Integration

Ollama integration

Ollama's cloud API (ollama.com) runs open-weight models hosted by Ollama, with no local install. Chat with a cloud model or generate a completion (thinking, tool calling and image input on models that support them), answer typed choice, yes/no and scoring questions with a System One model, search the web and fetch a page as text, list the cloud models and read a model's details, and check the account's usage and remaining credits. Not exposed: the local-server routes (pull, push, create, copy and delete a model, running models, version), embeddings (no cloud model serves them) and structured JSON output (not supported on Ollama's cloud). Authentication is an Ollama API key sent as a Bearer token.

Connect Ollama How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Ollama.Built from the 9 Ollama tools below, on the connection you add once.

What you can do with Ollama

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Model, 2 operations

get_model_detailsGet model detailsPOSTReturns one cloud model's details: its capabilities, family and parameter count, context length and other model_info metadata, and the thinking values it accepts with their default.
list_modelsList modelsGETLists the models available on Ollama's cloud, with each model's name (the value to pass as model), size, digest, last update and capabilities such as completion, tools, thinking, vision or decision.

Balance, 1 operation

get_balanceGet balanceGETReturns the remaining Ollama cloud credits in USD: the plan's included balance and allowance for the current period, and the unexpired purchased credits. Legacy plans return session and weekly remaining percentages instead.

Chat, 1 operation

chatChatPOSTSends a conversation (messages with a role and content) to an Ollama cloud model and returns the assistant's next message in message.content, with message.thinking and message.tool_calls when requested, plus token counts.

Completion, 1 operation

generate_completionGenerate completionPOSTGenerates one completion for a prompt (with an optional system prompt, and images on vision models) from an Ollama cloud model and returns the text in response, plus the reasoning in thinking when requested and token counts.

Decision, 1 operation

answer_questionsAnswer questionsPOSTAnswers up to 64 named choice, yes/no or score questions about one shared text (and optional images) with a System One cloud model such as clef:27b, returning each answer with its probabilities. Needs a paid plan or credits.

Usage, 1 operation

get_usageGet usageGETReturns the account's Ollama cloud usage (requests, USD value, input, cached and output tokens) over the last 24 hours, 7 days or 30 days, as totals and hourly or daily buckets, optionally per model.

Web page, 1 operation

web_fetchWeb fetchPOSTFetches one web page by URL and returns its title, its main content as text, and the links found on the page.

Web search, 1 operation

web_searchWeb searchPOSTSearches the web for one query and returns up to 10 results (default 5), each with its title, URL and a relevant content snippet. Works with an API key from a free Ollama account.

Use Ollama from Claude Code, Cursor or Codex

Connect Ollama in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Ollama operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect Ollama

Create your workspace
Sign up free. Nothing to install.
Connect Ollama once
Add your Ollama connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.