, units, autonomous agents, AA state, dry runs, tokens.

116 installs/wk local only

Agent Residue Evidence

by fantasyce

Report local task-scoped test and build residue without cleaning resources.

local only

MCP Eval Runner

by dbsectrainer

A standardized testing harness for MCP servers and agent workflows

50 installs/wk local only

RiskRover MCP

by be-sure-consulting

Draft PBS and quality assignments, assess test evidence, and submit guarded RiskRover updates.

311 installs/wk local only

Code Factory

by zrk222

Local proof facts for AI coding clients: intent, tests, Graph Ops, and review evidence.

3 727 installs/wk local only

Argus Testing — Autonomous QA MCP

by chriswu727

Autonomous QA MCP for web and macOS that tests like a real engineer, finds bugs, and verifies them.

190 installs/wk local only

Agent Reliability — questions

Answers built from our own checks of this server.

What can Agent Reliability do?

It exposes 8 tools, read directly from the server on our last check. Among them: answer, get_entity, get_latest, get_overview, get_related, get_sources and 2 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →

Is Agent Reliability working right now?

We send a real MCP handshake every 15 minutes. Over the last 24 hours 92 of 92 checks got a reply (100.0%), average response time 1306 ms. The bar chart above shows every period we have measured.

How do I connect Agent Reliability?

Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.

Does Agent Reliability need an API key?

No. Agent Reliability completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 8 of them are readable on this page. This is what we observed, not what the docs claim.

How fast is Agent Reliability?

It answers our handshake in 1306 ms on average, which is faster than 3% of all working MCP servers we measure. That is on the slow side — worth knowing if the tool sits inside an interactive loop. The comparison comes from our own checks across the whole registry, every 15 minutes.

Is Agent Reliability open source?

Yes — it is published under the CC-BY-4.0 licence and 0 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.