Agent Reliability is a Model Context Protocol (MCP) server: Testing, benchmarking and auditing autonomous AI agents — methods, harnesses, evidence. As an MCP server it plugs straight into AI assistants, exposing its functionality as tools the model can invoke on your behalf.
It's a hosted (remote) server — point your client at https://agentreliability.dev/mcp?via=manifest and you're connected, with nothing to install locally. The current release is v0.6.14, published under the CC-BY-4.0 license, with source at citarium/agentreliability-mcp on GitHub.
You'll find Agent Reliability in the AI & Agents category here on mcp.site; it connects to Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Zed, and any other MCP client — see the install snippets below. If you maintain Agent Reliability for agentreliability.dev, claim this listing to verify ownership, earn the Verified badge, and keep the details current.
