Log inSubmit server
Throng MCP logo

Throng MCP

Delegate tasks to Claude Code, Codex, OpenCode, Gemini CLI, Cursor CLI, or Copilot CLI through persistent ACP sessions.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Throng MCP

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "throng-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "throng-mcp"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Automated check passed— started and listed 6 tools correctly (Today).

Overview

Throng MCP lets an MCP client delegate work to another agent harness or model over the Agent Client Protocol (ACP). It can start persistent sessions, send follow-up messages, run several tasks in the background, and return results that conform to a supplied JSON Schema. Reach for it when you want a second model's review, a staged agent workflow, or structured findings that can feed into another task. It runs as a standard stdio MCP server through npm or a global installation.

Use cases

  • Ask another model to review a code change
  • Run repository analysis in the background
  • Pass structured findings between agents
  • Send fixes to one agent and verification to another
  • Continue an existing agent session with new instructions

Key features

  • ACP-based delegation to multiple agent harnesses
  • Persistent nested sessions with follow-up messages
  • Background execution and result collection
  • JSON Schema-constrained responses
  • Custom harness configuration
  • Harness availability and model discovery

Tools6

What Throng MCP lets your agent do. Expand a tool for its parameters.

Verified live~1.3k tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 2d ago

Recent health check succeeded.

What it can do

From the 6 tools this server returned when we ran it.

Read-only tools · 6
Network at startup3 connections
Files written at startupNone
Install scriptsNone
npm provenanceSigned build
Package age25 days
Maintainers1

Observed 2026-10-28 in an isolated sandbox. A description of reach, not a security audit.

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 7d ago via OSV.dev · throng-mcp (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars2Stargazers on the source repository.
npm downloads1.5kPackage downloads in the last 30 days.
Last commit4d agoMost recent push to the default branch.
Availability100%Our rolling endpoint + install checks that succeeded.
Install checkPassedOur sandbox started it and listed its tools.
Tools exposed6Callable tools this server registers over MCP.

How Throng MCP works

What Throng MCP does

Throng MCP routes work from one MCP client to another agent harness or model. Supported built-in harnesses include Claude Code, Codex, OpenCode, Gemini CLI, Cursor CLI, and GitHub Copilot CLI. Other ACP-compatible agents can be added as custom harnesses by describing their command and approval behavior.

The main workflow is delegation. A calling agent can ask one harness to inspect a repository, ask another to make changes, and then return to the first session for a follow-up review. This supports workflows such as independent code review, implementation followed by verification, and staged second opinions.

Results can be requested against a JSON Schema, allowing the caller to receive structured data such as findings, verdicts, plans, file locations, or reproduction steps instead of parsing free-form prose.

How it works

The server communicates with MCP clients over stdio and starts nested agents through ACP. Claude Code and Codex use separate ACP adapters; OpenCode, Gemini CLI, Cursor CLI, and Copilot CLI expose ACP interfaces directly. Each nested session remains available for later messages, so follow-up requests retain the session's prior context.

A call can run synchronously or use background execution. Background work returns immediately, and a later wait operation collects the result. This makes it possible to run multiple agent tasks while continuing work in the primary session.

The nested agent operates in the directory supplied by the caller and uses the permissions of the account running it. A harness must be installed and authenticated separately before it can accept delegated work.

Setup and configuration

Install the server with npx -y throng-mcp, which downloads and caches the package on first use, or install it globally with npm i -g throng-mcp and run throng-mcp. Node.js ^22.13 or >=24 is required.

Register the command as a stdio server in the MCP client. Claude Code can use claude mcp add --scope user throng -- npx -y throng-mcp; Codex uses codex mcp add throng -- npx -y throng-mcp. Other MCP clients should register the same command as a local stdio server.

Install and authenticate each harness separately. Claude Code and Codex require their ACP adapter packages. OpenCode, Gemini CLI, Cursor CLI, and Copilot CLI provide ACP themselves. Gemini CLI requires a Gemini API key or Vertex configuration, while Cursor CLI and Copilot CLI require their respective login commands.

Custom harnesses can be configured with their executable command and the options controlling approval behavior. Throng does not install or infer settings for custom harnesses.

Tools and capabilities

  • list_harnesses checks installed adapters and reports available harnesses, models, effort levels, and configured harnesses that are unavailable.
  • run_thronglet starts a delegated agent session with an agent selection, prompt, repository path, optional background mode, and optional JSON Schema.
  • send_message sends additional work to an existing nested session while preserving its context.
  • wait_thronglet retrieves the result of a background run.
  • Structured responses can be constrained to a caller-provided JSON Schema.
  • Multiple delegated sessions can run concurrently.

Limitations and notes

The server does not include the agent CLIs or ACP adapters. Those components, along with their authentication, must be installed and configured independently. A harness that is not installed will not appear as available, and failed authentication can make an otherwise configured harness unavailable.

Built-in harness behavior has provider-specific limits documented by the project for Gemini CLI, Cursor CLI, and GitHub Copilot CLI. Copilot CLI authentication through only the GitHub CLI can prevent model selection and cause runs to fail; its own copilot login flow is required for that use case.

The optional skills/throng package teaches a calling agent when and how to use the server, but it is not required for the MCP server itself. New agent sessions may be needed after installing that skill.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Throng MCP

Throng MCP is an MCP server that connects an MCP client to agent harnesses including Claude Code, Codex, OpenCode, Gemini CLI, Cursor CLI, and GitHub Copilot CLI. Its main tools start delegated sessions, send follow-up messages, wait for background runs, and list available harnesses, with optional JSON Schema-structured results.

Install it with `npx -y throng-mcp` or run `npm i -g throng-mcp` and use `throng-mcp`. Register that command as a stdio MCP server in your client, then install and authenticate the agent harnesses you want to use.

Throng MCP supports Claude Code, Codex, OpenCode, Gemini CLI, Cursor CLI, and GitHub Copilot CLI. Claude Code and Codex require ACP adapter packages; the other listed harnesses expose ACP directly. Custom ACP agents can also be configured with their command and approval options.

Yes, set a delegated run to background mode and collect its result later with `wait_thronglet`. This allows multiple nested agents to work concurrently while the primary MCP client continues handling other tasks.

Yes, `run_thronglet` accepts a JSON Schema and can return data matching that schema instead of prose. This is suitable for passing findings, plans, verdicts, file locations, or reproduction steps into a later agent call.

Related MCP servers

All in Developer Tools All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewThrong MCP AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/throng-mcp?style=directory)](https://allmcps.com/mcp/throng-mcp)
HTML Embed
<a href="https://allmcps.com/mcp/throng-mcp"><img src="https://allmcps.com/api/badge/throng-mcp?style=directory" alt="Throng MCP on AllMCPs" /></a>