Subgraph Registry

Agent-friendly semantic classification of all subgraphs on The Graph Network.

Pre-computed index of 15,330 subgraphs with domain classification, protocol type detection, schema fingerprinting, canonical entity mapping, and composite reliability scoring.

What's new in 0.8.0 — three agent-discovery upgrades:

• Semantic search via 384-dim embeddings (semantic_search_subgraphs)
• Schema evolution tracking with stability days surfaced on every result (get_schema_changes)
• OpenAPI 3.1 spec auto-generated for MCP tools + REST routes, served at /.well-known/openapi.json

The Problem

Agents querying The Graph need to discover and select the right subgraph before they can query data. Today this requires 3-4 tool calls (search, check volumes, fetch schema, infer structure) before any real work happens. This registry flips that: agents start with structured knowledge, not a blank slate.

What It Does

1. Crawls all active subgraphs from the Graph Network meta-subgraph
2. Fetches the GraphQL schema for every deployment
3. Extracts contract addresses from each manifest's dataSources and templates — agents can answer "which subgraph indexes contract 0x… on chain X?"
4. Generates a per-subgraph starter GraphQL query from the parsed schema (real top entity, real fields, sensible orderBy) — no more generic boilerplate that doesn't compile against most subgraphs
5. Classifies each subgraph by domain, protocol type, canonical entities, and schema family
6. Scores reliability using on-chain signals (query fees, volume, curation, stake)
7. Returns x402 + legacy query URLs — agents can pay $0.01 USDC on Base per query (no API key) or use a Studio key
8. Publishes as SQLite database + REST API + MCP server + per-subgraph JSON-LD at /.well-known/subgraph/{id}.jsonld for ecosystem crawlers
9. Generates visual dashboards and bot-readable category files (auto-updated with each sync)

Querying with x402 (no API key)

Every result includes query_url_x402 alongside the legacy query_url. The Graph's public x402 gateway (live since 2026-05-08) accepts $0.01 USDC on Base per query with zero signup.

// An x402-native agent — discovery to data in two calls
const { recommendations } = await mcp.call("recommend_subgraph", {
  goal: "find DEX trades on Arbitrum",
});
const top = recommendations[0];

// POST your GraphQL query. The first call returns HTTP 402 with a
// base64 `payment-required` header; the x402 client signs the
// EIP-3009 USDC transfer on Base and retries automatically.
const data = await x402Fetch(top.query_url_x402, {
  method: "POST",
  body: JSON.stringify({ query: "{ swaps(first: 5) { id amountUSD } }" }),
});

Pricing manifest returned per subgraph:

{
  "amount_usd": 0.01,
  "asset": "USDC",
  "asset_contract": "0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913",
  "chain": "base",
  "network": "eip155:8453",
  "pay_to": "0x79DC34E41B2b591078d3dE222C43EcaaBD52FcCB",
  "scheme": "exact",
  "asset_transfer_method": "eip3009"
}

Client libraries: @graphprotocol/client-x402, x402-fetch, or any generic x402 wrapper.

Registry at a Glance

Charts auto-generated from registry.db on each sync. See python/generate_docs.py.

Browse by Category

Domains

Explore subgraphs by use case — each file lists the top 25 subgraphs ranked by reliability score.

Full index: docs/DOMAINS.md

Networks

Explore subgraphs by blockchain — each file lists the top 25 subgraphs on that chain.

Full index: docs/NETWORKS.md

Protocol Types

Reliability Score

Each subgraph gets a composite reliability score (0-1) based on four on-chain signals:

All values are log-scaled and capped at 1.0. A 0.5 penalty is applied if the subgraph has been denied/deprecated.

Score tiers: High (0.7+) = strong signal, real usage | Medium (0.3-0.7) = functional, some activity | Low (<0.3) = minimal signal or test deployment

The score measures traction, so it measures age

All four inputs are cumulative — fees and curation accrue, volume needs 30 days to exist at all. A subgraph deployed last month therefore scores near zero no matter how good it is. Measured on the current corpus (served, non-denied):

The newest subgraph anywhere in the registry's top 25 is 280 days old — yet 59 of those 64 sub-30-day subgraphs are already serving real query volume.

Rather than reweight the score and trade a measurable signal for a guess, search_subgraphs returns young matches in a separate emerging list alongside an emerging_caveat explaining that a low score at that age is expected rather than damning. Every result also carries age_days and maturity (new < 30d, emerging < 90d, established). This matters most for new chains and new protocols, where no mature deployment can exist — searching "perpetual futures" surfaces years-old Ethereum and BSC deployments in the main list and the 40-day-old Monad perps subgraph under emerging.

semantic_search_subgraphs ranks by cosine similarity rather than reliability, so it is already age-neutral — it carries the maturity labels but no emerging list, because a three-week-old subgraph can top it on merit.

Ranking

Three tools rank, and each ranks differently on purpose:

• search_subgraphs — orders by how many of your query terms matched, then by reliability. OR-ing the terms and ordering on reliability alone meant a popular subgraph matching one incidental word beat a precise match on all three, so being more specific returned worse answers. Version tokens (v2, v3, v4) are kept rather than dropped as too short.
• semantic_search_subgraphs — orders by semantic_score × (0.5 + 0.5 × reliability). Pure cosine put testnets first, since their text is nearly identical to mainnet's. The 0.5 floor keeps new subgraphs competitive.
• recommend_subgraph — infers domain and protocol type from the goal, but as a ranking bonus, never a filter. As a filter, one bad keyword collapsed the candidate pool to nothing.

A term matching a subgraph's name counts for more than one matching its description — %ens% also matches "tokens", so equal weighting handed a search for ens to four Uniswap subgraphs.

Chain names are aliased, so ethereum, arbitrum, polygon and bnb resolve to the corpus values mainnet, arbitrum-one, matic and bsc.

Testnets