zetesis
Enables scientific due diligence by grading claims against public literature, clinical trials, and filings, with explicit citations and optional attestation.
README
Zetesis
Scientific due diligence on a claim, from inside Claude, Copilot, or any MCP host.
Zetesis takes a high-dimensional scientific or technical claim and grades it dimension by dimension against public literature, clinical trials, and filings. It returns an overall reading, cites every source by id, and, for a full evaluation, translates the science into what a commitment to the claim turns on and seals the result in an attestation anyone can re-check.
This package is a thin MCP client. It holds no keys and runs no model. Every call is proxied to the hosted engine at https://api.zetesis.science with your token.
Get a token
Free, no card, at https://api.zetesis.science/signup. The free plan gives you a handful of screening evaluations each month.
Connect it
Claude Code:
claude mcp add zetesis --env ZETESIS_TOKEN=zk_... -- uvx --from zetesis zetesis-client
Claude Desktop (claude_desktop_config.json):
{
"mcpServers": {
"zetesis": {
"command": "uvx",
"args": ["--from", "zetesis", "zetesis-client"],
"env": { "ZETESIS_TOKEN": "zk_..." }
}
}
}
Tools
- evaluate_claim — grade a claim.
depth="screen"returns the verdict directly (free tier);depth="deep"runs the full signed dossier in the background.mode="research"is science only;mode="diligence"adds the capital reading. - check_evaluation — get the verdict and the rendered dossier link for a deep run.
- verify_attestation — re-check any Zetesis attestation. No account needed.
- account_status — your plan and remaining evaluations or credits.
How it grades
It grades only what the evidence supports, cites sources by hard id (PMID, DOI, NCT, NIH grant, SEC filing), and flags gaps rather than filling them. It never invents citations. Claim text is not logged; only metadata (the routed domain, depth, counts) is kept.
Configuration
ZETESIS_TOKEN— your token (required for evaluations; verify works without one)ZETESIS_API— override the API base (defaulthttps://api.zetesis.science)
MIT licensed. The hosted engine is a separate service.
mcp-name: io.github.reutavidan/zetesis
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.