Atlas MCP Server

by corpussanctum Your server? Claim it

local only

Atlas MCP runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 14 Oct 2026.

Pre-action authorization for AI agents: permit, deny or escalate against a signed delegation chain.

—

Installs / week

npm · @corpussanctum/atlas-mcp

Stars

0 open issues

14 Oct 2026

Last commit

from GitHub

Apache-2.0

License

TypeScript

Nothing serious here today

Today is the operative word: we check Atlas MCP every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add atlas-mcp -- npx -y @corpussanctum/atlas-mcp

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "atlas-mcp": {
      "args": [
        "-y",
        "@corpussanctum/atlas-mcp"
      ],
      "command": "npx"
    }
  }
}

~/.codex/config.toml

[mcp_servers.atlas-mcp]
command = "npx"
args = ["-y", "@corpussanctum/atlas-mcp"]

.cursor/mcp.json

{
  "mcpServers": {
    "atlas-mcp": {
      "args": [
        "-y",
        "@corpussanctum/atlas-mcp"
      ],
      "command": "npx"
    }
  }
}

.vscode/mcp.json

{
  "mcpServers": {
    "atlas-mcp": {
      "args": [
        "-y",
        "@corpussanctum/atlas-mcp"
      ],
      "command": "npx"
    }
  }
}

Alternatives to Atlas MCP

same job, measured the same way

HANRIA agent mandate check

by hanria

Check an agent action against its operator's mandate before acting: permit, deny or escalate.

2 tools answering

Agent Sudo MCP

by kisyntra

MCP adapter for Agent_Sudo: authorization, delegation, provenance, and audit for AI agents.

232 installs/wk local only

Delego

by delego-dev

Intent-bound action authorization for AI agents: policy, human approval, and a signed audit trail.

229 installs/wk local only

HiveAttest

by srotzin

Pre-action attestation perimeter for AI agents — 8 primitives, signed C18 receipt per call.

18 tools answering

Vizier Guard

by vassiliylakhonin

Deterministic authorization and security guard for AI agent actions with signed receipts.

103 installs/wk local only

Figuard MCP

by figuard

Pre-flight spend authorization for AI agents. Set a budget, enforce limits, audit every decision.

44 installs/wk local only

AgentAuth

by raditotev

Identity and auth for AI agents: credentials, tokens, delegations, and permission checks.

115 installs/wk local only

Proof Layer

by world-999-labs

Signed, hash-chained provenance receipts for AI agent actions.

16 installs/wk local only

Atlas MCP — questions

Answers built from our own checks of this server.

Why is there no uptime for Atlas MCP?

Atlas MCP runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the npm package @corpussanctum/atlas-mcp.

How do I connect Atlas MCP?

Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It runs locally, so the command pulls @corpussanctum/atlas-mcp straight from npm; nothing to host, nothing to sign up for.

Is Atlas MCP open source?

Yes — it is published under the Apache-2.0 licence, written in TypeScript and 0 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.