rdkit-mcp-server
by tandemai-inc
Overview
Enables Large Language Models (LLMs) to access RDKit cheminformatics functions through natural language.
Installation
python run_server.py [--settings settings.yaml]Environment Variables
- OPENAI_API_KEY
Security Notes
The server exposes file system interaction tools (e.g., `read_file`, `write_file`, `mol_to_sdf`, `pdb_to_mol`, `MolToFile`) that accept arbitrary file paths from LLM input. There is no apparent sanitization or restriction of these paths to a safe, confined directory within the provided source code, making it vulnerable to directory traversal attacks, arbitrary file reads, and writes. This allows a malicious or jailbroken LLM to potentially access or modify sensitive files on the host system.
Similar Servers
mcpo
Exposes Model Context Protocol (MCP) tools as OpenAPI-compatible HTTP servers.
mem-agent-mcp
Provides a Model Context Protocol (MCP) server for a memory agent, enabling LLMs to interact with an Obsidian-like memory system for contextual assistance and RAG.
mcp-server
Provides a Model Context Protocol (MCP) server for AI agents to search and retrieve curated documentation for the Strands Agents framework, facilitating AI coding assistance.
Polymcp
A comprehensive toolkit and agent framework for building Model Context Protocol (MCP) servers and orchestrating them with Large Language Models (LLMs) across Python and TypeScript environments.