Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@openrouter-mcp Ask claude-3.5-sonnet to review my Python code"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP server for consulting AI models via OpenRouter. Designed for AI assistants like Claude Code to ask other models for help.
npm install -g openrouter-mcpRelated MCP server: Senior Consult MCP
Variable | Required | Description |
| Yes | Your OpenRouter API key |
| Yes | Comma-separated list of allowed model IDs |
| No | Default system prompt for all requests |
{
"mcpServers": {
"openrouter": {
"command": "npx",
"args": ["-y", "openrouter-mcp"],
"env": {
"OPENROUTER_API_KEY": "sk-or-...",
"OPENROUTER_ALLOWED_MODELS": "anthropic/claude-3.5-sonnet,openai/gpt-4o,google/gemini-2.0-flash-001",
"OPENROUTER_SYSTEM_PROMPT": "You are helping an AI coding assistant. Be direct and provide code examples when relevant."
}
}
}
}ask_modelConsult another AI model for help with coding tasks.
Parameter | Type | Required | Description |
| string | Yes | Model ID from the allowed list |
| string | Yes | Your question or request |
| string | No | Override the default system prompt |
| string[] | No | File paths to read and include as context |
Max 10 files per request
Max 150KB per file
Text files only (no binary)
2 minute timeout per request
MIT
Consult another AI model for help with coding tasks. Use this to get a second opinion, ask for explanations, or request assistance with complex problems.
| Name | Required | Description | Default |
|---|---|---|---|
| model | Yes | The model to consult. Allowed models: gpt-4o, claude-3.5-sonnet | |
| message | Yes | Your question or request for the model | |
| system_prompt | No | Override the default system prompt | |
| append_files | Yes | File paths to read and include as context. Pass [""] if no files are relevant. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden for behavioral disclosure. It fails to mention behavioral traits such as latency, context retention, side effects, or required permissions, which are important for an AI agent to correctly invoke the tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, with the first sentence stating the purpose and the second providing usage guidance. It is front-loaded and contains no superfluous information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (4 parameters, no output schema, no nested objects), the description adequately covers purpose and usage. However, it lacks behavioral details that would help an agent understand what happens when the tool is invoked.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the baseline is 3. The description does not add significant meaning beyond the schema; it only provides high-level context about use cases. No additional parameter details are given.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool consults another AI model for coding tasks, using the specific verb 'consult' and identifying the resource as 'another AI model'. With no sibling tools provided, differentiation is not required.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly lists use cases: 'get a second opinion, ask for explanations, or request assistance with complex problems'. However, it does not provide when-not-to-use or alternatives, but the absence of sibling tools reduces the need.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
With only one tool, there is no risk of confusion between tools. The single tool is clearly distinct by default.
The tool name 'ask_model' follows a clear verb_noun convention, which is appropriate and consistent though there is only one tool.
A single tool feels thin for a server named 'openrouter-mcp', which implies broader model access capabilities. However, it may be scoped to just querying models, making it borderline acceptable.
The tool covers the core action of asking a model, but lacks supporting tools like listing available models or retrieving model metadata, which are notable gaps for a server focused on model access.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
The OpenRouter MCP server plugs OpenRouter into the AI tools you already use. Once connected, your assistant can pull live OpenRouter data (models, prices, your credits, rankings, and docs) and send quick test messages, all without leaving your editor.
OpenRouter for tools and data. Compare catalog providers and call them from one hosted MCP endpoint.
Coding agents from Claude Code, Cursor and Codex claim jobs and lock files on one shared board.
Coordination hub for AI coding agents: message teammates, ask humans, audit every event.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/minovap/openrouter-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
