director — security grade SAFE, quality 68/100

Security audit verdict: SAFE · quality 68/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by fdmtl · MCP Server · ★ 482

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is director safe to install? View the security audit →

About director

Director MCP Playbooks for AI agents curl -LsSf https://director.run/install.sh | sh Overview Director allows you to provide playbooks to AI Agents. A playbook is a set of MCP tools, prompts and configuration, that give agents new skills. 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. https://github.com/user-attachments/assets/cafc0902-a854-4ee8-ac89-b7535f10c93d Key Features 📚 Playbooks -

mcpmcp-clientmcp-gatewaymcp-hostmcp-middlewaremcp-servermcp-tools

Quick Facts

Stars482
Forks74
LanguageTypeScript
CategoryMCP Server
LicenseAGPL-3.0
Quality Score67.8618280351389/100
Open Issues4
Last Updated2026-09-03
Created2025-03-20
Platformscli, mcp, node
Est. Tokens~16k

Compatible Skills

These tools work well together with director for enhanced workflows:

  • director — semantic(1.00)+rare_topics+same_lang+similar_pop+shared_platform (68%)
  • metamcp — semantic(0.56)+rare_topics+same_lang+similar_pop+shared_platform (63%)
  • archestra — semantic(0.57)+rare_topics+same_lang+similar_pop+shared_platform (59%)
  • Unla — semantic(0.45)+rare_topics+same_lang+similar_pop+shared_platform (55%)
  • mcphub — semantic(0.42)+rare_topics+same_lang+similar_pop+shared_platform (54%)

director alternative? Top 6 similar tools

Looking for a director alternative? If you're comparing director with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • director by director-run · ⭐ 465

    MCP Playbooks for AI agents

  • mcpstore by ip2a · ⭐ 431

    Elegantly manage your MCP services

  • mcpstore by whillhill · ⭐ 427

    开盒即用的优雅管理mcp服务 | 结合Agent框架 | 作者听劝 | 已发布pypi | Vue页面demo

  • remote-mcp-server by gleanwork · ⭐ 164

    Remote MCP Server that securely connects Enterprise context with your LLM, IDE, or agent platform of choice.

  • mcp-router by mcp-router · ⭐ 2.1k

    MCP Router — development, support and security updates ended 2026-09-18. Historical source and final release f

  • arcade-mcp by ArcadeAI · ⭐ 1.0k

    MCP Server Framework and Tool Development library for building custom capabilities into agents.

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is director?

director is MCP Playbooks for AI agents. It is categorized as a MCP Server with 482 GitHub stars.

What programming language is director written in?

director is primarily written in TypeScript. It covers topics such as mcp, mcp-client, mcp-gateway.

How do I install or use director?

You can find installation instructions and usage details in the director GitHub repository at github.com/fdmtl/director. The project has 482 stars and 74 forks, indicating an active community.

What license does director use?

director is released under the AGPL-3.0 license, making it free to use and modify according to the license terms.

What are the best alternatives to director?

The top alternatives to director on Agent Skills Hub include director, mcpstore, mcpstore. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse MCP Server tools