Agent Evidence Utility MCP server
io.github.defcron/agent-evidence-utilitydefcronstreamable-httpv0.8.230Scanned
Free MCP index for x402 APIs: CSV/ETL, JSON, invoices, PDF/OCR, XML, calendars, and weather.
4 tools: 4 only read.
- Reads private data · 3
- Reads text others write · 1
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
Decide which of this server's tools your agent can use.
- 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 Utility MCP server can do
The Agent Evidence Utility MCP server is published by the GitHub account defcron. It has 4 tools. Every one of them only reads: going by their definitions, none of them creates, changes, sends or deletes anything.
3 tools read private data (find_agent_apis, get_agent_api_details and get_csv_import_api_details); 1 tool brings in text other people can write (find_agent_apis).
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 4 times since Anlyon Radar first saw them.
Last scanned Nov 21, 2026, version 0.8.230.
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
Only reads 4Show 4 read-only tools
find_agent_apisSearch paid CSV, JSON, OpenAPI/API-discovery, HTTP, security, calendar, document, invoice, text, and U.S.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "find_agent_apis" says "find": a word for reading.
What it can reach
- private-dataThe description's first sentence says "search" and "calendar": it reads calendars.
- untrusted-inputThe description's first sentence says "search" and "http": it reads web pages, which anyone can write.
Description, as the server wrote it Search paid CSV, JSON, OpenAPI/API-discovery, HTTP, security, calendar, document, invoice, text, and U.S. weather APIs by task. Returns up to five best-matching route URLs, seller prices, categories, and free examples; does not initiate payment.
find_csv_import_apisSearch this service's vendor CSV, preflight, schema validation, typed JSON import, batch import, and recurring CSV monitoring endpoints.No findings
Why it is in this group
- The name "find_csv_import_apis" says "find": a word for reading.
Description, as the server wrote it Search this service's vendor CSV, preflight, schema validation, typed JSON import, batch import, and recurring CSV monitoring endpoints. Returns route contracts, prices, and free examples without processing CSV data or initiating payment.
get_agent_api_detailsReturn request fields when available, a free example when published, the OpenAPI link, seller price, and x402 notes for one API.Reads private dataNo findings
Why it is in this group
- The name "get_agent_api_details" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "return" and "note": it reads notes.
Description, as the server wrote it Return request fields when available, a free example when published, the OpenAPI link, seller price, and x402 notes for one API. Pass exactly one of id or endpoint_url from find_agent_apis. Does not call the endpoint or initiate payment.
get_csv_import_api_detailsReturn request fields when available, a free example when published, the OpenAPI specification, and x402 payment notes for one CSV endpoint.Reads private dataNo findings
Why it is in this group
- The name "get_csv_import_api_details" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "return" and "note": it reads notes.
Description, as the server wrote it Return request fields when available, a free example when published, the OpenAPI specification, and x402 payment notes for one CSV endpoint. Does not call the endpoint or initiate payment.
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 outbound.
- Reads private data3
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write1
- 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 15, 2026, 13:19 UTC, unchanged since Nov 15, 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
- 0
- 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
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.
Tools3 changed.~3 changedView diff
- Changed:find_agent_apisOnly readsdescriptioninputSchema
- Changed:get_agent_api_detailsOnly readsdescriptioninputSchema
- Changed:get_csv_import_api_detailsOnly readsdescriptioninputSchema
Tools1 changed.~1 changedView diff
- Changed:get_agent_api_detailsOnly readsinputSchema
Tools2 changed.~2 changedView diff
- Changed:get_agent_api_detailsOnly readsinputSchema
- Changed:get_csv_import_api_detailsOnly readsinputSchema
Tools2 added, 2 changed.+2 added~2 changedView diff
- Added:find_agent_apisOnly reads
- Added:get_agent_api_detailsOnly reads
- Changed:find_csv_import_apisOnly readsdescriptioninputSchema
- Changed:get_csv_import_api_detailsOnly readsinputSchema
Install
Pinned to version 0.8.230. Values in angle brackets are yours to fill in.
claude mcp add --transport http agent-evidence-utility https://agent-evidence-extractor.defcronyke.workers.dev/mcpclaude mcp add --transport http agent-evidence-utility https://agent-evidence-extractor.defcronyke.workers.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-utility__find_agent_apis",
"mcp__agent-evidence-utility__get_agent_api_details",
"mcp__agent-evidence-utility__find_csv_import_apis",
"mcp__agent-evidence-utility__get_csv_import_api_details"
],
"ask": [],
"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-utility. Review it before you use it.
Capability tags behind 3 rules
- mcp__agent-evidence-utility__find_agent_apis private-data, untrusted-input
- mcp__agent-evidence-utility__get_agent_api_details private-data
- mcp__agent-evidence-utility__get_csv_import_api_details private-data
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.defcron/agent-evidence-utility/verify?hash=6729b91870a16c730c3651a0dea7bfa172444e022025d747019a8a1ab86e5148" | jq -e '.changed == false'Pinned hash 6729b91870a1, from Nov 21, 2026, 23:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.defcron/agent-evidence-utility/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.defcron/agent-evidence-utility)Source: MCP Registry · repository. Synced Nov 21, 2026, 23:17 UTC.
Agent Evidence Utility MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Agent Evidence Utility MCP server safe?
- No scan can promise that. What its definitions show: 4 tools, all of which only read, and 0 findings from fixed checks. Read-only tools can still pass private data to a model.
Can the Agent Evidence Utility 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 Utility 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 Utility MCP server have?
- 4 tools: 4 read. find_agent_apis, get_agent_api_details, find_csv_import_apis and get_csv_import_api_details.
Does the Agent Evidence Utility MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Agent Evidence Utility 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 Evidence Utility MCP server changed its tools?
- Yes, 4 times since Anlyon Radar started tracking it, most recently on Nov 20, 2026. Every change is on this page and in its Atom feed.