Metagraphed
БесплатноНе проверенMCP server that enables AI agents to explore Bittensor subnets, check their health and economics, and discover their public APIs and schemas.
Описание
MCP server that enables AI agents to explore Bittensor subnets, check their health and economics, and discover their public APIs and schemas.
README
Every subnet, metagraphed.
Bittensor didn't ship with a map, so we drew one. For every subnet: what does it expose (public APIs, docs, schemas), is it healthy, and how do I call it — machine-readable and agent-native from the ground up.
Website MCP MCP Registry mcp.so smithery badge npm PyPI License: AGPL-3.0 Gittensor impact
Website · API · OpenAPI · GraphQL · MCP · Agent docs · Agent workflows · Feeds · npm · PyPI
Gittensor contributor impact — refreshed weekly by .github/workflows/gittensor-impact.yml
What it is
The native Bittensor metagraph tells you what's happening at the protocol layer. Metagraphed adds the builder-facing layer it lacks: a chain-direct block explorer (its own Rust indexer, no third-party RPC dependency), a registry of every subnet's public interfaces, endpoint health, and machine-readable schemas, and an agent toolkit — 200+ MCP tools, paste-ready OpenAI/Anthropic specs, a drop-in skill — built for integration developers, often reached through their AI agents. A live read-only RPC/WSS proxy and non-custodial, wallet-signed staking/delegation round it out.
Not an official OpenTensor/Bittensor project · not a replacement for the native metagraph · not an alpha/price dashboard · not custodial — staking and delegation are wallet-signed client-side; keys and credentials never touch our backend.
The web UI lives at metagraph.sh. The API is served from https://api.metagraph.sh (REST under /api/v1, artifacts under /metagraph).
Quickstart
Three ways to use Metagraphed. Pick one.
🤖 AI agent (MCP)
Agent-native, public, read-only, Streamable-HTTP. 200+ tools to explore the chain, discover a subnet, check if it's up, read its economics and metagraph, trace what a wallet does across the network, and learn how to call it.
claude mcp add --transport http metagraphed https://api.metagraph.sh/mcp
Cursor / other clients: add an MCP server with url
https://api.metagraph.sh/mcp, transportstreamable-http.Tools:
search_subnets·list_subnets·find_subnets_by_capability·get_subnet·get_subnet_health·get_subnet_economics·get_subnet_trajectory·get_subnet_metagraph·list_subnet_validators·get_neuron·get_account·get_account_events·get_account_subnets·list_subnet_apis·get_api_schema·get_fixture·get_agent_catalog·get_best_rpc_endpoint·registry_summary·list_enrichment_targets·find_subnet_opportunities·semantic_search·ask·find_subnet_for_task·how_do_i_call·verify_integration
📦 Typed client
Generated from the OpenAPI contract, published with provenance.
npm i @jsonbored/metagraphed # JS/TS
pip install metagraphed # Python
🌐 REST
Stable JSON envelope { ok, data, meta, error }. OpenAPI at /metagraph/openapi.json.
curl https://api.metagraph.sh/api/v1/subnets
🔮 GraphQL
Shape one request across the registry — a subnet with its health, surfaces, endpoints, and economics, a provider with its subnets, or the economic opportunity boards. POST to /api/v1/graphql; GET returns the SDL and introspection is enabled.
curl -X POST https://api.metagraph.sh/api/v1/graphql \
-H 'content-type: application/json' \
-d '{"query":"{ subnet(netuid: 7) { name health { status } surfaces { kind url } economics { emission_share } } }"}'
For agents
| Resource | URL |
|---|---|
| Copyable agent prompt | /agent.md |
| Agent workflows | /agent-workflows.md |
| Machine index | /llms.txt |
| GraphQL | /api/v1/graphql — POST a shaped query (subnet + health + surfaces + endpoints + economics, provider + subnets, opportunity boards); GET returns the SDL |
| Drop-in skill | /skills/bittensor/SKILL.md — or gh skill install JSONbored/metagraphed bittensor |
| Resources index | /metagraph/agent-resources.json |
| Content feeds | /api/v1/feeds/registry — registry changes + incidents, as RSS / Atom / JSON Feed; /api/v1/feeds/gaps for ranked coverage gaps (per-subnet at /api/v1/feeds/subnets/{netuid}) |
| Embeddable badge |  — SVG (also /providers/{slug}/badge.svg); ?metric=uptime for reliability, ?metric=completeness for coverage score, plus ?style=flat-square and ?label=… |
This repo
Cloudflare Worker API + Node build scripts. Schema-first: JSON Schema is the canonical contract → OpenAPI → types/clients. Artifacts are deterministic JSON; data refreshes on a schedule to R2/KV.
docs/ product + operating notes (start here)
registry/ subnet overlays, candidates, community submissions
schemas/ canonical JSON Schema components
scripts/ validation, generation, probe, safety
workers/ Cloudflare Worker API routes
public/metagraph/ compact generated artifacts + contracts
generated/ generated TypeScript types + client
Deeper docs: docs/api-stability.md (the /api/v1 contract), docs/curation-playbook.md.
Contributing
Open the repo in a devcontainer-aware tool (VS Code, GitHub Codespaces, the devcontainer CLI) for a zero-setup environment — Node 22 + Playwright's Chromium preinstalled. Issues are labeled good first issue and help wanted — start there.
- Schema-first edits require
npm run build(regeneratesopenapi.json+ types). - Community submissions are PR-first: add a surface to exactly one
registry/subnets/<slug>.jsonfile (vianpm run surface:add; usenpm run subnet:newfirst when that subnet has no file yet), no generated artifacts.
See CONTRIBUTING.md and docs/curation-playbook.md. Gittensor contributor impact is pinned at the top of this README.
Subnet catalog
128 curated subnets — 117 with a site, 46 with docs, 117 with a public repo. Live health, search, and the full list (every active subnet, not just the curated ones) at metagraph.sh; per-subnet JSON at https://api.metagraph.sh/api/v1/subnets/{netuid}. Root (SN0) is base-layer chain infrastructure, listed separately below, not counted as a subnet.
Focus areas: compute 9 · data 7 · defi 7 · inference 5 · language-models 4 · prediction-markets 4 · computer-vision 3 · finance 3 · dashboard 2 · data-artifact 2 · decentralized-training 2 · depin 2
- root
SN0—chain-rpc· site · docs · repo - Apex
SN1· site · docs · repo - DSperse
SN2—verifiable-oracleszkml· site · docs · repo - Templar
SN3—decentralized-trainingtournament· site · docs · repo - Targon
SN4· site · docs · repo - Hone
SN5· site · repo - Numinous
SN6—forecastingopenapisubnet-api· site · docs · repo - Allways
SN7—bitcoindefisubnet-api· site · docs · repo - Vanta
SN8· site · repo - iota
SN9· site · repo - Swap
SN10· site · docs · repo - TrajectoryRL
SN11· site · docs · repo - Compute Horde
SN12—computedashboard· site · repo - Data Universe
SN13—datamcp· site · docs · repo - Cacheon
SN14—inference· site · docs · repo - ORO
SN15· site · docs · repo - BitAds
SN16· repo - 404—GEN
SN17—3d-generation· site · repo - Zeus
SN18—weather-forecasting· site · docs · repo - blockmachine
SN19· site · docs · repo - GroundLayer
SN20—capital-markets· site - AdTAO
SN21—advertising· site · repo - Desearch
SN22—searchsocial-data· site · docs · repo - Trishool
SN23—subnet-api-observed· site · repo - Quasar
SN24—language-modelsmodel-artifacts· site · docs · repo - Mainframe
SN25—compute· site · repo - Perturb
SN26—adversarial-robustnesscomputer-vision· site · docs · repo - NI Compute
SN27—computedashboard - gm
SN28—llm-inferencemarketplacetee· site · repo - Coldint
SN29—datadistributed-training· site · docs · repo - Endure Network
SN30—defirisk-intelligence· site · docs - Recall
SN31—ragretrieval - ItsAI
SN32· site · repo - ReadyAI
SN33—conversation-datadata· site · docs · repo - BitMind
SN34—deepfake-detection· site · docs · repo - OxMarkets
SN35—defi· site · repo - Eirel
SN36—llm-evaluation· site · repo - Aurelius
SN37—alignment· site · repo - ChronoLLM
SN38—language-models· site · docs · repo - Basilica
SN39—compute· site · repo - Ralph
SN40—distributed-traininglanguage-models· site · docs · repo - Almanac
SN41—prediction-markets· site · repo - Gopher
SN42—datatee· site · docs · repo - Graphite
SN43—optimizationresearch· site · repo - Score
SN44—computer-vision· site · repo - AlphaRidge.ai
SN45—market-intelligencesentiment-analysis· site · repo - Zipcode
SN46—real-estate· site · repo - EvolAI
SN47—data· site · repo - Quantum Compute
SN48—computequantum· site · repo - Nepher Robotics
SN49—roboticstournament· site · docs · repo - Synth
SN50—finance· site · repo - lium.io
SN51—compute· site · repo - Dojo
SN52—tensorplex· site · docs · repo - EfficientFrontier
SN53—defifinancial-tradingtrading-strategies· site · repo - Yanez MIID
SN54—compliancesynthetic-data· site · repo - NIOME
SN55—genomicssynthetic-data· site · repo - Gradients
SN56—ai-trainingoperational-interface· site · docs · repo - Sparket
SN57—prediction-marketssports· site · repo - Handshake58
SN58—ai-marketplacepayments· site · docs · repo - Babelbit
SN59—language· site · repo - Bitsec
SN60—security· site · repo - RedTeam
SN61—cybersecurity· site · docs · repo - Ridges
SN62—agents· site · repo - Enigma
SN63—quantum· site · repo - Chutes
SN64—computeinference· site · docs · repo - TAO Private Network
SN65—networking· site · repo - ninja
SN66—software-engineeringworkflow· site · docs · repo - Harnyx
SN67· site · repo - NOVA
SN68· site · repo - ain
SN69· site · repo - NexisGen
SN70· site · repo - Leadpoet
SN71· site · repo - StreetVision by NATIX
SN72—computer-visiondatadepin· site · docs · repo - MetaHash
SN73—defiotctreasury - Gittensor
SN74—developer-toolsrepositories· site · docs · repo - Hippius
SN75—depinstorage· site · docs · repo - Byzantium
SN76· site · repo - Liquidity
SN77—defi· site · repo - Vocence
SN78· site · repo - MVTRX
SN79· site · docs · repo - dogelayer
SN80· repo - Grail
SN81—decentralized-training· docs · repo - Compelle
SN82· site · repo - CliqueAI
SN83· site · repo - ansuz
SN84—chip-designhardware· site · docs · repo - Vidaio
SN85· site · repo - Subnet 86
SN86 - Luminar Network
SN87—video-intelligencevision· site · docs · repo - Investing
SN88—data-artifactfinance· site · repo - InfiniteHash
SN89· site · docs · repo - DegenBrain
SN90—prediction-marketsverification· site - Bitstarter #1
SN91· site · repo - Tensorclaw
SN92—inferencestale-source-restored· site · repo - Bitcast
SN93· site · repo - Bitsota
SN94· site · repo - Actual
SN95—inferencemodel-registry· site - Verathos
SN96—inferencelanguage-models· site · docs · repo - Albedo
SN97· site · repo - ForeverMoney
SN98—finance· site · repo - Leoma
SN99· site · repo - Plaτform
SN100—ai-research· site · docs · repo - eni
SN101· site · repo - ConnitoAI
SN102· site · repo - Djinn
SN103· site · repo - for sale (burn to uid1)
SN104—no-public-project-surface - Beam
SN105· site · repo - Nodexo
SN106—computegpu· site · docs · repo - Minos
SN107· site · repo - TalkHead
SN108· site · repo - Academia
SN109—data-artifact· repo - Green Compute
SN110—model-directory· site · docs · repo - oneoneone
SN111—dataugc· site · repo - minotaur
SN112· site · repo - TensorUSD
SN113—stablecoin· site · docs · repo - SOMA
SN114—mcp· site · repo - HashiChain
SN115· repo - TaoLend
SN116—defilending· site - Glyph
SN117· site · repo - Ditto
SN118—agent-memory· site · docs · repo - Satori
SN119—virtual-world - Affine
SN120· site · repo - sundae_bar
SN121· site · repo - Bitrecs
SN122—recommendations· site · docs · repo - MANTIS
SN123—sdk· site · repo - Swarm
SN124—robotics· site · repo - 8 Ball
SN125—prediction-markets· site · docs · repo - Poker44
SN126—security· site · repo - Astrid
SN127—trading-strategies· site · repo - ByteLeap
SN128—compute· site · repo
Auto-generated from the curated overlays in registry/subnets/ by scripts/generate-registry-readme-section.ts — enrich a subnet (one PR) and it appears here. Not the live list; browse + monitor everything at metagraph.sh.
Related
- Frontend — apps/ui/ in this repo (folded in from the standalone
metagraphed-uirepo via monorepo consolidation): the web app at metagraph.sh — block explorer, subnet directory, and a non-custodial staking/delegation flow (/delegate). Vite + React 19 + TanStack Start, deployed as its own independent Cloudflare Worker. Holds no subnet data — it renders what this backend serves.
License
The backend (Cloudflare Worker + build pipeline) is AGPL-3.0. The published client SDKs are permissively licensed so you can embed them freely — packages/client (npm) and python/ (PyPI) are Apache-2.0.
© 2026 JSONbored
Установка Metagraphed
У этого сервера нет опубликованного пакета — он собирается из исходников. Открой репозиторий и следуй инструкции в README.
▸ github.com/JSONbored/metagraphedFAQ
Metagraphed MCP бесплатный?
Да, Metagraphed MCP бесплатный — установка в пару кликов через Unyly без оплаты.
Нужен ли API-ключ для Metagraphed?
Нет, Metagraphed работает без API-ключей и переменных окружения.
Metagraphed — hosted или self-hosted?
Доступен hosted-вариант: Unyly запускает сервер в облаке, локальная установка не обязательна.
Как установить Metagraphed в Claude Desktop, Claude Code или Cursor?
Открой Metagraphed на unyly.org, выбери вкладку своего клиента (Claude Desktop, Claude Code, Cursor) и нажми Install — конфиг сгенерируется автоматически, без правки JSON.
Похожие MCP
Fetch
Web content fetching and conversion for efficient LLM usage.
AWS KB Retrieval
Retrieval from AWS Knowledge Base using Bedrock Agent Runtime.
автор: modelcontextprotocolSpring AI MCP Server
Provides auto-configuration for setting up an MCP server in Spring Boot applications.
llm-analysis-assistant
A very streamlined mcp client that supports calling and monitoring stdio/sse/streamableHttp, and can also view request responses through the /logs page. It also
автор: xuzexin-hzCompare Metagraphed with
Не уверен что выбрать?
Найди свой стек за 60 секунд
Автор?
Embed-бейдж для README
Похожее
Все в категории ai

