← Index

ESG MCP Servers

io.github.freminder/esg-mcp-servers·v0.1.2·Documents & Spreadsheets
Quality Score
83
/100

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

§01  Install
Claude Desktop (uvx)
{
  "mcpServers": {
    "esg-mcp-servers": {
      "command": "uvx",
      "args": [
        "esg-mcp-servers"
      ],
      "env": {
        "ANTHROPIC_API_KEY": "<your-anthropic_api_key>",
        "POSTGRES_DSN": "<postgres_dsn>",
        "MONGODB_URI": "<mongodb_uri>",
        "EMBEDDING_MODEL": "<embedding_model>",
        "EMBEDDING_DIMENSIONS": "<embedding_dimensions>"
      }
    }
  }
}
§02  Environment variables
ANTHROPIC_API_KEY
requiredsecret

Anthropic API key — required for RAG queries and LLM-based metric extraction

POSTGRES_DSN
required

PostgreSQL connection string with pgvector extension (e.g. postgresql://esg:esg@localhost/esg_platform)

MONGODB_URI
required

MongoDB connection string for PDF binary storage via GridFS (e.g. mongodb://localhost:27017)

EMBEDDING_MODEL

Sentence-transformer model name for embedding generation (default: Snowflake/snowflake-arctic-embed-l-v2.0)

EMBEDDING_DIMENSIONS

Embedding vector dimension size (default: 1024)

§03  MCP Quality Score  ·  methodology
freshness
23
completeness
15
installability
25
documentation
15
stability
5
§04  Alternatives in Documents & Spreadsheets