Agent Evidence API MCP server
io.github.Thx93/agent-evidence-apiThx93streamable-httpv0.1.9Scanned
Cited web evidence and fact checking for AI agents. $0.01 per call, no API key.
4 tools: 1 change things and 3 only read.
- Reads private data · 0
- Reads text others write · 3
- Can send data out · 2
- 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 Evidence API MCP server can do
The Agent Evidence API MCP server is published by the GitHub account Thx93. It has 4 tools. It can create or change data (1 tool: health), but cannot delete data. 3 tools only read.
3 tools bring in text other people can write (research_evidence, preview_evidence and sample); 2 tools can send data out of your system (research_evidence and preview_evidence).
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, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 8, 2026, version 0.1.9.
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.
4 tools
Changes things 1Claude Code: ask
healthCheck that the Agent Evidence API MCP server is reachable and report which service version is running.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 Check that the Agent Evidence API MCP server is reachable and report which service version is running. Free to call, takes no arguments or payment. Returns only {status, service, version} and exposes no secrets or infrastructure detail.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
Only reads 3Show 3 read-only tools
preview_evidenceFree preview of the paid tool: give one question and one public URL and get back up to three cited excerpts with the source URL, retrieval time and content hash.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "preview_evidence" says "preview": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe description's first sentence says "url": it reads web pages, which anyone can write.
- untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Claude Code: ask, because it is tagged outbound.
Description, as the server wrote it Free preview of the paid tool: give one question and one public URL and get back up to three cited excerpts with the source URL, retrieval time and content hash. No assessment and no verdict - that is what research_evidence adds, over up to five sources. Capped per day. Use this to judge whether the paid call is worth 0.01 USDC.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
research_evidenceFetch public web sources and return structured, cited web evidence for a question or claim.Reads text others writeCan send data outNo findings
Why it is in this group
- The description's first verb is "fetch": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe description's first sentence says "fetch" and "web": it reads web pages, which anyone can write.
- untrusted-inputThe input takes a URL (input.urls), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.urls): a request to a URL can carry data to whoever runs it.
Claude Code: ask, because it is tagged outbound.
Description, as the server wrote it Fetch public web sources and return structured, cited web evidence for a question or claim. Use this for source verification, claim verification, evidence extraction, and source-grounded research, or to compare sources. Returns source URLs, retrieval timestamps, short evidence excerpts, publisher and document metadata, and an explicit supported/contradicted/mixed/inconclusive assessment. Fresh web evidence is retrieved per request unless served from a bounded cache, and each source reports its actual retrieval time. Every excerpt returned is cited evidence tied to its source URL. No API key and no account: discovery is free, a call costs $0.01 in USDC on Base via x402, and nothing is charged when no source is retrieved.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
sampleReturn one real, previously produced evidence package, free, so you can see exactly what a paid call returns before spending anything: a verdict, and for every source the URL, retr…Reads text others writeNo findings
Why it is in this group
- The description's first verb is "return": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "return" and "url": it reads web pages, which anyone can write.
Description, as the server wrote it Return one real, previously produced evidence package, free, so you can see exactly what a paid call returns before spending anything: a verdict, and for every source the URL, retrieval time, content hash and the cited excerpts. Takes no arguments and always returns the same package. The paid tool is research_evidence, which answers your own question.
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.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write3
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out2
- 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, 19:00 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://agent-evidence.thx93.dev/mcp: tools/list returned 4 tools to an anonymous client, including health (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.
Tools1 added.+1 addedView diff
- Added:preview_evidenceOnly reads
Install
Pinned to version 0.1.9. Values in angle brackets are yours to fill in.
claude mcp add --transport http agent-evidence-api https://agent-evidence.thx93.dev/mcpclaude mcp add --transport http agent-evidence-api https://agent-evidence.thx93.dev/mcpRun 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-evidence-api__sample"
],
"ask": [
"mcp__agent-evidence-api__research_evidence",
"mcp__agent-evidence-api__preview_evidence",
"mcp__agent-evidence-api__health"
],
"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-evidence-api. Review it before you use it.
Capability tags behind 3 rules
- mcp__agent-evidence-api__research_evidence untrusted-input, outbound
- mcp__agent-evidence-api__preview_evidence untrusted-input, outbound
- mcp__agent-evidence-api__sample untrusted-input
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/io.github.Thx93/agent-evidence-api/verify?hash=0c8656eba34da16734610a2299c5a4faed763dd4afbf35df9d93e10f9a7c6472" | jq -e '.changed == false'Pinned hash 0c8656eba34d, from Nov 8, 2026, 18:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.Thx93/agent-evidence-api/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.Thx93/agent-evidence-api)Source: MCP Registry · repository. Synced Oct 23, 2026, 01:17 UTC.
Agent Evidence API MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Agent Evidence API MCP server safe?
- No scan can promise that. What its definitions show: 4 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 Evidence API 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 Evidence API 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 Evidence API MCP server have?
- 4 tools: 1 write, 3 read. health, research_evidence, preview_evidence and sample.
Does the Agent Evidence API MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Agent Evidence API MCP server send data to outside services?
- 2 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): research_evidence and preview_evidence.
Has the Agent Evidence API MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 8, 2026. Every change is on this page and in its Atom feed.