MCPLow riskUnclaimed

citeguard

Verify citations in AI text: fetches each cited source, returns verdicts with evidence quotes.

Franksterinofranksterino/citeguardUpdated Jul 6, 2026

server.json

{
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "name": "io.github.Franksterino/citeguard",
  "description": "Verify citations in AI text: fetches each cited source, returns verdicts with evidence quotes.",
  "repository": {
    "url": "https://github.com/Franksterino/citeguard",
    "source": "github"
  },
  "version": "0.1.2",
  "packages": [
    {
      "registryType": "npm",
      "identifier": "citeguard",
      "version": "0.1.2",
      "transport": {
        "type": "stdio"
      },
      "environmentVariables": [
        {
          "description": "LLM judge preset: qwen | openai | anthropic",
          "format": "string",
          "name": "CITEGUARD_JUDGE_PRESET"
        },
        {
          "description": "API key for the judge LLM (required for verify_claims/check_document; check_links works without it)",
          "isRequired": true,
          "format": "string",
          "isSecret": true,
          "name": "CITEGUARD_JUDGE_KEY"
        }
      ]
    }
  ],
  "remotes": [
    {
      "type": "streamable-http",
      "url": "https://citeguard.boundy.workers.dev/mcp"
    }
  ]
}

Permissions

DeclaredDetected
Runs code—node
Installs—npm:citeguard@0.1.2
Runs install scripts—None
Networkciteguard.boundy.workers.devciteguard.boundy.workers.dev
Needs credentialsCITEGUARD_JUDGE_KEYCITEGUARD_JUDGE_KEY
Outside the workspace—None
Agent tools—None

Checks

Low risk · Nothing worth a warning was found.

Not reviewed by a person · Checked by rules; the model review is not switched on yet.

Versions

  1. #10.1.2latestOct 7, 2026