ChatSpatial
by cafferychen777
Overview
Perform spatial transcriptomics analysis through natural language queries, integrating diverse bioinformatics methods.
Installation
python -m chatspatial serverEnvironment Variables
- CHATSPATIAL_DATA_DIR
- CHATSPATIAL_CACHE_DIR
Security Notes
The server uses `os.system` to download the CellPhoneDB database, with the URL potentially controllable via the `cellphonedb_db_path_url` parameter. If an LLM could inject a malicious URL, this could lead to arbitrary file download or execution. The `rpy2` library is used extensively to execute R code for various analysis methods (e.g., SCTransform, CARD, Numbat, scType). While R code blocks are defined in Python, parameters sourced from user input (e.g., `sctype_db_`) are passed to R contexts, creating a potential for arbitrary R code injection if input validation is insufficient. This presents a high risk of remote code execution. Additionally, the `mllmcelltype` tool makes external API calls to various LLM providers, which requires careful management of API keys and network access.
Similar Servers
fastmcp
FastMCP is a Python framework for building and managing Model Context Protocol (MCP) servers and clients. It facilitates the creation of AI agents by defining tools, resources, and prompts, supporting both local and distributed execution, flexible communication transports (HTTP/S, SSE, Stdio), advanced authentication, background task management, and integration with large language models (LLMs) and external APIs. It's designed for creating robust and observable AI-powered microservices.
mcp-use
A full-stack framework for building Model Context Protocol (MCP) servers, clients, and AI agents in Python and TypeScript, with support for UI widgets, code execution, and observability.
gis-mcp
A Model Context Protocol (MCP) server that provides AI agents and LLMs with comprehensive GIS capabilities, enabling geospatial analysis, data gathering, and transformations through natural language.
Polymcp
A comprehensive TypeScript framework for building and orchestrating Model Context Protocol (MCP) servers and AI agents, enabling LLMs to intelligently discover, select, and execute external tools.