
Connects Claude to The Graph's decentralized blockchain indexing network through GraphQL queries against deployed subgraphs. You get indexed data from Ethereum, Polygon, and other supported chains without running your own nodes or parsing raw blocks. The gateway runs at pipeworx.io and includes an ask_pipeworx tool that translates natural language questions into the right GraphQL queries automatically. Useful when you need historical DeFi data, NFT ownership records, or any on-chain activity that's already being indexed by a subgraph. Part of a larger gateway offering 250+ data sources, but also available as a standalone server if you only need blockchain data access.
The Graph MCP — GraphQL queries against blockchain subgraphs.
Part of Pipeworx — an MCP gateway connecting AI agents to 1476+ live data sources.
query_subgraph(subgraph_id, query, variables?) — run an arbitrary GraphQL query.introspect_schema(subgraph_id) — fetch the subgraph schema for query construction.PLATFORM_THEGRAPH_KEY.?_apiKey=<key> after signing up at https://thegraph.com/studio/apikeys (free 100k queries/month).The legacy hosted service is gone; everything routes through the decentralized network gateway at gateway-arbitrum.network.thegraph.com.
Browse https://thegraph.com/explorer. Each subgraph's "Query URL" ends in /subgraphs/id/<the-id-you-want>.
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"the-graph": {
"url": "https://gateway.pipeworx.io/the-graph/mcp"
}
}
}
tools/list at https://gateway.pipeworx.io/the-graph/mcp returns the tools in the table
above plus the shared Pipeworx meta-tools — ask_pipeworx,
discover_tools, search_within, remember/recall and the rest of the
gateway-wide set. So the tool count you see is larger than this table: a
single-pack endpoint currently lists roughly 30 shared tools alongside the
pack's own. The connection's initialize response states its exact scope, and
is the authoritative answer for a given day.
This is deliberate, not multiplexing by accident. The meta-tools are what let a
scoped connection answer a question this pack does not cover — via
ask_pipeworx, which routes across the whole catalog — without you adding a
second MCP server. There is currently no way to mount a pack endpoint without
them; if the extra schemas cost you more context than the routing is worth,
connect to the full gateway once rather than to several pack endpoints.
Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:
{
"mcpServers": {
"pipeworx": {
"url": "https://gateway.pipeworx.io/mcp"
}
}
}
Both URLs reach the same gateway and the same 1476+ data sources. The
only difference is which pack's tools are listed directly; ask_pipeworx
reaches all of them from either one.
Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:
ask_pipeworx({ question: "your question about The Graph data" })
The gateway picks the right tool and fills the arguments automatically.
MIT