MCP server for OpenRouter model discovery
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"openrouter-mcp-2","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# OpenRouter MCP Server MCP (Model Context Protocol) server for discovering and querying 300+ AI models available on OpenRouter. ## Features - **List models** — Browse all available models with pricing, context limits, and capabilities - **Search & filter** — Find models by provider, price, context length, features (tools, vision, etc.) - **Compare models** — Side-by-side comparison of multiple models - **Get details** — Full metadata for any specific model - **Cached responses** — 5-minute cache to reduce API calls ## Installation ```bash pip install openrouter-mcp ``` ## Usage ### With OpenClaw Add to your `openclaw.json`: ```json { "mcp": { "servers": { "openrouter-models": { "command": "openrouter-mcp", "env": { "OPENROUTER_API_KEY": "your-api-key" } } } } } ``` > `OPENROUTER_API_KEY` is optional but recommended for higher rate limits. ### Standalone (stdio) ```bash export OPENROUTER_API_KEY=your-key python -m openrouter_mcp.server ``` ### Available Tools | Tool | Description | |------|-------------| | `list_models` | List all models with optional modality filter and sorting | | `get_model` | Get detailed info for a specific model by ID | | `search_models` | Search and filter models by query, provider, price, context, features | | `compare_models` | Compare multiple models side by side | | `refresh_cache` | Force refresh the model cache from OpenRouter API | ## Examples ### List models sorted by context length ```json { "name": "list_models", "arguments": { "modality": "text", "sort_by": "context_length" } } ``` ### Search for Claude models under $5/1M tokens ```json { "name": "search_models", "arguments": { "query": "claude", "provider": "anthropic", "max_input_price": 5.0, "requires_tools": true } } ``` ### Compare 3 models ```json { "name": "compare_models", "arguments": { "model_ids": "anthropic/claude-sonnet-4.6,qwen/qwen3.6-plus,opena…
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.