
Mcacp
- 8 repo stars
- Updated February 1, 2026
- Oortonaut/mcacp
io.github.Oortonaut/mcacp is an MCP server that bridges MCP clients to ACP coding agents over stdio.
About
io.github.Oortonaut/mcacp is a lightweight MCP server that bridges the Model Context Protocol to the Agent Client Protocol so developers can steer ACP coding agents from their existing MCP setup. Instead of juggling a separate ACP-only client, you register mcacp in Claude Code, Cursor, Windsurf, or another stdio-capable host and issue agent work through familiar MCP tooling. It targets developers who already standardized on MCP for repos, search, and deploy tools and now want the same entry point for autonomous coding sessions. Use it during Build when you are wiring agent stacks, experimenting with multi-agent flows, or delegating implementation to an ACP backend while you stay in the editor. The server is early (0.1.3) and focused: one npm package, stdio transport, GitHub source—ideal when protocol plumbing matters more than a full orchestration layer.
- Stdio MCP server (npm package mcacp v0.1.3) exposing an MCP-to-ACP bridge
- Lets any MCP client drive ACP coding agents from one config block
- Published on GitHub (Oortonaut/mcacp) with Model Context Protocol server schema
- No extra env vars in server.json—install and point your host at the stdio command
- Pairs with task-graph-mcp when you want governed workflows on top of ACP agents
Mcacp by the numbers
- Data as of Jul 22, 2026 (Skillselion catalog sync)
claude mcp add mcacp -- npx -y mcacpAdd your badge
Show developers this MCP server is listed on Skillselion. Paste this into your README.
| repo stars | ★ 8 |
|---|---|
| Package | mcacp |
| Transport | STDIO |
| Auth | None |
| Last updated | February 1, 2026 |
| Repository | Oortonaut/mcacp ↗ |
What it does
Run ACP-compatible coding agents from Claude Desktop, Cursor, or any MCP host without swapping clients.
Who is it for?
Best when you're already on MCP and want to pilot ACP coding agents without abandoning Claude Code or Cursor.
Skip if: Skip if you only need static API wrappers, geocoding, or OSINT lookups with no ACP agent backend.
What you get
After you add mcacp, the same MCP configuration can drive ACP agent sessions so implementation stays inside your current agent workflow.
- MCP tools that forward work to ACP coding agents
- Unified agent config without a second ACP-only desktop app
- Repeatable stdio MCP entry for local agent sessions
By the numbers
- Server version 0.1.3 on npm identifier mcacp
- Single stdio transport package in server.json
- GitHub repository Oortonaut/mcacp
README.md
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
| Tool | Description |
|---|---|
list_installed_agents |
List locally installed agents |
registry_search |
Search the ACP agent registry |
agent_install |
Install an agent from the registry |
agent_uninstall |
Remove an installed agent |
agent_check_upgrades |
Check for available upgrades |
discover_agents |
Scan editor configs (Zed, JetBrains) for agents |
reload_config |
Reload mcacp.json from disk |
Lifecycle
| Tool | Description |
|---|---|
initialize |
Spawn an agent process and perform the ACP handshake |
shutdown |
Gracefully shut down an agent |
Sessions
| Tool | Description |
|---|---|
new_session |
Create a session with working directory and permission policy |
load_session |
Resume a persisted session |
list_sessions |
List stored sessions for an agent |
close_session |
Close a session (preserved for later resume) |
Interaction
| Tool | Description |
|---|---|
prompt_start |
Send a prompt (returns immediately) |
prompt |
Block until events are available |
prompt_events |
Non-blocking poll for events |
grant_permission |
Resolve a pending permission request (operator mode) |
request_permission |
Send an MCP elicitation to the host for a permission decision |
cancel |
Cancel an in-progress prompt |
set_mode |
Switch agent operating mode |
Status
| Tool | Description |
|---|---|
list_running_agents |
List all agents with status and sessions |
get_agent_status |
Detailed status of a running agent |
set_agent_status |
Set status text for an agent |
Permission policies
Each session can use a different policy:
| Policy | Behavior |
|---|---|
allow_all |
Auto-approve all agent actions |
deny_all |
Block all tool use |
elicit |
Forward as MCP elicitations to the host; falls back to operator if unsupported |
operator |
Queue as events — the host agent decides via grant_permission |
Operator flow
Orchestrator MCACP ACP Agent
| | |
|-- prompt(sessionId, ...) ->| |
| |-- session/prompt --------->|
| |<- request_permission ------|
|<- {pendingPermission: ...} | |
| | |
|-- grant_permission ------->| |
| {toolCallId, optionId} |-- permission outcome ----->|
| |<- prompt result -----------|
|<- {stopReason, updates} | |
Configuration
MCACP looks for mcacp.json in these locations (first found wins):
--configflag orMCACP_CONFIGenv var.mcacp/mcacp.jsonin the current directory~/.config/mcacp/mcacp.json
{
"registries": ["https://cdn.agentclientprotocol.com/registry/v1/latest/registry.json"],
"defaultPermissionPolicy": "elicit",
"agent_servers": {
"my-custom-agent": {
"command": "node",
"args": ["my-agent.js"]
}
}
}
See docs/configuration.md for the full schema.
Building from source
git clone https://github.com/Oortonaut/mcacp.git
cd mcacp
npm install
npm run build
node dist/index.js
License
Recommended MCP Servers
How it compares
Protocol bridge MCP server, not a workflow graph or standalone agent skill.
FAQ
Who is io.github.Oortonaut/mcacp for?
Developers who use MCP daily and want ACP coding agents callable from that same host.
When should I use io.github.Oortonaut/mcacp?
Use it during Build when connecting your editor’s MCP client to an ACP agent runtime for delegated coding tasks.
How do I add io.github.Oortonaut/mcacp to my agent?
Install the npm package mcacp (v0.1.3), add a stdio MCP server entry pointing at that binary, and restart your MCP-capable client.