Agent Reliability MCP server
dev.agentreliability/agent-reliabilityagentreliability.devstreamable-httpv0.6.14Scanned
Testing, benchmarking and auditing autonomous AI agents — methods, harnesses, evidence
9 tools: 1 change things and 8 only read.
- Reads private data · 0
- Reads text others write · 0
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here changes things. Govern it.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the Agent Reliability MCP server can do
The Agent Reliability MCP server is published by agentreliability.dev, a domain the MCP Registry verified. It has 9 tools. It can create or change data (1 tool: answer), but cannot delete data. 8 tools only read.
None of its tools reads private data, brings in text other people write, or sends data out.
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 11, 2026, version 0.6.14.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
9 tools
Changes things 1Claude Code: ask
answerAnswer a question from the corpus, or refuse.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it 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 missing_topics say what was not covered — a refusal is a real result here, not an error. Use this when the user asked a question in words; use search when you want to see the candidates yourself.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
Only reads 8Show 8 read-only tools
compareTwo 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 …No findings
Why it is in this group
- The name "compare" says "compare": a word for reading.
Description, as the server wrote it 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 neighbours they have in common, and each one's claims with sources and confidence. Use this when the question is 'X vs Y', 'is X the same as Y' or 'how does X differ from Y' — search or get_topic first if you only have names, then pass the ids. An unknown id lands in `missing` with a near-miss suggestion and the rest are still compared.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_entityFetch one knowledge object by id, with its claims and the sources each claim cites.No findings
Why it is in this group
- The name "get_entity" says "get": a word for reading.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_latestMost recently verified knowledge objects (freshness signal).No findings
Why it is in this group
- The name "get_latest" says "get": a word for reading.
Description, as the server wrote it 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 when you want objects that are relevant rather than recent.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_overviewCorpus overview: what this instance knows, counts by type, published tags, freshness.No findings
Why it is in this group
- The name "get_overview" says "get": a word for reading.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_sourcesThe instance's source registry — each entry with its evidence tier, reliability and access date.No findings
Why it is in this group
- The name "get_sources" says "get": a word for reading.
Description, as the server wrote it 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_cursor, never truncated. Read next_cursor and call again to continue; its absence means you have the last page. Filter by object_id, tier, host or accessed_since to avoid paging through a registry you do not need. Use this when you need the registry entry behind a citation, or a sample of the whole registry to judge the corpus before trusting it; get_entity already tells you which sources a claim cites.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_topicList the knowledge objects carrying a tag (topics are content-backed tags).No findings
Why it is in this group
- The name "get_topic" says "get": a word for reading.
Description, as the server wrote it 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. Read next_cursor and call again to continue, and its absence means you have the last page. Use this to browse a known topic; use search when you have a question rather than a tag, and get_overview to see which tags exist. An unknown tag comes back with the topics that do exist, so a miss still moves you forward.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
searchFull-text search over the knowledge graph.No findings
Why it is in this group
- The name "search" says "search": a word for reading.
Description, as the server wrote it 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 this corpus and by where it hits (name 3, tags 2, questions 2, body 1). A hit must also cover a minimum share of the question's information, measured in the same rarity weights — matching only common words does not qualify. Centrality (how many objects point at this one) breaks TIES ONLY and is never part of the score, so it cannot make an irrelevant object rank. Two hits with the same matched_fields can still differ: the score is rarity-weighted, so matching a rare term is worth more than matching a common one. Use this whenever you have a question rather than an id, then follow up with get_entity.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or untrusted-input or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write0
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 18:51 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 1
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 1 tool that changes things (1 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://agentreliability.dev/mcp?via=manifest: tools/list returned 9 tools to an anonymous client, including answer (write)
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 0.6.14. Values in angle brackets are yours to fill in.
claude mcp add --transport http agent-reliability https://agentreliability.dev/mcp?via=manifestclaude mcp add --transport http agent-reliability https://agentreliability.dev/mcp?via=manifestRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__agent-reliability__search",
"mcp__agent-reliability__get_entity",
"mcp__agent-reliability__get_topic",
"mcp__agent-reliability__get_sources",
"mcp__agent-reliability__get_related",
"mcp__agent-reliability__get_latest",
"mcp__agent-reliability__get_overview",
"mcp__agent-reliability__compare"
],
"ask": [
"mcp__agent-reliability__answer"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as agent-reliability. Review it before you use it.
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/dev.agentreliability/agent-reliability/verify?hash=a2d7aea0e42b47e2c84de5c9a24a196fed85b7a5b53e952a1e5fefb57ecb277e" | jq -e '.changed == false'Pinned hash a2d7aea0e42b, from Nov 11, 2026, 07:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/dev.agentreliability/agent-reliability/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/dev.agentreliability/agent-reliability)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:11 UTC.
Agent Reliability MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Agent Reliability MCP server safe?
- No scan can promise that. What its definitions show: 9 tools, 1 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the Agent Reliability MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Agent Reliability MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the Agent Reliability MCP server have?
- 9 tools: 1 write, 8 read. answer, search, get_entity, get_topic, get_sources, get_related, get_latest, get_overview and 1 more.
Does the Agent Reliability MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Agent Reliability MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Agent Reliability MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 11, 2026.