Log inSubmit server
Agent Link logo

Agent Link

Spawn, coordinate, and converse with local AI coding-agent CLIs through MCP.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Agent Link

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": {
    "agent-link": {
      "command": "npx",
      "args": [
        "-y",
        "agent-link-mcp"
      ]
    }
  }
}

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

Install not yet sandbox-tested— the server itself is confirmed live (we called its tools/list endpoint). The stdio install command is a separate, ongoing check.

Overview

agent-link connects an MCP-compatible host to installed AI coding-agent CLIs such as Claude Code, Codex, Gemini CLI, and Aider. It can start one or many agents, pass tasks and context, handle clarification questions, and return results through MCP tools. Use it for second opinions, parallel reviews, cross-model workflows, or delegating coding subtasks. Agent sessions run as local subprocesses and remain in memory while the server is running.

Use cases

  • Delegate a stuck debugging task to another coding agent
  • Run parallel code reviews for bugs and security issues
  • Compare implementation advice from different agent CLIs
  • Build research, implementation, and review pipelines
  • Answer clarification questions from delegated agents

Key features

  • Spawn individual agent CLI subprocesses
  • Run multiple agents in parallel
  • Continue tasks through clarification replies
  • Retry failed tasks with optional escalation
  • Inspect available agents and active sessions
  • Terminate running agent sessions

Tools6

What Agent Link lets your agent do. Expand a tool for its parameters.

Verified live~953 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; 6 declare their own safety hints.

Runs commands · 2Can delete or modify data · 1Makes network requests · 2Read-only tools · 3
Network at startup3 connections
Files written at startupNone
Install scriptsNone
npm provenanceNot published
Package age213 days
Maintainers1

Observed 2026-10-22 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 13d ago via OSV.dev · agent-link-mcp (npm)

Adoption & maintenance

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

GitHub stars11Stargazers on the source repository.
npm downloads224Package downloads in the last 30 days.
Last commit9d agoMost recent push to the default branch.
Tools exposed6Callable tools this server registers over MCP.
Directory activity5 viewsConfig copies, upvotes, and views on AllMCPs.

How Agent Link works

What agent-link does

agent-link exposes local AI coding-agent command-line tools through MCP. A host agent can delegate a task to Claude Code, Codex, Gemini CLI, Aider, or another configured CLI, then receive either a completed result or a question requiring clarification. The host can answer that question with reply, allowing the work to continue.

The server supports both single-agent and multi-agent workflows. spawn_agent handles one task, while spawn_agents starts several independent tasks concurrently and returns their results together. This fits code review, bug investigation, architectural comparison, research followed by implementation, and other workflows where separate agents can work in parallel or provide different perspectives.

How it works

The MCP host calls an agent-link tool, which launches the selected agent CLI as a subprocess. Tasks can include a working directory, file references, an error description, intent, or Git diff content. The selected CLI processes the request and returns text that agent-link interprets as a result or a clarification request.

A waiting session receives an identifier such as codex-a1b2c3. The host passes that identifier and its response to reply; agent-link invokes the CLI again with the recorded task, context, working directory, and conversation. This is a fresh CLI invocation rather than a provider-side session resume. Concurrent replies to the same session are rejected.

Sessions are held in memory and are lost when the server restarts. kill_agent waits for the child process to stop and escalates after five seconds if necessary. Shutting down the server also cancels active child processes.

Setup and configuration

Node.js 20 or later is required, including the environment used by the MCP host's npx command. Install and authenticate each agent CLI you intend to use. The supported built-in profiles detect the claude, codex, gemini, and aider commands when they are available.

The server can be launched directly with:

Terminal
npx agent-link-mcp

For example, Claude Code can register it with claude mcp add agent-link npx agent-link-mcp, and Codex can use codex mcp add agent-link npx agent-link-mcp. Only the host agent needs the MCP server; delegated agents run as subprocesses and do not need agent-link installed.

Aider requires either OPENAI_API_KEY or ANTHROPIC_API_KEY. The other agent CLIs have their own installation and authentication steps, such as claude login, codex login, or Gemini's interactive sign-in flow.

Custom profiles are configured in ~/.agent-link/config.json. Profiles can specify the executable command, arguments, prompt handling, and output format. JSON profiles must return one result object containing a string result field; error markers are treated as failures.

Tools and capabilities

  • spawn_agent: Start one agent with a task, optional context, model, reasoning level, retry behavior, escalation, working directory, and timeout.
  • spawn_agents: Run multiple agent tasks in parallel and return aggregate counts plus individual results.
  • reply: Answer a clarification question and continue the associated task.
  • kill_agent: Stop an active session and clean up its resources.
  • list_agents: Show detected agent commands and their availability.
  • get_status: Show active sessions, agent identifiers, statuses, and start times.

Tasks can request automatic retries, with up to three attempts, and optional increases to the thinking level during retries. The default task timeout is one hour, with a maximum value controlled by the supplied timeout setting.

Limitations and notes

The delegated CLIs must be installed and authenticated separately, and each may impose additional requirements. Agent-link works with command-line tools that accept a prompt and return text; custom JSON output must follow the expected result shape. In-memory sessions do not survive a restart, and a reply does not resume a provider-managed session.

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 Agent Link

agent-link is an MCP server that connects an MCP host to local AI coding-agent CLIs, including Claude Code, Codex, Gemini CLI, and Aider. Its main tools spawn one or many agents, exchange clarification replies, inspect sessions, and terminate active work. Agents run as subprocesses on the host system.

Install it through an MCP client with `npx agent-link-mcp`, such as `claude mcp add agent-link npx agent-link-mcp` or `codex mcp add agent-link npx agent-link-mcp`. Node.js 20 or later is required, and the agent CLIs you plan to use must be installed separately.

agent-link includes built-in profiles for Claude Code, Codex, Gemini CLI, and Aider, and it auto-detects their installed commands. Custom profiles can be added through `~/.agent-link/config.json` for compatible command-line agents that accept prompts and return text.

The documented setup names Claude Code, Codex, and any MCP client, but does not provide a Cursor-specific configuration. The server is launched as a standard MCP process with `npx agent-link-mcp`.

Related MCP servers

All in Coding Agents 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 PreviewAgent Link AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/agent-link?style=directory)](https://allmcps.com/mcp/agent-link)
HTML Embed
<a href="https://allmcps.com/mcp/agent-link"><img src="https://allmcps.com/api/badge/agent-link?style=directory" alt="Agent Link on AllMCPs" /></a>