What kind of data does TheGraph MCP Server provide?
It provides indexed blockchain data from The Graph’s subgraphs, such as token prices, trading volumes, and swap events.
@kukapay
Basic information
An MCP server that powers AI agents with indexed blockchain data from The Graph.
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"thegraph-mcp": {
"command": "uv",
"args": [
"--directory",
"path/to/thegraph-mcp",
"run",
"main.py"
],
"env": {
"THEGRAPH_API_KEY": ""
}
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
TheGraph MCP Server is an MCP server that powers AI agents with indexed blockchain data from The Graph. It is built for developers who want AI assistants to fetch and analyze on-chain data through subgraphs.
Clone the repository and configure your MCP client with the uv command pointing to main.py. Set the THEGRAPH_API_KEY environment variable with your The Graph API key. Use the tools getSubgraphSchema and querySubgraph to fetch schema or run GraphQL queries.
It provides indexed blockchain data from The Graph’s subgraphs, such as token prices, trading volumes, and swap events.
Python 3.10 or higher, the `uv` package manager, and a valid The Graph API key configured in the environment variable `THEGRAPH_API_KEY`.
Add a JSON entry under `mcpServers` with the command `uv`, args pointing to the cloned directory and `main.py`, and the API key in the env section.
Yes, the `querySubgraph` tool executes any GraphQL query string, whether AI-generated or manually written.
A curated list of references for MLOps

A good sequence diagram can solve almost any communication problem in engineering. Volley lets your agent write them as plain text, with the real request and response payloads on every arrow. It checks its own syntax wi
AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

B2B competitive intelligence, live sales battlecards, 5-axis ICP prospect fit scoring, and tech stack teardowns over MCP and REST with cited public-web evidence.
🚀 The fast, Pythonic way to build MCP servers and clients.
Comments