ESG MCP Servers

31 MCP tools for ESG data extraction, PDF processing, vector search, and EU regulation analysis.

stdio v0.1.2

Connection Configuration

Add this to your AI agent's MCP config file to connect.

Run in your terminal:

claude mcp add io.github.freminder--esg-mcp-servers -- uvx

Transport

stdio

Authentication

None

Version

v0.1.2

Server Name

io.github.freminder/esg-mcp-servers

Last Updated

Feb 28, 2026

How to install and connect this MCP server.

Environment variables you must provide when running this server.

Variable	Description	Required
`ANTHROPIC_API_KEY` secret	Anthropic API key — required for RAG queries and LLM-based metric extraction	Yes
`POSTGRES_DSN`	PostgreSQL connection string with pgvector extension (e.g. postgresql://esg:esg@localhost/esg_platform)	Yes
`MONGODB_URI`	MongoDB connection string for PDF binary storage via GridFS (e.g. mongodb://localhost:27017)	Yes
`EMBEDDING_MODEL`	Sentence-transformer model name for embedding generation (default: Snowflake/snowflake-arctic-embed-l-v2.0)	Optional
`EMBEDDING_DIMENSIONS`	Embedding vector dimension size (default: 1024)	Optional