OpenNodes

Official

by opennodes-io · JavaScript

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

MCP Server: io.github.opennodes-io/opennodes

The MCP server provides access to “verified AI inference nodes.” It focuses on helping users find the best node plus model combination for a given task, and it supports “pre-price chains” for node/model selection. The catalog details are derived from the server’s name and description.

🛠️ Key Features

Verified AI inference nodes
Best node+model per task selection
Pre-price chains

🚀 Use Cases

Selecting an AI inference node and model for a specific task
Evaluating or planning inference runs using pre-priced chain information

⚡ Developer Benefits

Programmatic discovery of verified inference nodes
Easier mapping of tasks to a node+model pairing

⚠️ Limitations

No additional fields (e.g., topics, toolCount, or readmeExcerpt) were provided to describe more capabilities or constraints.

Topics

ai-agentsai-inferenceinference-apillmllm-gatewayllm-routerlocal-llmmcpmcp-servermodel-context-protocolmodel-registryollamaopen-protocolopenai-compatibleself-hosted

impl/packages/cli/README.md2 KBView on GitHub

@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 models onp/auto, onp/auto-cheap, onp/auto-fast, onp/auto-quality, onp/auto-private route each request by the advisor; aliases and query-defined virtual models are supported; every call is receipted.
onp search | estimate | invoke | card — the CLI.

bash

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.

Install

Configuration

Environment variables

ONP_REGISTRY

Registry base URL. Defaults to https://registry.opennodes.io; set http://127.0.0.1:4300 for a local registry.

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "opennodes": {
      "command": "npx",
      "args": [
        "-y",
        "@opennodes/cli@0.1.6",
        "mcp"
      ],
      "env": {
        "ONP_REGISTRY": "<YOUR_ONP_REGISTRY>"
      }
    }
  }
}