MCP server · Developer tools

Project Telos MCP server

Lets your AI run local checks, proofs, and receipts so its work can be re-checked later.

Developer tools For it and development Developer Tools

Project Telos is a local workbench that helps your AI leave behind evidence for the work it does. Instead of just answering, it can run small checks, write receipts, and verify that a result still holds up. It is handy for people who want to trust what the AI says, not just take its word for it.

What is an MCP server? The 30-second version

On its own, your AI can only chat. An MCP server is a small helper program that gives your AI a new skill or a connection to a tool. This one connects your AI to Project Telos, a local set of checkers and proof tools. When you ask for something, the AI uses this helper to run the checks and hand you back a receipt you can look at again later.

What this MCP server does

You ask your AI to check something, like whether a set of files is consistent or whether a claim holds up. The AI passes that request to this helper, which runs local commands on your machine. The helper gathers evidence, performs the check, and writes a receipt with a clear status like MATCH, DRIFT, or UNVERIFIABLE. You get the result back in the chat, along with the receipt so you can re-check it yourself. If the check cannot be done, it says so honestly instead of guessing.

Flow diagram: you ask your AI “Check if my project files are consistent”, on your own computer the Project Telos MCP server works with your own computer, and you get back A status and a receipt.

Click to zoom

What you can do with it

Run local proof checks and get a re-checkable receipt
Inspect a workspace and build a context pack for your AI
Run doctors that audit CI, accessibility, performance, and compatibility
Assemble proof packets for agent actions, research claims, visual truth, and builds
Replay a saved proof packet to verify it still passes
Explore a creative engine with measurable render outputs
Control a browser or native app through a documented contract

Try asking your AI

“Run the agent-action proof and show me the verdict”
“Check this workspace for context and give me a summary”
“Verify the proof packet I saved earlier”
“Run the accessibility doctor on my project and tell me what it found”

What it gives back to you

You get back a short status like MATCH, DRIFT, or UNVERIFIABLE, plus a receipt with the details. The receipt lists what was checked, what was found, and any gaps. It is written so you or another tool can re-run the check later and get the same answer. In the chat, it usually shows up as a compact summary with a link or path to the full receipt.

Before you start

What you need

Node.js 20 or newer
An MCP host like Claude Desktop, Codex, or another tool that supports MCP servers

Good to know

Native control can affect the foreground window, and browser evidence packets may contain private URLs and titles, so keep them private.

Install it with your AI

Add Project Telos MCP server to your AI, no technical skills needed

You don't install anything by hand. You copy one prompt, paste it into an AI that can work on your computer, and it checks, installs and connects the server for you, asking you when it needs something.

Sign in to get the install prompt

Members get a ready-made prompt that lets the Claude desktop app check Project Telos MCP server, install it and connect it for them, step by step. You don't need any technical skills: you copy, paste and answer a few questions. Your connected AI can also find and install any of the 4,066 MCP servers here for you.