What is the director MCP server?

fdmtl/director — MCP Playbooks for AI agents AgentRank score: 70.0/100.

Is the director MCP server actively maintained?

The director MCP server was last committed 2mo ago and has 5 contributors. Issue health: 84% of issues resolved. AgentRank freshness score reflects real-time maintenance activity.

director MCP Server

Name: fdmtl/director
Rating: 3.8 (1 reviews)
Author: fdmtl

fdmtl/director

Score: 70.0 Rank #4064 LLM Client

[![AgentRank](https://agentrank-ai.com/api/v1/badge/fdmtl--director)](https://agentrank-ai.com/tool/fdmtl--director/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge)

Are you the maintainer of fdmtl/director? Claim this listing →

MCP Playbooks for AI agents

Add AgentRank to Claude Code Discover and compare tools like fdmtl/director — your AI finds the right one automatically

Get API Access →

claude mcp add agentrank -- npx -y agentrank-mcp-server

Overview

fdmtl/director is a TypeScript tool licensed under AGPL-3.0. MCP Playbooks for AI agents Topics: mcp, mcp-client, mcp-gateway, mcp-host, mcp-server, mcp-tools, mcp-middleware.

Ranked #4064 out of 24846 indexed tools.

Ecosystem

TypeScript AGPL-3.0

mcpmcp-clientmcp-gatewaymcp-hostmcp-servermcp-toolsmcp-middleware

Score Breakdown

Stars 15% 482

482 stars → growing community

Freshness 25% 2mo ago

Last commit 2mo ago → moderate activity

Issue Health 25% 84%

27/32 issues closed → responsive maintainer

Contributors 10% 5

5 contributors → small team

Dependents 25% 0

No dependents → no downstream usage

npm Downloads N/A

PyPI Downloads N/A

Forks 78

Description Brief

License AGPL-3.0

Weights: Freshness 20% · Issue Health 20% · Dependents 22% · Stars 10% · Contributors 8% · How we score →

How to Improve

Description low impact

Expand your description to 150+ characters for better discoverability

Freshness high impact

Last commit was 69 days ago — a recent commit would boost your freshness score

Dependents medium impact

No downstream dependents detected yet — adoption by other projects is the strongest trust signal

Badge all embed codes →

Markdown

[![AgentRank](https://agentrank-ai.com/api/v1/badge/fdmtl--director)](https://agentrank-ai.com/tool/fdmtl--director/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge)

HTML

<a href="https://agentrank-ai.com/tool/fdmtl--director/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge"><img src="https://agentrank-ai.com/api/v1/badge/fdmtl--director" alt="AgentRank"></a>

Embed Widget docs →

HTML

<script src="https://agentrank-ai.com/embed.js" data-tool="fdmtl/director"></script>

Details

Stars: 482
Forks: 78
Open Issues: 5
Closed Issues: 27
Contributors: 5
Dependents: —
Language: TypeScript
License: AGPL-3.0
Last Commit: 2mo ago

Matched Queries

topic:mcptopic:mcp-server

From the README

<h1 align="center">Director</h1>
<p align="center">MCP Playbooks for AI agents</p>

<p align="center"><code>curl -LsSf https://director.run/install.sh | sh</code></p>

---

<div align="center">

</div>

# Overview

Director allows you to provide <ins>**playbooks**</ins> to AI Agents. A playbook is a set of <ins>**MCP tools**</ins>, <ins>**prompts**</ins> and <ins>**configuration**</ins>, that give agents new <ins>**skills**</ins>. You can connect Claude, Cursor and VSCode in 1-click, or integrate manually through a single MCP endpoint.

Playbooks are portable and can easily be switched in and out of context. Director is local-first - setup and client integration takes 30 seconds. In addition, Director provides all of the MCP management functionality that you'd expect: tool filtering, logging, strong isolation, and unified OAuth.

<br /><br />

https://github.com/user-attachments/assets/cafc0902-a854-4ee8-ac89-b7535f10c93d

## Key Features

- 📚 **Playbooks** - Maintain sets of tools, p

Read full README on GitHub →