Ask
- typescript
0
GitHub Stars
typescript
Language
7 months ago
First Indexed
3 months ago
Catalog Refreshed
Documentation & install
Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.
Installation
Add the following to your MCP client configuration file.
Configuration
View docs{
"mcpServers": {
"serpepe-ask-mcp": {
"command": "ask-mcp",
"args": [],
"env": {
"OPENROUTER_API_KEY": "your-openrouter-api-key-here"
}
}
}
}Ask MCP is a server that exposes multiple AI models through the MCP protocol, letting you query powerful models from clients like Cursor or Claude Desktop. It provides flexible setup options, including local execution or OAuth-enabled access to remote services, so you can pick the workflow that fits your environment and budget while enjoying fast, reliable model responses.
How to use
You connect to the Ask MCP server from your MCP client by configuring an MCP server entry that points to the local executable or a remote endpoint. Once registered, you can issue model-specific queries through simple command-like actions in your client. Choose Grok for deep reasoning, Gemini for multimodal tasks, Kimi for quick responses, Qwen for coding-focused work, or GLM for general language tasks. If you run into quota or payment errors, you automatically fall back to free model variants, or you can explicitly request a free option using the free flag.
How to install
Prerequisites: Node.js 16+ installed on your machine. You’ll also use npm to install and run the server locally.
Option A: Install the MCP server package globally (recommended) via npm.
Run these commands one by one in your terminal.
Available tools
ask_grok
Query Grok model for advanced reasoning and analysis.
ask_gemini
Query Gemini 2.5 Pro for multimodal tasks.
ask_kimi
Query Kimi for fast, efficient responses.
ask_qwen
Query Qwen 3 Coder for coding and technical tasks.
ask_glm
Query GLM for general language tasks.