Integration

Akkio integration

Akkio is a no-code AI analytics platform. Ask Chat Explore, its chat-with-your-data assistant, questions about a dataset or project and get answers with charts and tables; train predictive models on a dataset and read their accuracy and field importance; and read, update and delete projects and their Chat Explore custom instructions. Chat Explore and training run as tasks: submit, poll the status tool, then read the result. The legacy v1 dataset and prediction routes, which take the key in the query string or body, are not exposed, nor is project creation (it needs internal organization and owner ids no route returns), so dataset and project ids come from the Akkio app. Authentication is the team API key from Team Settings, sent in the X-API-Key header.

Connect Akkio How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

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

What you can do with Akkio

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.

Project, 3 operations

delete_projectDelete projectDELETEDeletes an Akkio project.
get_projectGet projectGETGets an Akkio project: its id, name and Chat Explore custom instructions (chatContext, chatInstructions, chatSuggestions).
update_projectUpdate projectPUTUpdates an Akkio project's name or Chat Explore custom instructions. Only the fields you provide change; leave a field out to keep its current value. Returns the updated project.

New, 2 operations

create_chat_explore_queryCreate chat explore queryPOSTAsks Chat Explore, Akkio's chat-with-your-data assistant, a question about a project or dataset. Returns a task_id at once: poll get_chat_explore_status until SUCCEEDED, then read the answer with get_chat.
train_modelTrain modelPOSTStarts training a predictive model on an Akkio dataset to predict the given fields. Returns a task_id at once: poll get_training_status until SUCCEEDED, then read the model with get_training_result.

Status, 2 operations

get_chat_explore_statusGet chat explore statusGETGets the status of a Chat Explore task. Poll until status is SUCCEEDED (metadata.location then ends with the chat id to pass to get_chat) or FAILED (metadata.error says why).
get_training_statusGet training statusGETGets the status of a model training task. Poll until status is SUCCEEDED, then call get_training_result with the same task_id, or FAILED (metadata.error says why).

Chat, 1 operation

get_chatGet chatGETGets a Chat Explore chat by id: the messages, each with role, content, and optional images (charts) and table rows. Pass image_format=plotly_json to get charts as Plotly JSON instead of base64 images.

Result, 1 operation

get_training_resultGet training resultGETGets the trained model of a finished training task: model_id, per-class accuracy stats, field importance and the data story of what drives each outcome.

Use Akkio from Claude Code, Cursor or Codex

Connect Akkio in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Akkio 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 Akkio

Create your workspace
Sign up free. Nothing to install.
Connect Akkio once
Add your Akkio 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.