# Openrouter — MCP server on mcp.ai
> Connect your Openrouter account and use 13 tools for artificial intelligence straight from your AI agent. Connect with your own API key. OpenRouter is a platform that provides a unified API for accessing various large language models (LLMs) from different providers, allowing developers to integrate multiple AI models seamlessly.

By: mcp.ai · official
Page: https://mcp.ai/openrouter

## Connect (MCP protocol)
Remote MCP endpoint (HTTP, streamable): https://api.mcp.ai/p_openrouter?ms=1787293560000
Add it as a custom/remote MCP connector, then authenticate when prompted.

## REST API (no MCP client required)
Every tool is also a REST endpoint, authed with a workspace API key.
Discover: GET https://api.mcp.ai/api/openrouter/_endpoints   # public; lists every endpoint
Call:     POST https://api.mcp.ai/api/openrouter/<endpoint>
  Authorization: Bearer sk_live_…   # create one at https://mcp.ai/settings/api-keys
  Content-Type: application/json
  Body: { …args }   →   { "ok": true, "tool": "<id>", "result": { … } }

## Developer docs
How to use (MCP or REST), markdown: https://mcp.ai/openrouter/skill.md
Postman collection (v2.1): https://mcp.ai/openrouter/postman.json

## Tools
- openrouter_create_chat_completion(n?: integer, stop?: string|string[], user?: string, model: string, top_p?: number, stream?: boolean, messages: object[], functions?: object[], logit_bias?: object, max_tokens?: integer, temperature?: number, function_call?: string|object, presence_penalty?: number, frequency_penalty?: number) — Tool to generate a chat-style completion. Use after assembling messages and selecting a model. Supports streaming and function calls. Response format varies across models; use explicit prompt instruct
- openrouter_create_coinbase_charge(amount: number, sender: string, X_Title?: string, chain_id: integer, HTTP_Referer?: string) — Tool to create a Coinbase charge for crypto payment to add credits to your OpenRouter account. Use when you need to purchase credits using cryptocurrency. Returns calldata needed to fulfill the transa
- openrouter_create_message(user?: string, model: string, tools?: object[], top_k?: integer, top_p?: number, models?: string[], stream?: boolean, system?: string|object[], plugins?: object[], x_title?: string, messages: object[], metadata?: object, provider?: object, thinking?: object, max_tokens: integer, session_id?: string, temperature?: number, tool_choice?: object, http_referer?: string, service_tier?: string, output_config?: object, stop_sequences?: string[]) — Tool to create a message using Anthropic Messages API format via OpenRouter. Use when you need Claude-compatible chat completion with support for text, images, PDFs, tools, and extended thinking.
- openrouter_get_credits() — Tool to get the current API credit balance for the authenticated user. Use before large or batch jobs to verify sufficient balance. A successful response may return total_credits=0, which confirms aut
- openrouter_get_current_key(x_title?: string, http_referer?: string) — Tool to get information about the currently authenticated API key. Use to check usage limits, spending, and key metadata.
- openrouter_get_generation(id: string) — Tool to retrieve a generation result by its unique ID. Use after a generation completes to fetch metadata like token counts, cost, and latency.
- openrouter_get_models_count(x_title?: string, http_referer?: string) — Tool to get the total count of available models on OpenRouter. Use when you need to know how many models are available without fetching the full list.
- openrouter_list_available_models(use_rss?: boolean, category?: string, use_rss_chat_links?: boolean) — Tool to list available models via OpenRouter API. Use after confirming authentication to fetch the model catalog. Use exact model IDs returned here in OPENROUTER_CREATE_CHAT_COMPLETION or OPENROUTER_C
- openrouter_list_embedding_models(X-Title?: string, HTTP-Referer?: string) — Tool to list all available embeddings models via OpenRouter API. Returns a list of embeddings models with their properties including architecture, pricing, and capabilities.
- openrouter_list_model_endpoints(slug: string, author: string) — Tool to list endpoints for a specific model. Use after specifying model author and slug to get endpoint details including pricing, context length, and supported parameters. Some metadata fields (e.g.,
- openrouter_list_providers() — Tool to list all AI model providers available through the OpenRouter API. Use after authentication to retrieve available provider options for routing configuration. Providers differ in latency, contex
- openrouter_list_user_models(x_title?: string, http_referer?: string) — Tool to list models filtered by user provider preferences, privacy settings, and guardrails. Use after authenticating to get models tailored to the user's configuration.
- openrouter_list_zdr_endpoints(x_title?: string, http_referer?: string) — Tool to preview the impact of Zero Data Retention (ZDR) on the available endpoints. Use to see which model endpoints remain accessible when ZDR is enabled.

## Example prompts
- "What can I do in Openrouter?"
- "Show me a summary of my Openrouter account"

## Links
Docs: https://mcp.ai/docs/mcps/openrouter
Website: https://mcp.ai/mcps/openrouter