Agent Reliability is a remote MCP server that gives an AI agent 9 tools, among them answer, compare, get_entity. It answers at https://agentreliability.dev/mcp?via=manifest over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 6 of 6 times since 10 September 2026; the last check, on 19 October 2026, succeeded.
Testing, benchmarking and auditing autonomous AI agents — methods, harnesses, evidence
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
answer | 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 missin Inputs: 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 Inputs: ids |
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. An unknown id is not a dead end: the answer names near-miss ids you can retry with. Inputs: id |
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. It ranks by verification date and ignores your topic entirely — use search or get_topic Inputs: limit |
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. 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_curs Inputs: id, limit, cursor |
get_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_cu Inputs: object_id, tier, host, accessed_since, limit, cursor |
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 truncated Inputs: tag, limit, cursor |
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 thi Inputs: query, limit |
Every block below points at https://agentreliability.dev/mcp?via=manifest. Pick your client and copy.
claude mcp add --transport http agent-reliability https://agentreliability.dev/mcp?via=manifest
{
"mcpServers": {
"agent-reliability": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://agentreliability.dev/mcp?via=manifest"]
}
}
}{
"mcpServers": {
"agent-reliability": {
"url": "https://agentreliability.dev/mcp?via=manifest"
}
}
}{
"servers": {
"agent-reliability": {
"type": "http",
"url": "https://agentreliability.dev/mcp?via=manifest"
}
}
}{
"context_servers": {
"agent-reliability": {
"url": "https://agentreliability.dev/mcp?via=manifest"
}
}
}{
"mcpServers": {
"agent-reliability": {
"serverUrl": "https://agentreliability.dev/mcp?via=manifest"
}
}
}{
"mcpServers": {
"agent-reliability": {
"url": "https://agentreliability.dev/mcp?via=manifest"
}
}
}name: Agent Reliability
version: 0.0.1
schema: v1
mcpServers:
- name: Agent Reliability
type: streamable-http
url: https://agentreliability.dev/mcp?via=manifest{
"mcpServers": {
"agent-reliability": {
"httpUrl": "https://agentreliability.dev/mcp?via=manifest"
}
}
}{
"mcpServers": {
"agent-reliability": {
"type": "http",
"url": "https://agentreliability.dev/mcp?via=manifest"
}
}
}{
"mcpServers": {
"agent-reliability": {
"url": "https://agentreliability.dev/mcp?via=manifest"
}
}
}goose://extension?url=https%3A%2F%2Fagentreliability.dev%2Fmcp%3Fvia%3Dmanifest&type=streamable_http&id=agent-reliability&name=Agent%20Reliability
It answered our last check on 19 October 2026 in 285 ms. Over 6 checks since 10 September 2026 it answered 6. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by agentreliability.dev and served from agentreliability.dev, the vendor's own domain: https://agentreliability.dev/mcp?via=manifest.
9, as returned by the server's own tools/list on 11 September 2026: answer, compare, get_entity, get_latest, get_overview, get_related, get_sources, get_topic, and 1 more.
It answered our last check on 19 October 2026 in 285 ms. Over 6 checks since 10 September 2026 it answered 6.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://agentreliability.dev/mcp?via=manifest. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: dev.agentreliability. Endpoint host: agentreliability.dev. ARD identifier: urn:air:dev.agentreliability:mcp:agent-reliability.
First indexed 10 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.