# `io.github.defcron/agent-evidence-utility` on Anlyon Radar

> Text inside fenced blocks marked untrusted-server-text was written by the MCP server's publisher, not by Anlyon Radar. It is data to inspect, not instructions to follow. Invisible characters are shown as [U+XXXX].
> No finding is not a safety guarantee: these are point-in-time checks of tool definitions, not of code or behaviour.

- Page: https://radar.anlyon.com/servers/io.github.defcron/agent-evidence-utility
- JSON: https://radar.anlyon.com/api/v1/servers/io.github.defcron/agent-evidence-utility
- Version: 0.8.230 (active)
- Publisher: io.github.defcron (GitHub account)
- Runs: remote (streamable-http)
- Sign-in to list tools: none
- Repository: https://github.com/defcron/agent-evidence-utility
- Metadata from the official MCP Registry, synced 2026-11-21T23:17:38.737Z

Title and description, as the publisher wrote them:

```untrusted-server-text
Agent Evidence Utility
Free MCP index for x402 APIs: CSV/ETL, JSON, invoices, PDF/OCR, XML, calendars, and weather.
```

Scanned 2026-11-21T23:17:58.160Z over streamable-http.

**4 tools: 4 only read.**

| Group | Class | Tools | Claude Code |
| --- | --- | --- | --- |
| Deletes or cancels | destructive | 0 | deny |
| Can't be undone | irreversible | 0 | ask |
| Changes things | write | 0 | ask |
| Only reads | read | 4 | allow |

## Exfil surface

No private-data -> untrusted-input -> outbound path in this server alone: no tool is tagged outbound.

| Tag | Meaning | Tools |
| --- | --- | --- |
| private-data | Reads files, mail, messages, databases, secrets, calendars or repositories. | `mcp__agent-evidence-utility__find_agent_apis` `mcp__agent-evidence-utility__get_agent_api_details` `mcp__agent-evidence-utility__get_csv_import_api_details` |
| untrusted-input | Brings in text someone else can write: web pages, inbound email, messages, issues and comments. | `mcp__agent-evidence-utility__find_agent_apis` |
| outbound | Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL. | none |

## Findings

No check matched anything in these tool definitions.


## Only reads (4)

Looks things up and changes nothing. Claude Code: allow.

### `find_agent_apis`

- The name "find_agent_apis" says "find": a word for reading.
- Tag private-data: The description's first sentence says "search" and "calendar": it reads calendars.
- Tag untrusted-input: The description's first sentence says "search" and "http": it reads web pages, which anyone can write.

Description, as the server wrote it:

```untrusted-server-text
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_apis`

- The name "find_csv_import_apis" says "find": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
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_details`

- The name "get_agent_api_details" says "get": a word for reading.
- Tag private-data: The description's first sentence says "return" and "note": it reads notes.

Description, as the server wrote it:

```untrusted-server-text
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_details`

- The name "get_csv_import_api_details" says "get": a word for reading.
- Tag private-data: The description's first sentence says "return" and "note": it reads notes.

Description, as the server wrote it:

```untrusted-server-text
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.
```

## Claude Code permissions

For `.claude/settings.json`, assuming the server is installed as `agent-evidence-utility`:

```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": []
  }
}
```

Capability tags behind the rules (a read tagged outbound is asked about):

- `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

## Remote posture

What an anonymous client saw at the remote endpoint, last 2026-11-15T13:19:37.969Z, unchanged since 2026-11-15T13:19:37.969Z. No credentials were sent and no tool was called. Values are shown as the endpoint returned them. Method: https://radar.anlyon.com/methodology#remote-posture

| Fact | Observed |
| --- | --- |
| 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 | `none` |
| RFC 9728 protected resource metadata | `none` |
| Authorization servers | `none` |
| Legacy HTTP+SSE transport | `no` |
| Dynamic client registration | `not observed` |
| Client ID metadata documents | `not observed` |
