data-commons-mcp
Verified Safeby EOSC-Data-Commons
Overview
Provides natural language search over open-access datasets and tools using a Large Language Model-assisted search, compliant with the Model Context Protocol (MCP).
Installation
uv run uvicorn src.data_commons_search.main:app --log-config logging.yml --reloadEnvironment Variables
- OPENSEARCH_URL
- EINFRACZ_API_KEY
- MISTRAL_API_KEY
- OPENROUTER_API_KEY
- CHAT_API_KEY
- SERVER_PORT
- SERVER_HOST
- CORS_ENABLED
- DEBUG_ENABLED
- OPENSEARCH_INDEX
- EMBEDDING_MODEL
- EMBEDDING_DIMENSIONS
- LLM_MAX_TOKENS
- LLM_SEED
- APP_NAME
- LOGS_FILEPATH
- OPENSEARCH_RESULTS_COUNT
- RERANKING_RESULTS_COUNT
- FILEMETRIX_API
- TOOL_REGISTRY_API
Security Notes
API keys for LLM providers and optional chat API key are loaded from environment variables (keys.env), which is a good practice. The system uses CORS (allow_origins=['*']), common for public APIs but requires consideration for sensitive operations. No direct 'eval' on user-controlled input or obvious code injection vulnerabilities were found. Debug logging should be disabled in production environments.
Similar Servers
mcp-server-elasticsearch
Enables AI clients to interact with Elasticsearch data through natural language conversations using the Model Context Protocol (MCP) by exposing a set of predefined tools.
mcp-omnisearch
Provides a unified interface for LLMs to access multiple web search, AI response, content processing, and enhancement tools from various providers through the Model Context Protocol (MCP).
mcp-openapi-server
Exposes OpenAPI endpoints as Model Context Protocol (MCP) tools, enabling Large Language Models (LLMs) to discover and interact with REST APIs through a standardized protocol.
gis-mcp
Enables Large Language Models (LLMs) to perform comprehensive geospatial analysis, transformations, and data operations using popular GIS libraries.