Connect Ollama to Cursor via MCP: Models and Chat

💡 No install? Use cloud.anythingmcp.com directly. Sign in, click Connectors → Ollama, paste your credentials, mint an MCP API key — done. No Docker, no git clone, no local server.

Ollama + Cursor

Let your AI use open-weight models such as Gemma, Llama, Qwen, Mistral and DeepSeek running on your own Ollama server (or Ollama Cloud): list installed and loaded models, read a model's details and capabilities, chat, generate text and create embeddings, without sending data to a hosted AI provider.

Prerequisites

See the full setup instructions baked into the connector (visible in the in-app store when you select the connector). The required environment variables for this connector are:

OLLAMA_URL

Step 1 — Get credentials

Setting up takes about 2 minutes. You need an Ollama server that AnythingMCP can reach, with at least one model pulled, or an Ollama Cloud API key.

1. Install Ollama from https://ollama.com/download and pull a model, e.g. ollama pull gemma3.
2. Put the server's base URL, without /api, into OLLAMA_URL, e.g. http://localhost:11434 (Ollama's default port). If AnythingMCP runs in Docker and Ollama runs on the host, use http://host.docker.internal:11434. For Ollama on another machine, start it there with OLLAMA_HOST=0.0.0.0 and use that machine's address.
3. Self-hosted AnythingMCP: add that host (e.g. localhost, host.docker.internal or the server's IP) to SSRF_ALLOWED_HOSTS on the AnythingMCP backend, which blocks local and private addresses by default. AnythingMCP Cloud cannot reach a server on your own machine or network: use Ollama Cloud (step 4) or an Ollama server with a public address.
4. Leave OLLAMA_API_KEY empty for a local server. For Ollama Cloud, set OLLAMA_URL to https://ollama.com and paste a key from https://ollama.com/settings/keys. For a server behind a reverse proxy that checks a token, put the proxy's bearer token here. The key is sent as Authorization: Bearer only when it is set.
5. Install the connector and run ollama_get_version: it shows that the server answers.

What it does: ollama_list_models lists the installed models with family, parameter size and quantization, and ollama_list_running_models shows which ones are loaded in memory right now. ollama_show_model returns a model's capabilities (completion, vision, tools, thinking, embedding), context length, parameters and prompt template, so the AI can check what a model supports before it sends images or tools. ollama_chat holds a conversation with a system prompt, history, images for vision models, tool calling, JSON output and thinking. ollama_generate answers a single prompt, including fill-in-the-middle with suffix on code models. ollama_embed creates embedding vectors with an embedding model such as embeddinggemma or nomic-embed-text. Prompts and answers stay on your own server.

Speed and costs: answers are not streamed. The first call to a model that is not loaded also loads it, which takes from a few seconds to a minute on large models (load_duration in the result shows it, in nanoseconds). A local server is free; Ollama Cloud usage counts against your account's plan. Model output can be wrong or contain instructions, so the AI treats it as data, not as orders.

Common errors: connection refused or blocked means Ollama is not running at OLLAMA_URL, it listens only on 127.0.0.1 of another machine, or the host is missing from SSRF_ALLOWED_HOSTS. 404 model 'x' not found means the model is not installed: run ollama pull x on the server. 400 does not support tools/thinking/insert, or an embedding error, means the model lacks that capability (check ollama_show_model). 401 on Ollama Cloud means the API key is missing or wrong.

The connector does not pull, push, copy, create or delete models, so it never changes what is installed on your server.

Step 2 — Install the adapter

curl -fsSL https://raw.githubusercontent.com/HelpCode-ai/anythingmcp/main/docker-compose.quickstart.yml -o docker-compose.yml
printf 'JWT_SECRET=%s\nENCRYPTION_KEY=%s\n' "$(openssl rand -hex 32)" "$(openssl rand -hex 32)" > .env
docker compose up -d

Step 3 — Add the connector in Cursor

Your server URL: in AnythingMCP, open MCP Servers → the server this connector is on, and copy its URL (https://cloud.anythingmcp.com/mcp/…). Use it wherever this guide shows YOUR_SERVER_ID.

Cursor reads MCP servers from ~/.cursor/mcp.json. Add this entry:

{
  "mcpServers": {
    "anythingmcp": {
      "url": "https://cloud.anythingmcp.com/mcp/YOUR_SERVER_ID",
      "headers": { "X-API-Key": "YOUR_MCP_API_KEY" }
    }
  }
}

1. Create an MCP API key in AnythingMCP under MCP Servers → your server → API keys, and paste it in place of YOUR_MCP_API_KEY.
2. Save the file and restart Cursor.
3. Open Cursor → Settings → MCP and check that anythingmcp is listed and connected.
4. Start chatting — the agent can now call the Ollama tools.

Available tools

FAQ

Does Cursor support custom MCP servers on the free tier? Yes — MCP is available on Hobby, Pro and Business plans.

Next steps

• Connector landing page
• Connect to Claude
• Connect to ChatGPT