Flagged: environment access. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by NapthaAI · MCP Server · ★ 303
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is automcp safe to install? View the security audit →
automcp 🚀 Overview automcp allows you to easily convert tools, agents and orchestrators from existing agent frameworks into MCP servers, that can then be accessed by standardized interfaces via clients like Cursor and Claude Desktop. We currently support deployment of agents, tools, and orchestrators as MCP servers for the following agent frameworks: CrewAI LangGraph Llama Index OpenAI Agents SDK Pydantic AI mcp-agent 🔧 Installation Install from PyPI: Or install from source: 🧩 Quick Start Create a new MCP server for your project: Navigate to your project directory with your agent implementation: Generate the MCP server files via CLI with one of the following flags (crewai, langgraph, llamaindex, openai, pydantic, mcpagent): Edit the generated file to configure your agent: python Replace these imports with your actual agent classes from yourmodule import YourCrewClass Define the input schema class InputSchema(BaseModel): parameter1: str parameter2: str Set your agent details name = "" description = "" For CrewAI projects mcp
| Stars | 303 |
| Forks | 148 |
| Language | Python |
| Category | MCP Server |
| License | Apache-2.0 |
| Quality Score | 67.0486925276839/100 |
| Open Issues | 6 |
| Last Updated | 2025-04-18 |
| Created | 2025-03-28 |
| Platforms | mcp, python |
| Est. Tokens | ~47k |
Explore other popular mcp server tools:
automcp is Easily convert tool, agents and orchestrators from existing agent frameworks to MCP servers. It is categorized as a MCP Server with 303 GitHub stars.
automcp is primarily written in Python.
You can find installation instructions and usage details in the automcp GitHub repository at github.com/NapthaAI/automcp. The project has 303 stars and 148 forks, indicating an active community.
automcp is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
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: