AI Plugin Index
Ollama / vLLM Bridge
CommunityMCP server by setheerwagen · updated · ★ 0
Call your local Ollama or vLLM model over MCP with schema-validated JSON output Ollama / vLLM Bridge is a community project by setheerwagen, not verified by a company domain.
Install Ollama / vLLM Bridge
Built from the published package, never by AIclaude mcp add ollama-vllm-bridge -- uvx mcp-ollama-vllmRun in your terminal. Add --scope user to use it in every project.
{
"mcpServers": {
"ollama-vllm-bridge": {
"command": "uvx",
"args": [
"mcp-ollama-vllm"
]
}
}
}Settings, Developer, Edit config. Paste into claude_desktop_config.json and restart.
Step-by-step: install Ollama / vLLM Bridge in Claude Desktop
{
"mcpServers": {
"ollama-vllm-bridge": {
"command": "uvx",
"args": [
"mcp-ollama-vllm"
]
}
}
}Add to ~/.cursor/mcp.json (all projects) or .cursor/mcp.json (this project).
{
"servers": {
"ollama-vllm-bridge": {
"command": "uvx",
"args": [
"mcp-ollama-vllm"
]
}
}
}Add to .vscode/mcp.json. VS Code uses "servers", not "mcpServers".
codex mcp add ollama-vllm-bridge -- uvx mcp-ollama-vllm{
"mcpServers": {
"ollama-vllm-bridge": {
"command": "uvx",
"args": [
"mcp-ollama-vllm"
]
}
}
}Add to ~/.gemini/config/mcp_config.json (all projects) or .agents/mcp_config.json (this project).
Step-by-step: install Ollama / vLLM Bridge in Antigravity CLI
gemini mcp add ollama-vllm-bridge uvx mcp-ollama-vllmGemini CLI was replaced by Antigravity CLI in June 2026 and remains only for enterprise licences and paid API keys.
MCP servers run with your permissions and can read what you give them access to. Some need an API key: check the README and add it under env in the ollama-vllm-bridge block.
Last commit 10 days ago
MIT: permissive, fine for commercial use
Clear description, published package or server URL, original repository
Not checked yet. What we check
What you need
| Setting | Needed | What it is |
|---|---|---|
LOCAL_Environment variable | Optional | Backend to use: ollama, vllm or openai Default: ollama |
LOCAL_Environment variable | Optional | Model endpoint URL; must be local or on your own network. Required for the openai backend |
LOCAL_Environment variable, secret | Optional | Optional bearer token, openai backend only; sent as a header, never logged |
LOCAL_Environment variable | Optional | Read timeout in seconds Default: 600 |
LOCAL_Environment variable | Optional | Default embedding model Default: nomic-embed-text |
LOCAL_Environment variable | Optional | Optional, openai backend only: embedding endpoint path Default: /v1/embeddings |
LOCAL_Environment variable | Optional | Optional, openai backend only: auto, response_format or none Default: auto |
From the publisher's entry in the official MCP Registry. Required settings are already in the install config below as placeholders.
Weekly newsletter
Like Ollama / vLLM Bridge? Get the best new MCP servers every week
The best new tools, security warnings before you install something risky, and one practical tip. Free, three minute read.
Alternatives to Ollama / vLLM Bridge
All alternatives →
Start Claude Code and Codex agents the person can watch, wait for them and read their answers.
Publish and discover MCP servers via the official MCP Registry. Powered by HAPI MCP server.
Provide your AI coding tools with token-efficient access to up-to-date technical documentation for…
Official Microsoft Learn MCP Server – real-time, trusted docs & code samples for AI and LLMs.
Give your AI agents trusted access to the full Postman platform.
Agent-Native design tool - create and edit visual designs with agent assistance
Ollama / vLLM Bridge: common questions
How do I install Ollama / vLLM Bridge?
In Claude Code run claude mcp add ollama-vllm-bridge -- uvx mcp-ollama-vllm. For Claude Desktop, Cursor and VS Code, paste the config shown above and restart. See the install guides.
Is Ollama / vLLM Bridge the official server?
Ollama / vLLM Bridge is a community project by setheerwagen, not verified by a company domain.
Is Ollama / vLLM Bridge free?
The code is published under the MIT licence. The service it connects to may have its own pricing.
Is Ollama / vLLM Bridge safe to use?
It scores 30 of 100. Grades: maintenance A, licence A, quality C. The security check has not run for it yet. Review the code before you install. How grades work.
What are alternatives to Ollama / vLLM Bridge?
Similar MCP servers: Harness, MCP Registry Server, ref-tools-ref-tools-mcp, Microsoft Learn MCP.
Does Ollama / vLLM Bridge work with ChatGPT?
Not directly. It runs locally, and ChatGPT only connects to remote servers with a URL. Use it in Claude Code, Claude Desktop, Cursor, VS Code or Codex.