Agent Reliability
Testing, benchmarking and auditing autonomous AI agents — methods, harnesses, evidence
Reviews
No review yet. Used Agent Reliability? Be the first to help others choose.What it does
Agent Reliability 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.
No capability identified yet from its description.
Facts come from the Official MCP Registry, as declared by the publisher. Capabilities are matched automatically (low confidence). None of this is a test of the tool.
At a glance
How to connect
As declared in the Official MCP Registry · hosted endpoint tested by Electra Index 1d ago (live check)Hosted endpoint
https://agentreliability.dev/mcp?via=manifeststreamable-http
In Claude Code: claude mcp add --transport http agent-reliability https://agentreliability.dev/mcp?via=manifest
MCP settings (Claude Desktop, Cursor and other MCP clients)
{
"mcpServers": {
"agent-reliability": {
"url": "https://agentreliability.dev/mcp?via=manifest"
}
}
}Live check
Electra Index connected to the hosted endpoint 1d agoONLINE Agent Reliability answered an MCP connection on 15 Nov 2026 and introduced itself as dev.agentreliability/agent-reliability 0.9.2 (MCP protocol 2025-06-18).
9 tools offered to AI assistants
search· Full-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 and a score. BM25 relevance: each query term is weighted by how RARE it is in thiget_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. An unknown id is not a dead end: the answer names near-miss ids you can retry with.get_topic· List 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 per call — a page over budget comes back shorter WITH a next_cursor, never truncatedanswer· Answer 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. When the corpus cannot answer, answered is false and abstention_reason plus missinget_sources· The 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 budget of about 64 KB per call — a page over budget comes back shorter WITH a next_cuget_related· Graph neighbours of an object: outgoing and incoming relations, each with its relation type. PAGED: 25 relations by default, 200 at most, and a response budget of about 64 KB per call — a page over budget comes back shorter WITH a next_cursget_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. It ranks by verification date and ignores your topic entirely — use search or get_topicget_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.compare· Two 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 not say), the tags they share, the relations that run between them, the neighbo
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
Is this your server? Monitoring Pro: a check every 30 minutes and an email within the hour when it stops answering. Launch offer: $39.99 once, for life.
Facts & evidence
Each fact shows where it was seen and when.| Fact | Value | Evidence | Source | Last confirmed |
|---|---|---|---|---|
| Hosted endpoint | https://agentreliability.dev/mcp?via=manifest | DECLARED | SRC-001 Official MCP Registry | 23h ago |
| Local install (package) | no | DECLARED | SRC-001 Official MCP Registry | 23h ago |
| Remote access (hosted) | yes | DECLARED | SRC-001 Official MCP Registry | 23h ago |
| Repository | https://github.com/citarium/agentreliability-mcp | DECLARED | SRC-001 Official MCP Registry | 23h ago |
| Registry status | active | DECLARED | SRC-001 Official MCP Registry | 23h ago |
| Version | 0.6.14 | DECLARED | SRC-001 Official MCP Registry | 23h ago |
| MCP server | yes | DECLARED | SRC-001 Official MCP Registry | 23h ago |
Change history
Is this page accurate?
Flag it and our robot re-checks the official source. Reports never change a score.Is Agent Reliability still online?
Free alerts · no account▲ 0Do you run Agent Reliability? Know when it stops answering
For publishers · optionalIts hosted endpoint can be monitored. Monitoring Pro connects every 30 minutes like an AI assistant, emails you within the hour when it stops answering, keeps a 90-day availability history and adds your answer rate to your badge.
Monitoring never changes a score or a rank.
Questions about Agent Reliability
How do I connect Agent Reliability?
Use the hosted endpoint https://agentreliability.dev/mcp?via=manifest 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 Reliability offer?
When Electra Index connected on 15 Nov 2026, it listed 9 tools: search, get_entity, get_topic, answer, get_sources, get_related, get_latest, get_overview and more. The full list is in "Live check" above.
Is Agent Reliability online?
Yes. Its hosted endpoint answered an MCP connection from Electra Index 1d ago.