Which LLM providers are supported?
OpenAI (GPT models), Anthropic (Claude models), Google (Gemini models), and DeepSeek.
LLM Bridge MCP Server
@sjquant
Basic information
About LLM Bridge MCP Server
A model-agnostic Message Control Protocol (MCP) server that enables seamless integration with various Large Language Models (LLMs) like GPT, DeepSeek, Claude, and more.
LLM Bridge MCP Server config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"llm-bridge-mcp": {
"command": "npx",
"args": [
"-y",
"@smithery/cli",
"install",
"@sjquant/llm-bridge-mcp",
"--client",
"claude"
]
}
}
}LLM Bridge MCP Server tools
5The text prompt to send to the LLM
Specific model to use (default: "openai:gpt-4o-mini")
Controls randomness (0.0 to 1.0)
Maximum number of tokens to generate
Optional system prompt to guide the model's behavior
Overview
What is LLM Bridge MCP?
LLM Bridge MCP allows AI agents to interact with multiple large language models through a standardized interface. It leverages the Message Control Protocol (MCP) to provide seamless access to different LLM providers, making it easy to switch between models or use multiple models in the same application.
How to use LLM Bridge MCP?
Configure API keys in a .env file (or pass them as environment variables) and then add a server entry to your Claude Desktop or Cursor configuration. The server exposes a single tool, run_llm, which accepts a prompt, optional model name (default openai:gpt-4o-mini), temperature, max tokens, and system prompt.
Key features of LLM Bridge MCP
- Unified interface to OpenAI, Anthropic, Google, and DeepSeek models.
- Built with Pydantic AI for type safety and validation.
- Supports customizable temperature and max tokens parameters.
- Provides usage tracking and metrics.
- Simple single-tool API:
run_llm.
Use cases of LLM Bridge MCP
- Let an AI agent query multiple LLM providers from one integration.
- Switch models in a running application without reconfiguration.
- Compare outputs from GPT, Claude, Gemini, and DeepSeek in the same workflow.
- Build a multi-model assistant that can choose the best model per task.
Frequently asked questions
How do I install LLM Bridge MCP?
You can install it automatically via Smithery (`npx -y @smithery/cli install @sjquant/llm-bridge-mcp --client claude`) or manually by cloning the repository and following the manual installation steps.
How do I configure API keys?
Create a `.env` file in the root directory with keys like `OPENAI_API_KEY`, `ANTHROPIC_API_KEY`, `GOOGLE_API_KEY`, and `DEEPSEEK_API_KEY`. Alternatively, pass them as environment variables in the MCP server configuration.
How do I use LLM Bridge MCP with Claude Desktop or Cursor?
Add a server entry to your Claude Desktop configuration or `.cursor/mcp.json` file, specifying the command `uvx` and the package name `llm-bridge-mcp`, along with the required API keys.
What does the "spawn uvx ENOENT" error mean?
It means the system cannot find the `uvx` executable in your PATH. Find the full path to `uvx` using `which uvx` (macOS/Linux) or `where.exe uvx` (Windows), then update your MCP server configuration to use that full path.
More AI & Agents MCP servers
L
Legion MCP
faulkjMCP-native LLM councils for debates, juries, blind panels, voting, refinement, and custom multi-model deliberation.
1
CrawlForge MCP Server
mysleekdesigns28-tool MCP server for web scraping, crawling, deep research & autonomous extraction — clean Markdown & structured JSON for Claude, Cursor & any MCP client. 1,000 free one-time credits, local-Ollama LLM support.
2
Phi Longevity PRISM
Phi LongevityGuideline-cited lab-results analysis for people managing type 2 diabetes, kidney disease, lupus and cancer survivorship. Flags tests that are missing or overdue (ADA, KDIGO, NCCN — each cited) and returns questions to br
AskOne: Live Q&A and Polls
phurynRun free live audience Q&A and polls from your agent: start an AskOne room, add and launch a poll, approve or hide questions and mark them answered, close the room, then read the questions as a FAQ draft and get the resu
litshrine
litshrineA quiet place for agents to make wishes, light a daily lamp, and receive a reviewed oracle. Six MCP tools support registration, wishes, lighting, oracles, status, and shrine search.
Comments