Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/data-nexus-web3/thegraph-mcp/claude-mdgit clone --depth 1 https://github.com/Data-Nexus-Web3/thegraph-mcpWrote 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.
[](https://agentmods.dev/instructions/data-nexus-web3/thegraph-mcp/claude-md)<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="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00484 | $0.00484 |
| Opus 5 | $0.00242 | $0.00242 |
| Sonnet 5 | $0.00097 | $0.00097 |
| Haiku 4.5 | $0.00048 | $0.00048 |
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 5d 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.
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'ssubgraphMetadataSearchfull-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. WhenasText=True, the helperjson_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.AsyncClienttohttps://gateway.thegraph.com/api/{API_KEY}/subgraphs/id/{subgraphId}with a 10-second timeout. - Authentication is via the
THEGRAPH_API_KEYenvironment variable (loaded from.envby python-dotenv).
Dependencies
Managed by uv (lock file: uv.lock). Python >=3.13 required.
mcp[cli]— MCP server frameworkhttpx— async HTTP clientdotenv— .env file loading
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.
- 5d ago First seen · 39 lines · 484 tokens per session scan A 3b879f58c36f
thegraph-mcp CLAUDE.md is an instructions file published in the GitHub repository Data-Nexus-Web3/thegraph-mcp (0 stars, last pushed 6mo ago), licensed MIT. It adds 484 tokens to every session, about $0.0024 per session on Opus 5. A static security scan graded it A with 0 findings. It comes from a forked repository.
Other instructions, from other repositories
evmole AGENTS.md
Instructions for cdump/evmole: EVMole extracts structured facts from deployed EVM runtime bytecode.
experiencer CLAUDE.md
Claude Code instructions for vincentlaucsb/experiencer: The canonical repository instructions are in AGENTS.md. Read and follow that file; this compatibility entrypoint intentionally defines no independent rules.
plamen CLAUDE.md
Claude Code instructions for PlamenTSV/plamen, covering plamen — security auditor, execution model, reference files and shared.
pip-web CLAUDE.md
Claude Code instructions for playpip/pip-web, covering claude.md — agent guide for pip, read first (by task), the three layers (respect the boundaries), non-negotiables and commands / definition of done.
bitcoin-mcp copilot-instructions.md
Instructions for Bortlesboat/bitcoin-mcp, covering bitcoin-mcp copilot instructions, rules, satoshi api reference and verification.
kya-hub AGENTS.md
AGENTS.md instructions for UMBRAXON/kya-hub, covering agents.md — instructions for ai agents, 1. what kya-hub is, in one paragraph, 2. should you integrate?, 3. quickstart for an llm agent and 4. signing rules — the part that breaks everyone.