Opennodes
FreeNot checkedOpen protocol and registry for discovering, verifying and pricing AI inference endpoints. MCP server, OpenAI-compatible gateway, Ollama router, and a Node Kit f
About
Open protocol and registry for discovering, verifying and pricing AI inference endpoints. MCP server, OpenAI-compatible gateway, Ollama router, and a Node Kit for operators.
README
npm @opennodes/cli PyPI onp-node opennodes-io/opennodes MCP server License: Apache-2.0
AI inference, measured — not just claimed. OpenNodes is an open protocol (ONP) and registry for AI inference endpoints, from your own Ollama box to sovereign EU clouds. The registry checks what each endpoint really serves — which model, how much context actually works, how fast it answers, on what hardware, at what price — and your prompts go straight to the endpoint you pick: OpenNodes is never in the data path.
- Browse: registry.opennodes.io — 10,000+ offerings from about 250 providers, with trust tiers and measured results
- Learn: opennodes.io · Integrations (one-click install for Cursor and VS Code; Claude, Kiro, Open WebUI, OpenAI SDKs, agents)
- Status: ONP Draft 0.1 with errata (2026-10-23) and revisions 2 and 3 (2026-10-31, 2026-11-02; changes), a working proposal not affiliated with any standards body yet; reference stack live, with project-run reference nodes in Germany and Finland. Operators: list your endpoint or write to [email protected].
Quick start
npx @opennodes/[email protected] # OpenNodes for Ollama: one Ollama endpoint over local + LAN + verified public models
npx @opennodes/[email protected] mcp --print-config # MCP tools for Cursor / VS Code / Claude Desktop / Kiro (or use https://registry.opennodes.io/mcp)
npx @opennodes/[email protected] gateway --port 4141 # OpenAI-compatible gateway with onp/auto routing; base URL http://127.0.0.1:4141/v1
npx @opennodes/[email protected] # run your own registry: web app + API + MCP on http://127.0.0.1:4300
pipx install onp-node==0.1.9 # Node Kit: list a vLLM / Ollama / TGI deployment, or an API you already run
npm: @opennodes/core · @opennodes/cli · @opennodes/registry · @opennodes/ollama-router — PyPI: onp-node

OpenNodes for Ollama (impl/packages/ollama-router): point Open WebUI, Continue, Zed, or the ollama CLI at OLLAMA_HOST=127.0.0.1:11435 and one model list spans your local Ollama, other machines on your LAN (plain Ollama servers or Node Kit nodes you add with --peer, or Node Kit nodes found via mDNS with --mdns and pinned by card key), and verified public nodes from the registry — with auto, auto-cheap, auto-fast, auto-quality, auto-private (this machine and pinned LAN peers only), auto-eu and auto-ca or any auto-<country> (pinned LAN peers plus operators that declare that country) routed by the advisor, pinned prices, budget caps, and signed receipts for public calls.
MCP server — five read-only tools: recommend (best node and model for a task; the prompt is analysed locally and only its features are sent), search_offerings, get_offering, get_node, estimate. Listed on the MCP Registry (as io.github.opennodes-io/opennodes, stdio and remote), Glama and mcprush:
Why a protocol
MCP standardized how AI applications reach tools; the OpenAI API shape standardized how they invoke models — but nothing standardizes how a client finds an inference endpoint it doesn't already know about: what model it serves, how big it is, what hardware backs it, how well it benchmarks, what it costs per token, and whether it's up. ONP fills exactly that gap and composes the rest from existing standards: a signed Node Card at /.well-known/open-node.json, a registry API with automated verification, OpenAI-compatible invocation with pinned prices, and signed usage receipts.
Documents
Start here
- 00 — Project overview — the concept, architecture, implementation status, completed development stages, and next steps in one document.
Research (why this standard, and why now)
- 01 — Protocol & standards landscape — MCP + Registry, WebMCP, A2A, AGNTCY, ANP, NANDA, OpenAI-compatible APIs, DIDs/VCs, x402, UCAN, model cards, MLPerf; full gap analysis.
- 02 — Market landscape & demand evidence — OpenRouter, HF Inference Providers, gateways, DePIN/decentralized compute, OS-level AI runtimes, payment rails; viability assessment.
- 05 — OpenNodes and European digital sovereignty — one-page brief: no middlebox, EU-declared operator filter with a server-front check, signed self-descriptions and receipts, mapped to GDPR, the AI Act and the Data Act (web version).
- 04 — Universal AI client landscape — AI browsers, branded assistants, neutral/BYOK clients, multi-homing data, distribution economics; assessment of the "primary access point" client idea.
Specification suite
- ONP-1 — Overview, terminology, architecture, conformance
- ONP-2 — The Node Card — self-description document at
/.well-known/open-node.json - ONP-3 — Registry & Discovery API — registration, verification, search, health, ranking, federation
- ONP-4 — Invocation profiles — bindings for text, image/diffusion, embeddings, agents
- ONP-5 — Settlement — price advertisement, payment schemes (x402 / prepaid / free), signed usage receipts
- ONP-6 — Bridging — connecting discovered nodes to MCP servers, WebMCP sites, and conventional web data
- Known issues → Draft 0.2 — what external reviews raised about Draft 0.1, and what was fixed (errata 2026-10-23), planned, or not adopted
Development requirements
- REQ-001 — Discovery Service (registry) — MVP registry: registration, admission battery, search, estimation, MCP surface; acceptance criteria.
- REQ-002 — Test client — CLI + OpenAI-compatible gateway + MCP modes; compatibility matrix (Cursor, VS Code, Open WebUI…).
- REQ-003 — Node Kit — reverse-proxy wrapper turning vLLM/Ollama/TGI into a conforming node: card generation, receipts, registration, self-test.
Implementation
- schemas/open-node.schema.json — normative JSON Schema for the Node Card (Phase 0 deliverable).
- impl/ — reference stack source (registry + fixture node +
onpCLI/gateway);npm install && npm testinimpl/. - node-kit/ — Python Node Kit (REQ-003): wraps any OpenAI-compatible engine (vLLM/Ollama/TGI) into a conforming node; cross-language e2e against the JS registry.
Ecosystem
Clients and products consuming ONP — independent of the standard, listed here for discovery:
Claude Code plugin —
/plugin marketplace add opennodes-io/opennodes, then/plugin install opennodes@opennodes. Before bulk AI work it quotes the options across providers (what you use now, your own machine, checked hosts, the cheapest, an in-region one), each with a data label, and runs nothing until you choose; an agent then pilots the chosen option through the local gateway. The same behaviour for Cursor is a project rule: plugins/cursor/opennodes-quote.mdc (install line on the Integrations page).Surge (desktop client, pre-release — Windows installer; macOS and Linux build from source) — a desktop "browser for MCP" and the reference OpenNodes client: the model picker is fed live from the registry (trust tier, measured latency, price), Auto runs the advisor on your machine to pick a node per prompt, and every call is pinned to the node's card revision and comes back with a signed receipt Surge verifies. A spend policy is on from first launch, a dashboard keeps the ledger, and one click switches to private mode (local Ollama and LAN only). The first client to span both discovery layers (models via ONP, tools via MCP).

Your client here — ONP is an open standard; any client can implement discovery via ONP-3 and invocation via ONP-4. Open a PR to be listed.
Design principles
- Standardize the gap, reuse the rest. ONP defines only the Node Card, the Registry API, and thin profiles binding existing standards together. Invocation is OpenAI-compatible; payment is x402/prepaid; identity is domain-based with optional DIDs; tool access is MCP.
- Registry as a protocol, not a place. Like the MCP Registry, ONP specifies an OpenAPI interface any registry can implement. Anyone can run a registry; clients can query several; a root "meta-registry" is a bootstrap convenience, not an architectural requirement.
- Metadata is claims + attestations. Nodes self-report; registries and third-party attesters verify (liveness probes, conformance tests, benchmark attestations as Verifiable Credentials). Rank is computed by registries from declared, transparent components — ONP standardizes the signal format, not the ranking formula.
- Curated trust tiers, permissionless entry. Anyone can publish a Node Card and register (Community tier). Paid production traffic concentrates in Verified/Attested tiers — this is the lesson of Bittensor/Akash vs. OpenRouter/HF.
- The client is the orchestrator. Multi-node scenarios, MCP bridging, and WebMCP access are client-side composition over standard primitives — ONP specifies the primitives and a portable scenario format, not an orchestration runtime.
Installing Opennodes
This server has no published package — it is built from source. Open the repository and follow its README.
▸ github.com/opennodes-io/opennodesFAQ
Is Opennodes MCP free?
Yes, Opennodes MCP is free — one-click install via Unyly at no cost.
Does Opennodes need an API key?
No, Opennodes runs without API keys or environment variables.
Is Opennodes hosted or self-hosted?
Self-hosted: the server runs locally on your machine via the install command above.
How do I install Opennodes in Claude Desktop, Claude Code or Cursor?
Open Opennodes on unyly.org, pick your client tab (Claude Desktop, Claude Code, Cursor) and press Install — the config is generated automatically, no JSON editing.
Related MCPs
Opencode Omniroute Plugin
OpenCode plugin for the OmniRoute AI Gateway. Drives dynamic model discovery, /connect auth flow, and multi-instance OmniRoute providers via the official @openc
by GitHub ActionsRoblox Studio
Enables AI coding tools to control Roblox Studio for workspace exploration, instance manipulation, and script management. It provides tools for playtesting, sce
by paralovAntigravity Drawio
MCP server that enables AI assistants to create, parse, render, and validate Draw.io diagrams programmatically.
by S-SUJAN-SFetch
Web content fetching and conversion for efficient LLM usage.
AWS KB Retrieval
Retrieval from AWS Knowledge Base using Bedrock Agent Runtime.
by 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
by xuzexin-hzMCP-Agent
A simple, composable framework to build agents using Model Context Protocol by [LastMile AI](https://www.lastmileai.dev)
by lastmile-aiSpring AI MCP Client
Provides auto-configuration for MCP client functionality in Spring Boot applications.
mcp.natoma.ai
A Hosted MCP Platform to discover, install, manage and deploy MCP servers by [Natoma Labs](https://www.natoma.ai)
Compare Opennodes with
Not sure what to pick?
Find your stack in 60 seconds
Author?
Embed badge for your README
Browse similar
All ai MCPs
