MCP.Market

Mcacp MCP server

by Oortonaut·io.github.Oortonaut/mcacp·v0.1.3·9 stars
No reviews yet

MCP-to-ACP bridge — let any MCP client drive ACP coding agents

B75/100grade B
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
B75/100

full report

Adoption
Growing

9 stars137 downloads/wk

Reviews

Write one

Nobody has reviewed Mcacp yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Mcacp tools (24, 5 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • agent_check_upgrades

    Check all installed agents for available version upgrades.

  • agent_install

    Install an ACP agent from the registry.

  • agent_uninstallwrite action

    Remove a locally installed ACP agent.

  • cancelwrite action

    Cancel an in-progress prompt.

  • close_session

    Close an active session. Session file preserved for future load_session.

  • discover_agents

    Scan editor configs (Zed settings.json, JetBrains acp.json) for ACP agents. Returns agents with command/args/env and source. To import, add them to agent_servers in your mcacp.json and call reload_config.

  • events

    Block until any prompted session produces events. Returns events stamped with sessionId and agentId. Supports optional Nagle-style coalescing to batch events across sessions.

  • get_agent_status

    Get detailed status of a running ACP agent.

  • grant_permission

    Respond to a pending permission request (operator policy). The agent resumes; new events flow to the queue.

  • initialize

    Spawn an ACP agent process and perform the initialize handshake. Must be called before creating sessions.

  • list_installed_agents

    List all locally installed ACP agents with their id, name, version, and description.

  • list_running_agents

    List all spawned ACP agent processes with status, heartbeat, and active sessions.

  • list_sessions

    List stored sessions. Does not require the agent to be running.

  • load_session

    Resume a previously created session. Agent must support session loading.

  • new_sessionwrite action

    Create a new ACP session on an initialized agent. Returns the agent's session ID.

  • prompt

    Block until at least one prompt event is available. Returns queued events including updates (with full ACP metadata), permission requests, and completion. The default way to consume prompt results.

  • prompt_events

    Non-blocking poll for prompt events. Returns all queued events (updates, permission requests, completion). May return empty array if no new events.

  • prompt_startwrite action

    Send a prompt to an active ACP session. Returns immediately with { status: "prompted" }. Use prompt or prompt_events to consume events.

  • registry_search

    Search configured ACP agent registries for available agents.

  • reload_config

    Reload configuration from disk. Use after editing mcacp.json to pick up new agent_servers entries or changed settings. Returns the new config.

  • request_permissionwrite action

    Send an MCP elicitation to the outer host asking for a permission decision. Does not require a running agent or session.

  • set_agent_status

    Set an explicit status text for a running agent.

  • set_mode

    Switch the operating mode of a session.

  • shutdown

    Gracefully shut down a running ACP agent, closing all sessions.

Public scan report

scanner v0.1.10 · 2026-09-28 · same rubric, same numbers if you re-run it

no findings
  • Code scan31 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 239 days ago4/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 75/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Mcacp compares

Against every graded Productivity MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
75/100
higher than 40% of 1,299 Productivity servers
Tools
24
the typical Productivity server has 7
Tools that change things
21%
typical: 0%. Fewer write tools means less an agent can break
GitHub stars
9
more than 76% of 854 Productivity servers
Downloads a week
137
more than 63% of 427 Productivity servers with a package

What its tools let an agent do: 16 read · 1 create · 6 change · 1 delete

Install Mcacp in Claude Code, Cursor or VS Code

Runs npx -y mcacp on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add mcacp -- npx -y mcacp
Add to Cursor

What the publisher says

From the Mcacp repository's README, as published. We do not edit it. Read it on GitHub

MCACP

Bridge any MCP client to any ACP coding agent.

MCACP is an MCP server that speaks the Agent Client Protocol on behalf of your MCP host. It lets Claude Code, Zed, VS Code, or any MCP-compatible client spawn, manage, and interact with ACP coding agents — turning a single chat window into a multi-agent control plane.

MCP Client (Claude Code, Zed, VS Code, ...)
    |
    |  MCP (stdio)
    v
  MCACP
    |
    |  ACP (stdio, per agent)
    v
 Claude Code  ·  Gemini CLI  ·  Codex  ·  Auggie  ·  Copilot  ·  ...

What can you do with this?

Run any ACP agent from any MCP client. You don't need a dedicated IDE plugin for each agent. Install Gemini from Claude Code. Run Codex from Zed. Mix and match.

Compare agents side by side. Give the same task to Claude Code ACP and Gemini CLI in parallel sessions and compare the results.

Build agent-driven pipelines. One agent writes code, another reviews it, a third runs the tests. MCACP handles the lifecycle and permission flow for all of them.

Control permissions interactively. On hosts that support MCP elicitation (Zed), permission requests pop up as interactive forms. On hosts that don't (Claude Code), they fall back to operator mode where the host agent decides.

Resume where you left off. Sessions persist to disk. Shut down, restart, load_session — the agent picks up where it stopped.

Discover and install agents from chat. Browse the ACP registry, install agents, check for upgrades — without leaving your conversation.

Quick start

Install

npm install -g mcacp

Or run directly:

npx mcacp

Add to your MCP client

Claude Code (~/.claude/settings.json):

{
  "mcpServers": {
    "mcacp": {
      "command": "npx",
      "args": ["-y", "mcacp"]
    }
  }
}

Zed (settings.json):

{
  "context_servers": {
    "mcacp": {
      "command": { "path": "npx", "args": ["-y", "mcacp"] }
    }
  }
}

Then from chat:

"Search for available agents"        →  registry_search
"Install the Gemini agent"           →  agent_install
"Initialize it and start a session"  →  initialize + new_session
"Ask it to refactor auth"            →  prompt_start + prompt

MCP tools

MCACP exposes 22 tools organized into five groups.

Registry

Lifecycle

Sessions

Interaction

Status

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Mcacp: common questions

Is Mcacp MCP server safe?
Mostly: it is graded B (75/100). Read the Mcacp safety report
How do I install Mcacp?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Mcacp need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Mcacp maintained?
The last commit was 276 days ago (2026-02-01). The latest release is v0.1.3.
What can I use instead of Mcacp?
Servers from other publishers that do the same job: Argent MCP server, gflow-cli MCP server and Buoy Gg MCP server.
How does Mcacp compare with other Productivity MCP servers?
safety score 75/100 (higher than 40% of 1,299 Productivity servers); tools 24 (the typical Productivity server has 7); tools that change things 21% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Mcacp

Same job from other publishers: the closest match first, then the best rated.

  • Argent
    Drive iOS Simulators, Android emulators, TVs and Electron/web apps from your coding agent
    A
  • gflow-cli
    Drive Google Flow from an agent: Veo video and Imagen image generation
    A
  • Buoy Gg
    Let AI agents read and drive a running React Native or Flutter app through Buoy's devtools.
    A
  • Unreal Engine
    EngineWire: drive the Unreal Editor (UE 5.0-5.8): levels, Blueprints, UI, materials, VFX and more.
    B
  • CLEO MCP Server
    Task management for AI coding agents — CQRS 2-gateway pattern, 200 ops across 10 domains
    B