mcpField
A
acp-mcp-server

acp-mcp-server

Remote
agenticcontrolplane.comSecurity0Updated 6d ago

About acp-mcp-server

acp-mcp-server is a bridge between MCP clients and Agentic Control Plane governance, for teams governing AI agent tool calls. It exposes policy decisions and connection status while forwarding governance checks to ACP.

Key features

  1. 01Check whether a tool call is allowed
  2. 02Return allow, deny, or confirmation decisions
  3. 03Verify workspace connection and identity
  4. 04Forward checks for policy and audit handling

Use cases

  1. 01Check a sensitive call before execution
  2. 02Inspect governance connection and workspace identity

MCP support

Exposes `acp_check` and `acp_status` to MCP clients. It proxies governance requests to ACP and supports streamable HTTP.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://api.agenticcontrolplane.com/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

ACP Governance MCP Server

Model Context Protocol server that lets Claude, ChatGPT, Cursor, Lovable, and any MCP client check tool calls against Agentic Control Plane governance — policy decisions, rate limits, audit logs, identity attribution.

One sentence: before your AI agent runs a sensitive tool, it asks ACP whether the call is allowed. ACP says yes, no, or asks for confirmation, and writes an audit row attributable to the human behind the agent.

What it exposes

Two tools, callable via MCP:

ToolWhat it does
acp_checkAnswer "would this call be allowed?" for a specific call — for explicit questions or pre-flight planning. If ACP hooks are installed in the harness, tool calls are already governed automatically and this doesn't need to be called per tool. Returns allow / deny / ask plus a reason.
acp_statusVerify the connection and your workspace identity.

That's the whole surface. Everything else — policies, audit logs, scope intersection, delegation chains — runs server-side at api.agenticcontrolplane.com. This MCP server is just the bridge.

Install (hosted — recommended)

The server is hosted at https://mcp.agenticcontrolplane.com/mcp. Add it as a connector in your MCP client:

Claude Desktop / Claude.ai connector:

URL: https://mcp.agenticcontrolplane.com/mcp
Auth: OAuth (sign in with Google through ACP)

ChatGPT, Cursor, Lovable, Cline: Same URL, same OAuth flow. Most clients have a one-click "Add MCP Server" UI.

Programmatic clients (your own agent code):

POST https://mcp.agenticcontrolplane.com/mcp
Authorization: Bearer gsk_<your-acp-api-key>
Content-Type: application/json

You'll need an ACP workspace. The free tier is unlimited tool-call logging — sign up at cloud.agenticcontrolplane.com/login.

Install (self-host)

If you want to run the bridge yourself — for air-gapped deployments, or to point at a self-hosted ACP gateway — clone and run:

git clone https://github.com/agentic-control-plane/acp-mcp-server
cd acp-mcp-server
npm install
npm run build

# Point at the ACP API (default: https://api.agenticcontrolplane.com)
export ACP_API_BASE=https://your-acp-gateway.example.com

# Optional: service-level API key for OAuth users (ChatGPT, Claude.ai)
# whose JWTs aren't directly usable as ACP tokens
export ACP_SERVICE_KEY=gsk_workspace_...

npm start
# → MCP endpoint: POST http://0.0.0.0:3000/mcp
# → OAuth discovery: GET /.well-known/oauth-protected-resource

The bridge speaks streamable-HTTP MCP and proxies to ACP's /govern/tool-use endpoint.

How it fits

your AI client            this MCP server          ACP gateway
─────────────            ─────────────────         ───────────
Claude / ChatGPT  ──►  mcp.agenticcontrolplane  ──►  api.agenticcontrolplane
Cursor / Lovable    POST /mcp (acp_check)         POST /govern/tool-use
                                                      ↓
                                                   policy + audit + identity
                                                      ↓
                                                   allow / deny / ask

Every call writes an audit row attributable to the human identity behind the OAuth session — so you get a complete log of every governed tool call across every MCP client your team uses, in one workspace.

Auth model

The server supports two authentication paths:

  1. OAuth (recommended for human-driven clients) — Claude.ai, ChatGPT, etc. complete an OAuth flow against ACP's identity provider; the resulting Auth0 JWT identifies the human. The bridge uses an ACP_SERVICE_KEY to authorize the underlying governance call on the human's behalf.
  2. Bearer gsk_ API key (recommended for programmatic clients) — pass an ACP API key directly as Authorization: Bearer gsk_.... The key's identity is the ACP-side actor. Skip OAuth.

OAuth discovery metadata is served at /.well-known/oauth-protected-resource per the MCP authorization spec.

Local development

npm install
npm run dev        # tsx-based hot reload

Tools are defined in src/tools/tools.ts. The MCP JSON-RPC handler is in src/handlers/mcpHandler.ts. The Express entry point and rate limits are in src/server/expressServer.ts.

License

MIT — see LICENSE.

Links

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.