Inspect Estuary Flow captures, materializations, collections and stats. Hosted by usefulapi — connect from Claude, Cursor, or any MCP client.
Team and Enterprise: an Owner adds the connector for the organization first.
Run this command, then run /mcp in Claude Code to log in:
Add to Cursor or add this to ~/.cursor/mcp.json:
{
"mcpServers": {
"estuary-flow": {
"url": "https://estuary-flow.usefulapi.io/mcp"
}
}
}Add to VS Code or add this to .vscode/mcp.json:
{
"servers": {
"estuary-flow": {
"type": "http",
"url": "https://estuary-flow.usefulapi.io/mcp"
}
}
}Other MCP clients (Windsurf, Cline, Zed and more): add the URL as a remote MCP server (Streamable HTTP). The client then opens the login page in your browser. Do not add an Authorization header: see Before you connect.
The login page asks for your Estuary Flow refresh token.
Create one in Estuary Flow → Admin → CLI-API. Your token is used only to call the API on your behalf and to derive a private account id; it is never shown to anyone.
Add only the URL. Do not add an Authorization header or an API key to the client config. The server signs you in with OAuth: the login page asks for your Estuary Flow refresh token. If the config has such a header, remove it: some clients then send that header instead of the login token, and every call fails with 401.
Turn on the Estuary Flow connector, then ask in plain words. The AI picks the tools.
| Tool | Type | What it does |
|---|---|---|
estuary_list_catalog | read | List catalog entities List live catalog entities (captures, collections, materializations, tests) the user can read, with connector + last-publication metadata. Optionally filter by a catalog-name prefix and spec_type. Estuary control-plane view live_specs_ext. PostgREST: GET /live_specs_ext. |
estuary_get_catalog_spec | read | Get catalog spec Get one live catalog entity by its exact catalog_name, including the full serialized `spec` and compiled `built_spec`. Estuary control-plane view live_specs_ext. PostgREST: GET /live_specs_ext?catalog_name=eq.<name>&limit=1. |
estuary_get_catalog_stats | read | Get catalog stats Get usage/throughput stats for one catalog entity — bytes & docs read/written (both directions), usage_seconds, warnings/errors/failures, and txn_count — per time grain. Optionally bound by a timestamp range. Estuary control-plane view catalog_stats. PostgREST: GET /catalog_stats. |
estuary_list_connectors | read | List connectors List the connector catalog — available capture/materialization Docker connectors, with titles, descriptions, and logos. Optionally filter to recommended connectors. Estuary control-plane table connectors. PostgREST: GET /connectors. |
estuary_list_connector_versions | read | List connector versions List available versions (image tags) of connectors, with protocol and documentation URL. Optionally filter by connector_id. Estuary control-plane table connector_tags. PostgREST: GET /connector_tags. |
estuary_list_drafts | read | List drafts List the user's draft workspaces (staging areas for catalog edits before publishing). Estuary control-plane table drafts. PostgREST: GET /drafts. |
estuary_list_draft_specs | read | List draft specs List the staged spec entries within a draft (each an insert/replace of a catalog entity pending publication). Estuary control-plane table draft_specs. PostgREST: GET /draft_specs. |
estuary_list_publications | read | List publications List publication history/status — each publish attempt of a draft; job_status carries the queued/success/failed outcome. Estuary control-plane table publications. PostgREST: GET /publications. |
estuary_list_discovers | read | List discovers List connector discovery jobs (auto-detecting bindings/resources for a capture). Estuary control-plane table discovers. PostgREST: GET /discovers. |
estuary_list_roles | read | List roles List the roles/capabilities the current credential is granted — which catalog prefixes it can read/write/admin. Read-only RPC. Estuary control-plane: POST /rpc/auth_roles. |
estuary_get_tenant | read | Get tenant Get the user's tenant(s) — quotas (tasks/collections), billing tiers, recurring charge, trial start, and payment provider. Estuary control-plane table tenants. PostgREST: GET /tenants. |
estuary_view_task_logs | read | View task logs Fetch the log lines for a job by its logs_token (a UUID found on a publication, discover, or connector-tag record). Optionally page from a last-seen timestamp. Read-only RPC. Estuary control-plane: POST /rpc/view_logs. |
estuary_create_draft | write | Create draft WRITE: create a new empty draft workspace (a staging area for catalog changes; does not affect live pipelines). Estuary control-plane: POST /drafts. Returns the created row. |
estuary_upsert_draft_spec | write | Upsert draft spec WRITE: stage (insert or replace) a catalog spec inside a draft. Edits only the draft — live pipelines are unaffected until the draft is published. Estuary control-plane: POST /draft_specs (upsert on draft_id,catalog_name). Returns the staged row. |
estuary_publish_draft | write | Publish draft WRITE (DESTRUCTIVE when dry_run=false): publish a draft. dry_run=true (default) only VALIDATES the draft without changing anything. dry_run=false APPLIES the draft to the LIVE catalog — this can create, modify, or DELETE running data pipelines and their data. Set dry_run=false only when you intend to change live infrastructure. Estuary control-plane: POST /publications. Returns the publication row. |
estuary_flow_usage_status | Usage status (free-tier meter) Report the caller's current free-tier usage this month: calls used, monthly limit, remaining, and whether the cap is reached. Read-only; does not count against the meter. | |
estuary_flow_request_feature | Request a missing feature Tell usefulapi that the user needs something the Estuary Flow tools cannot do yet (a missing tool, field or filter). Call it only when the user asks for something none of the tools can do, and tell the user that you send the request. Do not call it for errors or for normal requests. Do not include personal data, credentials or customer records. Stored with the product name and the client type (for example Claude or Cursor), without the user's account. At most 5 requests per day. Does not count against the meter. | |
estuary_flow_upgrade | Upgrade to Pro (unlimited) Subscribe to the Pro plan for UNLIMITED Estuary Flow tool calls (the free tier caps monthly usage). Choose monthly ($9/month) or yearly ($90/year — 2 months free) billing. Returns a Stripe Checkout link to open in your browser; after payment your account upgrades automatically. Does not count against the meter. | |
estuary_flow_cancel_subscription | Cancel the Pro subscription Cancel the caller's Estuary Flow Pro subscription at the end of the paid period (no refund for the current period; unlimited calls continue until then, then the free tier applies). Requires confirm: true. Run estuary_flow_upgrade later to undo the cancel before the period ends. Does not count against the meter. |
| Plan | Price | Limit |
|---|---|---|
| Free | $0 | 100 tool calls / month |
| Pro | $9/mo · $90/yr | Unlimited |
Pro covers this Estuary Flow server only. Subscribe with estuary_flow_upgrade (it returns a Stripe Checkout link). Cancel any time with estuary_flow_cancel_subscription: Pro continues to the end of the paid period, with no refund for the current period, and running estuary_flow_upgrade before then undoes the cancel. Or write to [email protected].
No. usefulapi is an independent service. It is not affiliated with or endorsed by Estuary Flow. The server calls the Estuary Flow API with your own Estuary Flow access, so it sees only the data that your account can see.
The login page asks for your Estuary Flow refresh token. See Before you connect for where to find it.
No. Add only the URL. Do not add an Authorization header or an API key to the client config. The server signs you in with OAuth: the login page asks for your Estuary Flow refresh token. If the config has such a header, remove it: some clients then send that header instead of the login token, and every call fails with 401.
The login stores them encrypted in the authorization grant of your connection. The server uses them to call the Estuary Flow API for you and to derive a private account id for usage metering. usefulapi does not show them on any page or in any reply. To stop all access, remove the connector and change or delete these credentials in Estuary Flow.
Yes, if you approve it. 3 of the 15 Estuary Flow tools can create or change data. The other 12 are marked read-only. Most MCP clients ask you to approve a tool call before it runs.
The Free plan gives 100 tool calls / month. Pro costs $9/mo or $90/yr, with unlimited tool calls, for this Estuary Flow server only. Run estuary_flow_usage_status to see how many calls you used.
Ask the AI to run estuary_flow_upgrade: it returns a Stripe Checkout link. To cancel, run estuary_flow_cancel_subscription. Pro continues to the end of the paid period.
Tell the AI what you wanted to do. It can send the request with estuary_flow_request_feature. We store the text with the server name, the type of AI client and the tool you tried, not with your account, and read every request when we plan new tools. You can send up to 5 requests per day.
Any client that supports remote MCP servers (Streamable HTTP) with OAuth login: Claude (web and desktop), Claude Code, Cursor, VS Code, Windsurf and others.
This is a Model Context Protocol endpoint — meant to be connected from an AI client, not opened in a browser. An invalid_token response at the URL is the auth gate working as designed; clients authenticate automatically.