Koskamo

Agent Evidence API MCP

Provides cited, timestamped web evidence and US weather data for AI agents via MCP. It returns quoted excerpts with source URLs, retrieval times, and content hashes, along with an explicit supported/contradicted/mixed/inconclusive assessment. It prevents access to private or loopback addresses and re-validates DNS to defeat rebinding attacks.

Visit Thx93

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

Agent Evidence API MCP logo, by Thx93Community listingStreamable HTTPNo sign-inEndpoint checked 2026-11-01Published by Thx93
You need:No account, no API key
MCP endpoint (Streamable HTTP)
https://agent-evidence.thx93.dev/mcp
Vendor documentation

What you can do with it

  • Fetch cited web evidence for a specific question and set of URLs
  • Retrieve active weather alerts for a US state
  • Get weather forecasts for specific latitude and longitude coordinates
  • Verify claims by comparing source text against a query

Source and maintenance

Community listingRegistry 0.1.9
mcp-registry: io.github.Thx93/agent-evidence-api@0.1.9Source repositoryProject website
Maintenance checked

Protocol and capabilities

Server
agent-evidence-api 0.1.9
MCP protocol
2025-06-18
Tools
4 advertised
Resources
Not advertised
Resource templates
Not advertised
Prompts
Not advertised
Server-advertised capabilities
{
  "tools": {}
}

Server-provided instructions

Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.

Agent Evidence API returns web evidence for AI agents. Call research_evidence with a question or claim and the public source URLs to verify to receive structured, cited evidence with an explicit assessment. Call health to check connectivity.

Tools

4 advertised

research_evidence — Research Evidence
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

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.

research_evidence input schema
{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "question"
  ],
  "properties": {
    "mode": {
      "enum": [
        "evidence"
      ],
      "type": "string",
      "description": "Reserved input. Only \"evidence\" is supported in version 0.1.0."
    },
    "urls": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "maxItems": 25,
      "description": "Candidate public source URLs to retrieve and cite. Version 0.1.0 requires at least one such URL."
    },
    "language": {
      "type": "string",
      "maxLength": 35,
      "minLength": 1,
      "description": "Preferred evidence language: \"auto\" or a BCP-47 tag such as \"en\"."
    },
    "question": {
      "type": "string",
      "maxLength": 2000,
      "minLength": 1,
      "description": "The question or claim to gather web evidence for."
    },
    "max_sources": {
      "type": "integer",
      "maximum": 25,
      "description": "Cap on the number of sources processed.",
      "exclusiveMinimum": 0
    }
  },
  "additionalProperties": false
}
research_evidence annotations
{
  "readOnlyHint": true,
  "openWorldHint": true,
  "idempotentHint": true,
  "destructiveHint": false
}
preview_evidence — Preview evidence (free)
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

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.

preview_evidence input schema
{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "question",
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "format": "uri",
      "description": "One public source URL to retrieve and cite. The paid tool accepts up to five."
    },
    "question": {
      "type": "string",
      "maxLength": 2000,
      "minLength": 8,
      "description": "The question or claim to gather web evidence for."
    }
  },
  "additionalProperties": false
}
preview_evidence annotations
{
  "readOnlyHint": true,
  "openWorldHint": true,
  "idempotentHint": true,
  "destructiveHint": false
}
sample — Sample evidence
Advertised by the server during the last successful anonymous check.
Advertised read-only

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.

sample input schema
{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {},
  "additionalProperties": false
}
sample annotations
{
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
health — Health
Advertised by the server during the last successful anonymous check.
Advertised read-only

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.

health input schema
{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {},
  "additionalProperties": false
}
health annotations
{
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks
1 of 1 (100%)
Average latency
528 ms
95th percentile latency
528 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

  • · probe · passed · 528 ms · metadata changed · 4 tool(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.
Claude Code configuration
claude mcp add --transport http agent-evidence-api-mcp https://agent-evidence.thx93.dev/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).
Codex configuration
codex mcp add agent-evidence-api-mcp --url https://agent-evidence.thx93.dev/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable agent-evidence-api-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "agent-evidence-api-mcp": {
      "url": "https://agent-evidence.thx93.dev/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "agent-evidence-api-mcp": {
      "type": "streamableHttp",
      "url": "https://agent-evidence.thx93.dev/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start agent-evidence-api-mcp and inspect its tools.
VS Code configuration
{
  "servers": {
    "agent-evidence-api-mcp": {
      "type": "http",
      "url": "https://agent-evidence.thx93.dev/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.
Gemini CLI configuration
gemini mcp add --transport http agent-evidence-api-mcp https://agent-evidence.thx93.dev/mcp

Claude Desktop

Merge this into claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\), then restart Claude Desktop.
Claude Desktop configuration
{
  "mcpServers": {
    "agent-evidence-api-mcp": {
      "url": "https://agent-evidence.thx93.dev/mcp"
    }
  }
}

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.
Windsurf configuration
{
  "mcpServers": {
    "agent-evidence-api-mcp": {
      "serverUrl": "https://agent-evidence.thx93.dev/mcp"
    }
  }
}

Let your agent find its tools

Find servers like Agent Evidence API MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows
See all 3,756