ESG MCP Servers runs on your own machine — the client starts it, so there is no endpoint to ping. 111 installs a week from pypi. Last commit 28 Feb 2026.
31 MCP tools for ESG data extraction, PDF processing, vector search, and EU regulation analysis.
Nothing serious here today
Today is the operative word: we check ESG MCP Servers every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Connect this server
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add esg-mcp-servers -e 'ANTHROPIC_API_KEY=<ANTHROPIC_API_KEY>' -e 'POSTGRES_DSN=<POSTGRES_DSN>' -e 'MONGODB_URI=<MONGODB_URI>' -- uvx esg-mcp-servers{
"mcpServers": {
"esg-mcp-servers": {
"command": "uvx",
"args": [
"esg-mcp-servers"
],
"env": {
"ANTHROPIC_API_KEY": "<ANTHROPIC_API_KEY>",
"MONGODB_URI": "<MONGODB_URI>",
"POSTGRES_DSN": "<POSTGRES_DSN>"
}
}
}
}[mcp_servers.esg-mcp-servers]
command = "uvx"
args = ["esg-mcp-servers"]
env = { ANTHROPIC_API_KEY = "<ANTHROPIC_API_KEY>", POSTGRES_DSN = "<POSTGRES_DSN>", MONGODB_URI = "<MONGODB_URI>" }{
"mcpServers": {
"esg-mcp-servers": {
"command": "uvx",
"args": [
"esg-mcp-servers"
],
"env": {
"ANTHROPIC_API_KEY": "<ANTHROPIC_API_KEY>",
"MONGODB_URI": "<MONGODB_URI>",
"POSTGRES_DSN": "<POSTGRES_DSN>"
}
}
}
}{
"servers": {
"esg-mcp-servers": {
"type": "stdio",
"command": "uvx",
"args": [
"esg-mcp-servers"
],
"env": {
"ANTHROPIC_API_KEY": "<ANTHROPIC_API_KEY>",
"MONGODB_URI": "<MONGODB_URI>",
"POSTGRES_DSN": "<POSTGRES_DSN>"
}
}
}
}Put your own values in place of
<ANTHROPIC_API_KEY> (Anthropic API key — required for RAG queries and LLM-based metric extraction), <POSTGRES_DSN> (PostgreSQL connection string with pgvector extension (e.g. postgresql://esg:esg@localhost/esg_platform)), <MONGODB_URI> (MongoDB connection string for PDF binary storage via GridFS (e.g. mongodb://localhost:27017)).
The author’s registry entry marks them as required.
Optional settings from the registry entry, left out of the block above:
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)).
Alternatives to ESG MCP Servers
same job, measured the same wayLocal FAISS vector database for RAG with document ingestion, semantic search, and MCP prompts.
MCP server exposing HouyiDB vector search, collection status, and opt-in writes.
Bounded tools for rendering, extraction, RAG, enrichment, local discovery and review analysis.
Web design analysis with 26 MCP tools: layout, motion, quality, semantic search via pgvector
Web search, scraping, RAG answers with citations, and translation as MCP tools.
Temporal memory MCP server with LanceDB vector search, weight-decay scoring, and LLM consolidation
Encrypted-first embedded database with vector search and agent memory, exposed as MCP tools
Geospatial analysis: vector and raster GIS operations, cartographic maps, spatial data access
ESG MCP Servers — questions
Answers built from our own checks of this server.