dev.agentreliability/agent-reliability
up checked
Unclaimed · Unverified
Agent searches it appeared in, last 30 days: 0. Run this server? Claim the listing: verified label, uptime alerts and analytics.
Publisher-provided title
Agent Reliability
Publisher-provided description
Testing, benchmarking and auditing autonomous AI agents — methods, harnesses, evidence
Summary by lookupd
Queries a corpus of verified knowledge on AI agent testing and auditing: search, fetch entities, compare objects, and inspect sources and…
Install
Claude Code, remote (streamable-http)
claude mcp add --transport http agent-reliability 'https://agentreliability.dev/mcp?via=manifest'
Codex, remote (streamable-http)
codex mcp add agent-reliability --url 'https://agentreliability.dev/mcp?via=manifest'
Cursor, remote (streamable-http) → .cursor/mcp.json
{
"mcpServers": {
"agent-reliability": {
"url": "https://agentreliability.dev/mcp?via=manifest"
}
}
}Other clients: docs. Or tell your agent: Set up lookupd for me: read https://lookupd.com/agent.md and follow it.
Tools (9 tools)
Publisher-provided text
searchFull-text search over the knowledge graph. Matching ignores accents and apostrophes, so query in the user's own words; every hit carries the fields it matched aget_entityFetch 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. An unknown idget_topicList the knowledge objects carrying a tag (topics are content-backed tags). PAGED: 25 objects by default, 200 at most, and a response budget of about 64 KB peranswerAnswer a question from the corpus, or refuse. Returns only the claims that bear on the question, each with the sources it cites and its editorial confidence. Whget_sourcesThe instance's source registry — each entry with its evidence tier, reliability and access date. PAGED: 25 entries by default, 200 at most, and a response budgeget_relatedGraph neighbours of an object: outgoing and incoming relations, each with its relation type. PAGED: 25 relations by default, 200 at most, and a response budgetget_latestMost 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. It rankget_overviewCorpus 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 corpuscompareTwo to six knowledge objects side by side: their cards, every indexed attribute as a matrix (the same fields api/index.json publishes, null where an object does
Details
- Version: 0.6.14
- Transports: streamable-http
- Uptime (7 days): 100%
- Median latency: 1175 ms
- First indexed:
- Last seen in registry:
- Repository: https://github.com/citarium/agentreliability-mcp
Badge for your README
Shows this live status and links here; updates hourly.
[](https://lookupd.com/servers/dev.agentreliability/agent-reliability)
- 62071 servers
- Last crawl: 2026-11-11T16:39:06.253Z
- API base:
https://api.lookupd.com - MCP URL:
https://api.lookupd.com/mcp