Integration

Mode integration

Mode (a ThoughtSpot company) is a collaborative SQL, Python and reporting platform. An agent can browse the Workspace's Collections and reports, start a report run and follow its state and per-query runs (SQL rendered, state, errors), read, add, edit and delete the SQL queries of a report, rename, move, archive, unarchive or delete reports, and list the connected data sources. Not exposed: downloading run results (the vendor documents those content routes only in its cookbook), cloning and duplicating runs, purging results, schedules, subscriptions, members, groups, invites and data source edits. Authentication is HTTP Basic with a Workspace API token (username) and its secret (password), created by a Workspace admin under Workspace Settings, Privacy and Security, API; the API needs a paid Workspace, and the connection also stores the Workspace username (lowercase) that every call is made under.

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Mode.Built from the 22 Mode tools below, on the connection you add once.

What you can do with Mode

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.

Query, 5 operations

  • create_queryCreate queryPOSTAdds a SQL query to a report, run against one of the Workspace's data sources.
  • delete_queryDelete queryDELETERemoves a query from a report and returns it.
  • get_queryGet queryGETReturns one SQL query of a report, with its text and data source.
  • list_queriesList queriesGETLists the SQL queries of a report.
  • update_queryUpdate queryPATCHChanges the SQL text, name or data source of a query in a report.

Report, 5 operations

  • delete_reportDelete reportDELETEDeletes a report from its Collection.
  • get_reportGet reportGETReturns one report: name, Collection, run statistics, last successful run token and links.
  • list_collection_reportsList collection reportsGETLists the reports of one Collection (space), 30 per page; ask for the next page with page.
  • list_data_source_reportsList data source reportsGETLists the reports that use a given data source.
  • update_reportUpdate reportPATCHRenames a report, changes its description, or moves it to another Collection (space_token).

Run, 3 operations

  • get_report_runGet report runGETReturns one run of a report, with its state (pending, enqueued, running_notebook, succeeded, completed, failed or cancelled) and timestamps.
  • list_report_runsList report runsGETLists the runs of a report, with their state and timestamps.
  • run_reportRun reportPOSTStarts a new run of a report and returns that run; follow its state with get_report_run.

Data source, 2 operations

  • get_data_sourceGet data sourceGETReturns one connected database: adapter, host, database, warehouse and state.
  • list_data_sourcesList data sourcesGETLists the databases connected to the Workspace; each id is what create_query takes as data_source_id.

Query run, 2 operations

  • get_query_runGet query runGETReturns one query run of a report run: the rendered SQL, state, data source and error details.
  • list_query_runsList query runsGETLists the query runs of one report run: one per query, with the SQL that ran, its state and any error.

Space, 2 operations

  • get_collectionGet collectionGETReturns one Collection (space). The token's user must be allowed to view the reports in it.
  • list_collectionsList collectionsGETLists the Collections (called spaces in the API) visible to the token. filter=all also returns personal Collections (all of them for an admin), filter=custom only non-personal ones.

Archive, 1 operation

  • archive_reportArchive reportPATCHArchives a report: it is hidden from view but Workspace members still reach it through search or a direct link.

Resource, 1 operation

  • get_workspaceGet workspaceGETReturns the Workspace of the connection: its username, name, plan limits and links.

Unarchive, 1 operation

  • unarchive_reportUnarchive reportPATCHRestores an archived report.

Use Mode from Claude Code, Cursor or Codex

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

  1. Create your workspace

    Sign up free. Nothing to install.

  2. Connect Mode once

    Add your Mode connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.

  3. 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.

Mode integration FAQ

What can you do with the Mode integration?

LiveContext exposes 22 operations on Mode, covering query, report, run and data source.

Popular integrations

Browse the whole catalog