MCP Tools DirectoryAbout this integration
Sends the same prompt to multiple LLM providers in parallel and returns a divergence score via MCP.
- Transport
- stdio
- Authentication
- api-key
- Initial setup
- credentials
- Runtime
- unattended
- Evidence
- documented
- Version
- 0.1.4
- Package
- truthroute-cli
- Last compatibility test
- Not independently tested
Connect your agent
truthroute-cliPublisher documentation and source manifest were reviewed. The package, model APIs, scoring implementation, and publisher validation claims were not executed or independently audited. Calls are billed by the selected providers, prompts are sent to them, and the score is not a fact check.
Capabilities: Send one prompt to selected OpenAI, Anthropic, and Gemini models, Compute a local response-divergence score, Return structured comparison results and confidence bands
Connected profiles
Additional details
io.github.RudrenduPaul/truthroute
Source ↗ · Checked 2026-09-170.1.4
Source ↗ · Checked 2026-09-17CC0-1.0; package licenses are separate
Source ↗ · Checked 2026-09-17npm
Source ↗ · Checked 2026-09-17truthroute-cli
Source ↗ · Checked 2026-09-190.1.4
Source ↗ · Checked 2026-09-19The truthroute mcp command runs a stateless stdio MCP server exposing compare as a typed tool; provider calls use the configured keys and local scoring follows each invocation.
Source ↗ · Checked 2026-09-19Users must provide environment-variable API keys for the requested OpenAI, Anthropic, and/or Gemini providers, and only selected providers need keys.
Source ↗ · Checked 2026-09-19Configure an MCP host to launch the truthroute executable with the mcp subcommand over stdio.
Source ↗ · Checked 2026-09-19Publisher documentation reviewed; package and integration endpoint not executed or independently security-audited.
Source ↗ · Checked 2026-09-19