thegraph-mcp: Instructions file for Claude Code

CLAUDE.md

thegraph-mcp CLAUDE.md is an instructions file for Claude Code from Data-Nexus-Web3/thegraph-mcp. It costs 484 tokens per session, scanned A, original, from a forked repository, MIT.

Project instructions for an MCP server that gives AI agents access to blockchain data indexed by The Graph. The Graph organizes blockchain data so applications can search it with GraphQL, a language for requesting specific data.

In plain words
What is it for?
Finding indexed blockchain subgraphs, inspecting their GraphQL schemas, and running GraphQL queries against them.
Why use it?
They explain how to install dependencies, run the server, and use its three data tools without having to infer the project structure.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is Data-Nexus-Web3/thegraph-mcp's own configuration. It tells Claude Code how to work on thegraph-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything thegraph-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Data-Nexus-Web3/thegraph-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Data-Nexus-Web3/thegraph-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Data-Nexus-Web3/thegraph-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for thegraph-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/data-nexus-web3/thegraph-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/data-nexus-web3/thegraph-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/data-nexus-web3/thegraph-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/data-nexus-web3/thegraph-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for thegraph-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/data-nexus-web3/thegraph-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/data-nexus-web3/thegraph-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 484 This file is loaded in full into every session.
When invoked 484 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin fork From a forked repository.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00484 $0.00484
Opus 5.5 $0.00194 $0.00194
Sonnet 5.5 $0.00097 $0.00097
Haiku 4.5 $0.00048 $0.00048

Measured 2mo ago against content hash 3b879f58c36f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

thegraph-mcp CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 39 lines

How it starts

The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

An MCP (Model Context Protocol) server that exposes The Graph's indexed blockchain data to AI agents. Built with Python's FastMCP framework, it provides three tools: searchSubgraphs (find subgraphs by name/description), getSubgraphSchema (introspect a subgraph's GraphQL schema), and querySubgraph (execute arbitrary GraphQL queries against a subgraph).

Commands

# Run the MCP server
uv run main.py

# Install/sync dependencies
uv sync

There is no test suite or linter configured.

Architecture

The entire server lives in main.py (~115 lines):

  • FastMCP server instance exposes tools via @mcp.tool() decorators
  • searchSubgraphs(searchQuery) — uses the Network Subgraph's subgraphMetadataSearch full-text search to find subgraphs by name/description. Returns a list sorted by signal (highest first) with subgraph IDs, display names, networks, signal amounts, descriptions, and full GraphQL schemas. Filters out inactive subgraphs (no current version). Schemas are included so agents can go directly from discovery to querying.
  • getSubgraphSchema(subgraphId, asText) — fetches a subgraph's schema via GraphQL introspection. When asText=True, the helper json_to_graphql_schema() converts the JSON introspection result into human-readable GraphQL SDL.
  • querySubgraph(subgraphId, query) — posts an arbitrary GraphQL query to The Graph gateway and returns the JSON response.
  • All API calls go through httpx.AsyncClient to https://gateway.thegraph.com/api/{API_KEY}/subgraphs/id/{subgraphId} with a 10-second timeout.
  • Authentication is via the THEGRAPH_API_KEY environment variable (loaded from .env by python-dotenv).

Dependencies

Managed by uv (lock file: uv.lock). Python >=3.13 required.

  • mcp[cli] — MCP server framework
  • httpx — async HTTP client
  • dotenv — .env file loading

Read the full file on GitHub · 39 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2mo ago First seen · 39 lines · 484 tokens per session scan A 3b879f58c36f

Subscribe to this mod's changes

thegraph-mcp CLAUDE.md is an instructions file published in the GitHub repository Data-Nexus-Web3/thegraph-mcp (0 stars, last pushed 9mo ago), licensed MIT. It adds 484 tokens to every session, about $0.0019 per session on Opus 5.5. A static security scan graded it A with 0 findings. It comes from a forked repository.

Related

thegraph-mcp CLAUDE.md compared with instructions from other repositories

thegraph-mcp CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
thegraph-mcp CLAUDE.mdData-Nexus-Web3/thegraph-mcpInstructions file09mo agoMITA484Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file144ktodayMITA8,130Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file150ktodayMITA4,680Codex, OpenCode
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file283ktodayMITA4,342Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA3,153GitHub Copilot