Developer · Remote MCP server
Agent Reliability
Testing, benchmarking and auditing autonomous AI agents - methods, harnesses, evidence.
What the MCP Registry states
The entry as published to the official MCP Registry (read 2026-10-04), latest version.
- Registry name
dev.agentreliability/agent-reliability- Version
- 0.6.14
- Status
- Active
- Category
- developer
- Transport
- Streamable HTTP
- Published
- 2026-08-23
- Updated
- 2026-08-23
- Publisher
- dev.agentreliability
- Namespace
- Namespace verified by the MCP Registry via the domain agentreliability.dev · how
- Repository
- github.com/citarium/agentreliability-mcp
- Source
- Registry API entry
Remote endpoints
| Transport | URL | Headers declared |
|---|---|---|
| Streamable HTTP | https://agentreliability.dev/mcp?via=manifest | None |
Live check
This directory connected to each remote endpoint and asked for its list of tools. The check connects and lists tools only; it doesn't run tools, sign in or test security.
- Reachable
- Yes (HTTP 200)
- Handshake
- dev.agentreliability/agent-reliability 0.9.2 · protocol 2025-06-18
- Tools discovered
- 9:
search,get_entity,get_topic,answer,get_sources,get_related,get_latest,get_overview,compare - Checked on
- 2026-10-05
How to connect Agent Reliability
Agent Reliability is a remote MCP server: there is nothing to install. Its endpoint is https://agentreliability.dev/mcp?via=manifest, served over Streamable HTTP. In an assistant that accepts remote MCP servers (often under a setting named connectors, integrations or tools), add a new server and give it this URL; in a client configured by file, add it as a remote (HTTP) server with the same URL.
No headers are declared in the registry entry. If the server needs you to sign in, a client that supports MCP authorization opens the service's own sign-in page when it first connects.
Derived from the registry entry; the live check above only shows whether the endpoint answered. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect
More developer servers
| Server | Runs |
|---|---|
| Agent Ready Website CheckCheck whether a website is readable by AI agents: robots, llms.txt, sitemap, HTML. Bounded. | Remote · HTTPLive check: ✓ handshake |
| Agent RecallCorrection-first agent memory. Precision KPI tracks if agents heed warnings. 5 layers, local-only. | Local · stdio |
| Agent Recall TrailPrivate Agent memory and governed shared knowledge. | Local · stdio |
| Agent Release AuditorDeterministic release gate for AI-written code and coding agents. | Local · stdio |
| Agent Rescue Desk Production TriageRead-only triage for n8n, MCP, webhook, and AI agent workflow production failures. | Remote · HTTPLive check: ✓ handshake |
| Agent SecZero-install security baseline for AI coding agents - OWASP/CWE-cited rules over MCP. | Remote · HTTPLive check: ✓ handshake |
| Agent Security Scanner MCPSecurity layer for AI agents: blocks prompt injection, detects fake packages, scans vulnerabilities. | Local · stdio |
| Agent Skill & Config Security AuditScan AI agent skills and configs for hidden Unicode, prompt injection and exfiltration. | Remote · HTTPLive check: sign-in required |