About OpenNodes
OpenNodes is a client toolkit for the OpenNodes Protocol, used to discover AI inference nodes, estimate call costs, and invoke models. It offers an MCP server, CLI, and local OpenAI-compatible gateway, with signed receipts for calls.
Key features
- 01Search and filter inference nodes and models
- 02Recommend nodes and models for a task
- 03Pre-price multi-step call chains
- 04Invoke at pinned prices with signed receipts
- 05Provide a local OpenAI-compatible gateway
- 06Route by ranking with node failover
Use cases
- 01Find inference providers for a specific task
- 02Estimate multi-step request costs before invocation
- 03Connect existing OpenAI SDK apps to node routing
- 04Review node operators, tier history, and availability
MCP support
OpenNodes provides a stdio MCP server for recommending nodes and models, searching and retrieving offerings, inspecting node details, and estimating costs. The recommendation tool sends extracted features only; the prompt itself stays on the local machine.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://registry.opennodes.io/mcpclaude mcp add --transport http opennodes-io-opennodes https://registry.opennodes.io/mcp{"mcpServers":{"opennodes-io-opennodes":{"type":"http","url":"https://registry.opennodes.io/mcp"}}}Open in Cursor{"servers":{"opennodes-io-opennodes":{"type":"http","url":"https://registry.opennodes.io/mcp"}}}Open in VS Code{"mcpServers":{"opennodes-io-opennodes":{"type":"http","url":"https://registry.opennodes.io/mcp"}}}{"mcpServers":{"opennodes-io-opennodes":{"serverUrl":"https://registry.opennodes.io/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
4| Parameter | Type | Required | Description |
|---|---|---|---|
| task | string | Yes | |
| policy | object | No | |
| est_output_tokens | number | No |
Details
From the project README@opennodes/cli
The OpenNodes Protocol (ONP) client: discover verified AI inference nodes, pre-price multi-step chains with enforceable estimates, invoke with pinned prices and signed receipts — and bring all of it into the tools you already use.
onp mcp— a stdio MCP server for Cursor, VS Code, Claude Desktop and any MCP host. Tools:recommend(best node + model for a task, priced and explained; the prompt never leaves your machine — only extracted features are sent),search_offerings,get_offering,get_node(vet a provider: operator, tier history, availability),estimate.onp gateway— a local OpenAI-compatible server over discovered nodes. Point any OpenAI-SDK app at it. Virtual modelsonp/auto,onp/auto-cheap,onp/auto-fast,onp/auto-quality,onp/auto-private,onp/auto-eu(EU/EEA operators only),onp/auto-caor anyonp/auto-<country>route each request by the advisor; aliases and query-defined virtual models are supported; every call is receipted. Failover: auto models try up to 5 ranked nodes in turn; a node that hasn't started answering within a budget built from its measured latency and the request size (15 s – 3 min) is skipped; and an OpenRouter-stylemodels: ["a", "b"]list in the request adds further models to try, in order (it is never forwarded to nodes). Auto-routing only picks what you can actually call: free registered nodes, plus the listings of any host you hold a key for — passed with--key host=KEYor picked up fromOPENROUTER_API_KEY,HF_TOKEN,OPENAI_API_KEY,MISTRAL_API_KEY,GROQ_API_KEY,TOGETHER_API_KEY,DEEPINFRA_API_KEY,FIREWORKS_API_KEY(each key is sent only to its own host;--no-env-keysturns detection off).onp search | estimate | invoke | card— the CLI.
npx @opennodes/cli mcp --print-config # paste into your MCP host's config
npx @opennodes/cli gateway --port 4141 # then set OPENAI_BASE_URL=http://127.0.0.1:4141/v1
npx @opennodes/cli search --modality text --tier verified --sort tps
Registry: ONP_REGISTRY — defaults to the hosted registry at https://registry.opennodes.io (9,000+ offerings); set it to http://127.0.0.1:4300 to use your own (npx @opennodes/registry).
Part of OpenNodes · specification · Apache-2.0.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.