← All integrations

Databox MCP server

14 operations0 webhooks

Business analytics with Databox - create data sources and datasets, push up to 500 records per call, poll ingestion results, read metrics over date ranges with breakdowns, and list dashboards.

Try Databox with your agent

Connect Databox, then paste this into Claude, ChatGPT or Cursor. For ideas from other apps, see the use cases.

Using Corsair, show me what you can do in Databox on my account, then run one read-only example and show me the result.

Runs once, when you ask

Databox tools and triggers

Tools are what your agent can do in Databox through Corsair's MCP server. Triggers are the Databox events a routine can start from.

Datasets

  • CreateWrite

    Create a dataset in a data source with column definitions and an optional primary key that makes re-ingested records overwrite

    datasets.create

  • GetRead-only

    Read one dataset with its status, sync and verification info

    datasets.get

  • Get IngestionRead-only

    Read one ingestion's status and record counts: how many records were appended, overwritten or rejected

    datasets.getIngestion

  • Ingest DataWrite

    Submit up to 500 records for ingestion; the response carries an ingestionId to poll in datasets.getIngestion

    datasets.ingestData

  • ListRead-only

    List datasets, optionally filtered by data source or type (API-created or merged), with search and paging

    datasets.list

  • List DataRead-only

    Read a page of a dataset's records with the column schema; records are keyed by column ID

    datasets.listData

Data Sources

  • CreateWrite

    Create a data source for pushing custom data through the API; only a name is required

    dataSources.create

  • DeleteDestructive

    Permanently delete a data source and every dataset and record it holds; this cannot be undone

    dataSources.delete

  • GetRead-only

    Read one data source, including its status and sync interval

    dataSources.get

  • ListRead-only

    List the data sources in the organization, with search, connection filter, sorting and paging

    dataSources.list

Metrics

  • Get DataRead-only

    Read a metric's values over a date range with granularity, dimension breakdowns and filters; may wait for a first sync (up to two minutes)

    metrics.getData

  • ListRead-only

    List the organization's metrics with their dimensions, optionally filtered by source or name

    metrics.list

Connect Databox to Claude, ChatGPT or Cursor

  1. 1

    Connect Databox in Corsair

    Add your Databox API key once in Corsair. Corsair stores the credential encrypted and makes the Databox API calls for your agent, so it never goes into a prompt or a config file. Connect Databox

    If your link lets the agent add apps, you can skip this: it gives you a sign-in link the first time it needs Databox. On a ChatGPT personal plan, connect Databox here first.

  2. 2

    Add Corsair's MCP server to your agent

    Every client uses the same address:

    https://mcp.corsair.dev/mcp
    Open Customize → Connectors → Add custom connector, paste the address, then select Connect.

    Codex, Gemini CLI, VS Code, Zed and other clients with OAuth sign-in work the same way. Clients without it, such as GitHub Copilot's coding agent, use a link's own address and an API key. Setup for every client

  3. 3

    Sign in and choose what needs your approval

    Your client opens Corsair to sign in. Pick a link: the apps your agent can use and a mode that decides what it may do without asking. In the default Cautious mode, Databox's read and write operations run right away and its 1 destructive operation waits for your approval. Strict mode asks before every write and refuses destructive operations, and Read mode allows reads only.

FAQ

Install corsair and @corsair-dev/databox, add the Databox plugin, and connect with an API key. Then call methods like corsair.databox.api.auth.validateKey() from your app. Corsair keeps each tenant isolated.

Yes. Databox requires an API key from your Databox account or developer dashboard. Create credentials with access that matches what you automate, then paste them into Corsair or connect through managed auth in Hub.

Yes. One Corsair client can hit Databox, GitHub, Notion, Stripe, and the rest. Trigger Databox from a webhook, push updates to Slack, or chain actions across plugins. Same tenant context across integrations, plain TypeScript.

Teams use Corsair for business analytics with Databox - create data sources and datasets, push up to 500 records per call, poll ingestion results, read metrics over date ranges with breakdowns, and list dashboards. Common builds include sync jobs, admin tooling, and agents that call Databox APIs from your backend.

The SDK is open source. Self-host and you pay Corsair nothing for the integration layer. Hub bills for hosted auth and execution, not per Databox API call. Hub has a generous free tier. For hobby projects you can probably run the whole thing on free. Paid plans start to matter with more tenants or heavier traffic.

We maintain @corsair-dev/databox in the open repo. When Databox ships API changes, upgrade the package. Your call sites stay typed. You should not need to rewrite the integration layer each time.

No. Corsair does not read your Databox data or hold individual access credentials. Credentials stay in your database. API calls run on your instance. We do not store Databox data on your behalf.

Yes. Add https://mcp.corsair.dev/mcp as a custom connector or MCP server in Claude, ChatGPT, Cursor, VS Code, Claude Code, Codex or any client that supports remote MCP servers with OAuth sign-in, then sign in to Corsair. On ChatGPT personal plans, custom servers currently get read tools only.

Yes. Put Databox on a link in Strict mode and every write waits for your approval, while destructive actions are refused. The default Cautious mode asks only before the 1 destructive Databox operation. You can change a link's mode at hub.corsair.dev/me.