# Agent Evidence API (remote · agent-evidence.thx93.dev)

Cited web evidence and fact checking for AI agents. $0.01 per call, no API key.

- Trust score: 76/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-23

## Components

- remote · `agent-evidence.thx93.dev`: 76/100 (this document), [markdown](https://verifymcp.io/servers/thx93-agent-evidence-api/agent-evidence.md), [page](https://verifymcp.io/servers/thx93-agent-evidence-api/agent-evidence)

## Channel facts

- Endpoint: `https://agent-evidence.thx93.dev/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.1.9`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-23.

- **Endpoint Security**: 83/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC is configured correctly; the domain's records validate against the full chain to the root.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 77/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 559 tokens (~139/item across 4 items; 4 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 7/100
  - Stability observed for 2 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 4 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 5 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the Agent Evidence API MCP server?

Agent Evidence API is a hosted endpoint at https://agent-evidence.thx93.dev/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http thx93-agent-evidence-api 'https://agent-evidence.thx93.dev/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "thx93-agent-evidence-api": {
      "url": "https://agent-evidence.thx93.dev/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "thx93-agent-evidence-api": {
      "type": "http",
      "url": "https://agent-evidence.thx93.dev/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.thx93-agent-evidence-api]
url = "https://agent-evidence.thx93.dev/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "thx93-agent-evidence-api": {
      "type": "remote",
      "url": "https://agent-evidence.thx93.dev/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add thx93-agent-evidence-api --url 'https://agent-evidence.thx93.dev/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  thx93-agent-evidence-api:
    url: "https://agent-evidence.thx93.dev/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "thx93-agent-evidence-api": {
      "Transport": "http",
      "Url": "https://agent-evidence.thx93.dev/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add thx93-agent-evidence-api -t streamable-http -u 'https://agent-evidence.thx93.dev/mcp'
```

### Other

```json
{
  "mcpServers": {
    "thx93-agent-evidence-api": {
      "type": "http",
      "url": "https://agent-evidence.thx93.dev/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-23 (score 76, +2)

- [security improvement] DNSSEC: fail → pass
- [functional regression] Schema quality: 436 → 559
- [functional] Server version: 0.1.6 → 0.1.9
- [functional] New tool “preview_evidence”

### 2026-10-22 (score 74, 0)

- [functional improvement] Stability: unverified → 0.03

### 2026-10-21 (score 74)

First indexed and scored.

## MCP tools (4)

### `research_evidence` (~262 tokens)

Research Evidence

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.

Input parameters:

- `language` (string): Preferred evidence language: "auto" or a BCP-47 tag such as "en".
- `max_sources` (integer): Cap on the number of sources processed.
- `mode` (string): Reserved input. Only "evidence" is supported in version 0.1.0.
- `question` (string, required): The question or claim to gather web evidence for.
- `urls` (array): Candidate public source URLs to retrieve and cite. Version 0.1.0 requires at least one such URL.

### `preview_evidence` (~123 tokens)

Preview evidence (free)

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.

Input parameters:

- `question` (string, required): The question or claim to gather web evidence for.
- `url` (string, required): One public source URL to retrieve and cite. The paid tool accepts up to five.

### `sample` (~76 tokens)

Sample evidence

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.

### `health` (~52 tokens)

Health

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.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/thx93-agent-evidence-api/agent-evidence#diagnostics

## Score history

- 2026-10-23: 76
- 2026-10-22: 74
- 2026-10-21: 74

## Common questions

### What is the Agent Evidence API MCP server?

Agent Evidence API is an MCP server listed in the public MCP registry as io.github.Thx93/agent-evidence-api. Cited web evidence and fact checking for AI agents. $0.01 per call, no API key. This page covers its hosted endpoint (https://agent-evidence.thx93.dev/mcp).

### Is the Agent Evidence API MCP server safe to use?

Agent Evidence API scores 76 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Agent Evidence API MCP server expose?

Agent Evidence API exposes 4 tools: research_evidence, preview_evidence, sample, health. Their descriptions and schemas cost roughly 513 tokens of context every time the server is loaded.

### Does the Agent Evidence API MCP server require authentication?

No. We connected to Agent Evidence API without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Agent Evidence API MCP server still maintained?

Agent Evidence API is still listed as active in the MCP registry. We last reached this channel on 23 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://agent-evidence.thx93.dev/mcp
- Repository: https://github.com/Thx93/agent-evidence-api
- Website: https://agent-evidence.thx93.dev/
- Changelog RSS feed: https://verifymcp.io/servers/thx93-agent-evidence-api/agent-evidence.xml
- Changelog JSON feed: https://verifymcp.io/servers/thx93-agent-evidence-api/agent-evidence.json
- HTML version of this page: https://verifymcp.io/servers/thx93-agent-evidence-api/agent-evidence