# CHAP Coordinator

> CHAP Coordinator is an MCP server for ai models and llm tooling. Record human approvals, edits and overrides of AI agent work in an auditable workspace. It runs locally on your machine and is started by your AI client.

- **Kind:** MCP server
- **Platforms:** CLI, self-hosted, API
- **Repository:** https://github.com/brightbeamai/chap/tree/HEAD/packages/coordinator-mcp
- **MCP Registry name:** io.github.BrightbeamAI/chap
- **Categories:** [AI models and LLM tooling](https://ai-powered.com/categories/ai-and-llm), [security](https://ai-powered.com/categories/security)
- **Listing updated:** 2026-11-15

## About

CHAP is a protocol for logging human decisions over agent output, and this package exposes its Coordinator as an MCP server so an agent can create tasks, ask questions and read the audit trail. The default stdio server makes every call as one participant, `agent:assistant`, and refuses to act as a human or as any other participant, so approvals stay with a person in a separate desk.

The default agent tool set covers creating, updating and completing tasks, asking whisper questions, reading workspace descriptions and the audit log, and verifying the hash chain. Decision tools exist for work the agent is asked to review, but the coordinator refuses them on the agent's own work and records the attempt. Tools that choose reviewers, escalate or manage workspaces are left out. Setting review_required on a task means the agent cannot complete it alone.

Without a URL or database path it keeps everything in memory. It can forward calls to a running CHAP server, or keep workspaces in a SQLite file. Node 22 or newer is needed.

## Features

- **Single-participant calls:** Every call is made as one named agent and cannot impersonate a human.
- **Audit chain:** Reads the audit log and verifies its hash chain.
- **Review gating:** Tasks flagged review_required cannot be completed by the agent alone.
- **Pluggable storage:** Runs in memory, in a SQLite file, or forwards to a CHAP server.
- **Filtered tool sets:** Choose the agent subset or every method.
- **HTTP handler included:** The package also serves MCP over HTTP for your own server.

## Good for

- Keep a trail of which agent outputs a human approved or edited
- Gate an assistant's task completion behind a person's review
- Verify the integrity of an audit log
- Add a human decision desk to an agent project

## Install

### Claude Code (Terminal)

```sh
claude mcp add chap -- npx -y @brightbeamai/chap-coordinator-mcp
```

### Claude Desktop (claude_desktop_config.json)

```json
{
  "mcpServers": {
    "chap": {
      "command": "npx",
      "args": [
        "-y",
        "@brightbeamai/chap-coordinator-mcp"
      ]
    }
  }
}
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "chap": {
      "command": "npx",
      "args": [
        "-y",
        "@brightbeamai/chap-coordinator-mcp"
      ]
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "chap": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@brightbeamai/chap-coordinator-mcp"
      ]
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "chap": {
      "command": "npx",
      "args": [
        "-y",
        "@brightbeamai/chap-coordinator-mcp"
      ]
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "chap": {
      "command": "npx",
      "args": [
        "-y",
        "@brightbeamai/chap-coordinator-mcp"
      ]
    }
  }
}
```

## Tools

- `chap.task.create`: Create a task.
- `chap.task.update`: Update a task.
- `chap.task.complete`: Complete a task.
- `chap.whisper.ask`: Ask a whisper question.
- `chap.decide.approve`: Approve work the agent was asked to review.
- `chap.decide.reject`: Reject work under review.
- `chap.decide.override`: Override a decision.
- `chap.review.acknowledge`: Acknowledge a review.
- `chap.workspace.describe`: Describe the workspace.
- `chap.audit.read`: Read the audit log.
- `chap.audit.verify_chain`: Verify the audit hash chain.

## FAQ

### Can the agent approve its own work?

No. The coordinator refuses decisions on the agent's own work and logs the attempt.

### Where is data kept?

In memory by default; set a database path for SQLite or point it at a CHAP server.

### What runtime is needed?

Node 22 or newer.

### Can it act as a human?

No. The server refuses a human participant URI at start.

### How do I add CHAP Coordinator to Claude Code?

Run this command in your terminal: claude mcp add chap -- npx -y @brightbeamai/chap-coordinator-mcp

### What are the best alternatives to CHAP Coordinator?

The closest alternatives to CHAP Coordinator are Chipp Agents, Two-Key, Approval Gate MCP, Chipp Agent settings and mcpcut.

## Where this comes from

- Description: written from the project's README.
- Install steps: from the official MCP Registry entry.

## Alternatives

- [Chipp Agents](https://ai-powered.com/mcp/chipp-agents): Chipp Agents is a paid MCP server for ai models and llm tooling.
- [Two-Key](https://ai-powered.com/mcp/two-key): Two-Key is an open-source MCP server for security.
- [Approval Gate MCP](https://ai-powered.com/mcp/approval-gate-mcp): Approval Gate MCP is an open-source MCP server for security.
- [Chipp Agent settings](https://ai-powered.com/mcp/chipp-agent-settings): Chipp Agent settings is a paid MCP server for ai models and llm tooling.
- [mcpcut](https://ai-powered.com/mcp/mcpcut): mcpcut is an open-source MCP server for security.
- [Callsign](https://ai-powered.com/mcp/callsign): Callsign is an open-source MCP server for communication.
- [Chipp Core](https://ai-powered.com/mcp/chipp-core): Chipp Core is a paid MCP server for ai models and llm tooling.
- [Agent Audit MCP](https://ai-powered.com/mcp/agent-audit-mcp): Agent Audit MCP is a paid MCP server for security.

---
Source: https://ai-powered.com/mcp/chap-coordinator
