Qsp Mcp

Name: Qsp Mcp
Author: qso-graph

by qso-graphcommunityv0.1.1

qsp-mcp relays tool calls between a local LLM and MCP servers, allowing models with function calling capability to access a wide range of tools from local weights.

From the registry: QSP — relay MCP tools to any OpenAI-compatible local LLM (llama.cpp, Ollama, vLLM)

GitHub Repository

Install & configure

Prerequisites

required
Install qsp-mcp
Python package for relaying MCP tools to local LLM endpoints
```
$ pip install qsp-mcp
```
https://pypi.org/project/qsp-mcp/
required
OpenAI-compatible LLM endpoint
A local LLM server (llama.cpp, Ollama, vLLM, etc.) running at an accessible URL
https://ollama.ai

Install in your client

Paste into the AI you're chatting with — it will figure out the rest

Please install the `qsp-mcp` MCP server into my current AI client (that's you).

Required prerequisites (do these first if not already done):
- **Install qsp-mcp** — Python package for relaying MCP tools to local LLM endpoints Run: `pip install qsp-mcp` (https://pypi.org/project/qsp-mcp/)
- **OpenAI-compatible LLM endpoint** — A local LLM server (llama.cpp, Ollama, vLLM, etc.) running at an accessible URL (https://ollama.ai)

Canonical MCP server config (stdio transport):
- command: `qsp-mcp`
- args: ["--config","~/.config/qsp-mcp/config.json"]

Note: qsp-mcp is an LLM bridge/relay tool, not a traditional MCP server for Claude. It relays MCP tool calls to a local OpenAI-compatible LLM. Configured via a JSON config file with mcpServers and bridge sections.

Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.

Note: qsp-mcp is an LLM bridge/relay tool, not a traditional MCP server for Claude. It relays MCP tool calls to a local OpenAI-compatible LLM. Configured via a JSON config file with mcpServers and bridge sections.