MCP SERVERSend a completion to any model on OpenRouter, after picking that model by price, context length or capability rather than by memory.
LABSCO SUMMARY
search_models filters the registry by price ceiling, context length and capability, so the cheapest model meeting a hard requirement is one call rather than a browse through a pricing page. Completions then go wherever you picked, with provider routing and parameter overrides supplied per request. Four tools, and none of them a framework: this routes, it does not orchestrate.
Four tools over OpenRouter.ai: one sends messages to a named model, three answer questions about the registry — search it, describe one model, or check that an ID is valid.
An OpenRouter account and OPENROUTER_API_KEY. Four further environment variables hold defaults the calls fall back to: OPENROUTER_DEFAULT_MODEL, OPENROUTER_MAX_TOKENS, OPENROUTER_PROVIDER_QUANTIZATIONS and OPENROUTER_PROVIDER_IGNORE.
One command plus a key — pnpm install @mcpservers/openrouterai, then supply credentials
USE CASES
Filter the registry by prompt and completion price ceilings plus a minimum context length, then read the full metadata of the one that survives.
Hand the conversation to a model chosen for this call, with its own temperature, token cap and provider routing, and keep the rest of the session where it is.
A boolean answer on whether the ID exists, which is cheaper than discovering it does not in the middle of a chain.
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
chat_completionSends conversational context (messages) to OpenRouter.ai for completion using a specified model. Use this for dialogue, text generation, or instruction-following tasks. Supports advanced provider routing and parameter overrides. Returns the generated text response.
get_model_infoRetrieves the complete metadata for a single OpenRouter.ai model specified by its unique ID. Use this when you know the model ID and need its full details (pricing, context limits, capabilities, etc.). Returns a model information object.
search_modelsQueries the OpenRouter.ai model registry, filtering by various criteria like capabilities, pricing, or provider. Use this to discover models suitable for specific needs. Returns a list of matching model metadata objects.
validate_modelVerifies if a given model ID exists within the OpenRouter.ai registry. Use this for a quick check of model ID validity before making other API calls. Returns a boolean value (true if valid, false otherwise).
BEFORE YOU INSTALL
4 tools when we connected.
Both documented clients run the server on your machine.
CONTEXT COST
Rated by the size of the 4 tool definitions that ride along on every turn, not by how many there are
INSTALLATION
pnpm install @mcpservers/openrouterai{
"mcpServers": {
"openrouterai": {
"command": "npx",
"args": [
"@mcpservers/openrouterai"
],
"env": {
"OPENROUTER_API_KEY": "<YOUR_OPENROUTER_API_KEY>"
}
}
}
}OPENROUTER_DEFAULT_MODEL, OPENROUTER_MAX_TOKENS, OPENROUTER_PROVIDER_QUANTIZATIONS and OPENROUTER_PROVIDER_IGNORE are optional defaults — add them to env only if you want them. With no model named anywhere, calls use openrouter/auto.
MCP servers
YuChenSSR
klitchevo
mzxrai
aliargun