{"servers":[{"server":{"$schema":"https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json","name":"io.github.freminder/esg-mcp-servers","description":"31 MCP tools for ESG data extraction, PDF processing, vector search, and EU regulation analysis.","title":"ESG MCP Servers","repository":{"url":"https://github.com/freminder/esg-mcp-servers","source":"github"},"version":"0.1.2","packages":[{"registryType":"pypi","identifier":"esg-mcp-servers","version":"0.1.2","transport":{"type":"stdio"},"environmentVariables":[{"description":"Anthropic API key — required for RAG queries and LLM-based metric extraction","isRequired":true,"format":"string","isSecret":true,"name":"ANTHROPIC_API_KEY"},{"description":"PostgreSQL connection string with pgvector extension (e.g. postgresql://esg:esg@localhost/esg_platform)","isRequired":true,"format":"string","name":"POSTGRES_DSN"},{"description":"MongoDB connection string for PDF binary storage via GridFS (e.g. mongodb://localhost:27017)","isRequired":true,"format":"string","name":"MONGODB_URI"},{"description":"Sentence-transformer model name for embedding generation (default: Snowflake/snowflake-arctic-embed-l-v2.0)","format":"string","name":"EMBEDDING_MODEL"},{"description":"Embedding vector dimension size (default: 1024)","format":"string","name":"EMBEDDING_DIMENSIONS"}]}]},"_meta":{"io.modelcontextprotocol.registry/official":{"status":"active","statusChangedAt":"2026-02-28T09:59:45.171386Z","publishedAt":"2026-02-28T09:59:45.171386Z","updatedAt":"2026-02-28T09:59:45.171386Z","isLatest":true}}}],"metadata":{"count":1}}