Skip to content
MCP server

Rithmo

Governance for company AI agents: pre-action checks, approvals and an audit trail over MCP

Pricing
Freemium
Platforms
self-hosted, API, Web
Runs
Remotely
Version
0.1.0
Listing updated
1 day ago

About Rithmo

Rithmo is a freemium MCP server for security. It runs as a hosted remote server, so there is nothing to install locally.

Rithmo describes itself as a fact-checker for a company's AI agents. Each agent connects to Rithmo's MCP server and checks in before every action; Rithmo supplies the steps for each run over that connection, so you do not write them into the agent. Every check and approval is logged.

The platform is deployed in your own cloud, and its MCP endpoint is your Rithmo address followed by /api/mcp, or the address given to you if Rithmo operates an instance. Once connected, the agent shows up on an Agents tab and, until someone takes it live, is told to report its setup and stop. An agent running in two assistants counts as two agents. Guides cover ChatGPT, Claude (web and Claude Code) and custom code.

The pricing page lists a seven-layer governance stack, automatic blocks on unsafe actions, human approvals, cost and usage per run, prompt and model drift detection and custom authority maps. The first workflow is free with unlimited agents, and an organization tier carries enterprise terms.

Install

Run in a terminal

claude mcp add --transport http rithmo https://app.rithmo.ai/api/mcp

Add to Settings → Connectors → Add custom connector

https://app.rithmo.ai/api/mcp
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "rithmo": {
      "url": "https://app.rithmo.ai/api/mcp"
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "rithmo": {
      "type": "http",
      "url": "https://app.rithmo.ai/api/mcp"
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "rithmo": {
      "serverUrl": "https://app.rithmo.ai/api/mcp"
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "rithmo": {
      "type": "http",
      "url": "https://app.rithmo.ai/api/mcp"
    }
  }
}

What it does

Pre-action check-in
Agents consult Rithmo before each action.
Human approvals
Approvals with a complete audit trail.
Automatic blocks
Stops unsafe actions.
Cost per run
Tracks agent usage and cost.
Drift detection
Flags prompt and model drift.
Runs in your cloud
Deployed in your own cloud or on-prem.

Good for

  • Governing agents built in ChatGPT or Claude
  • Requiring approval for risky agent actions
  • Auditing what agents did and why
  • Monitoring agent cost per run
  • Rolling out agent controls across teams

Pricing

Freemium

First workflow free; organization tier on enterprise terms

Prices change. Check rithmo.ai before you buy.

Rithmo FAQ

What does the first workflow cost?

It is free, with unlimited agents, so you can prove value before a wider rollout.

Where does it run?

In your own cloud or on-prem.

Which agents can connect?

Any agent over MCP, with guides for ChatGPT, Claude and custom code.

What happens when an agent first connects?

It is told to report its setup and stop until someone takes it live.

Is Rithmo free?

Rithmo has a free plan, with paid plans for more usage or features.

How do I add Rithmo to Claude Code?

Run this command in your terminal: claude mcp add --transport http rithmo https://app.rithmo.ai/api/mcp

What are the best alternatives to Rithmo?

The closest alternatives to Rithmo are REA, Claude Code Ultimate Guide, Agent Roast, Midplane and Leash.

Alternatives to Rithmo

  1. REA

    MCP server

    CLI and MCP server that lets coding agents reverse engineer apps and binaries

    Runs locally
    • Open source
    • 464K GitHub stars
    • Developer tools
  2. MCP server for searching the Claude Code Ultimate Guide from any MCP client

    Runs locally
    • Open source
    • 6.5K GitHub stars
    • AI models and LLM tooling
  3. Agent Roast

    MCP server

    Offline review that flags agent changes which weaken tests, assertions or CI

    Runs locally
    • Open source
    • 4 Hacker News points
    • Developer tools
  4. Midplane

    MCP server

    Postgres gateway for AI agents with table grants, column masking and approval for writes

    Runs locally
    • Open source
    • 5 GitHub stars
    • Databases
  5. Leash

    MCP server

    Review what your AI touched, approve risky actions and undo supported changes

    • 1 tool
    • Remote
    • Free
    • 1 GitHub star
    • Security