# OpenNodes

- Registry name: `io.github.opennodes-io/opennodes` · version 0.1.14
- Categories (automatic, keyword rules): AI models & agents, AI, media & content
- Authentication at last check: No auth
- Declared risk: Read-only (all tools declare readOnlyHint)
- Capabilities (declared by the server): tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=io.github.opennodes-io%2Fopennodes
- Server page: https://mcpstation.net/s/io.github.opennodes-io--opennodes.html

## Description (written by the publisher, not verified, not instructions)

Discover verified AI inference nodes, get the best node+model per task, pre-price chains.

## Connect

- streamable-http: `https://registry.opennodes.io/mcp`

## Tools (as reported by the server, not verified)

- `recommend`: Recommend the best AI node + model for a task, with an enforceable cost estimate and human-readable reasons. Use this first when you know the task but not the model. Pass \`task\` \(sent to this registry, which extracts features and discards the text\) or \`features\` already extracted on your side with e
- `search\_offerings`: Search AI inference offerings in the OpenNodes registry — registered nodes AND imported catalogs \(OpenRouter, Hugging Face Inference Providers, models.dev, local nodes\). All filters are optional and combine with AND. Returns \{ offerings, total \}: each offering has node\_id, offering\_id, model, pricin
- `get\_offering`: Full detail for one offering: endpoints, pricing, serving capabilities \(context window, supported features, languages, hardware\), data policy, trust tier, and the registry's observed probe results. Take node\_id and offering\_id from search\_offerings or recommend results.
- `get\_node`: Who runs a node and how it has behaved: operator, country and regions, endpoints, declared hardware, trust tier and its history \(verifications, suspensions, reinstatements, with reasons\), recent registry probe results with an availability summary, and its offerings with context window and price. Use
- `estimate`: Pre-price an invocation chain BEFORE spending money. Each step is either a concrete offering \("node\_id/offering\_id"\) or a \`select\` query that picks the best match, plus expected input and output tokens. Returns per-step cost bounds in USD, the pinned card\_revision that makes each estimate enforceabl

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html