Extract

View saved version →

---
name: control-extract-diagnostics
description: Diagnose failed Control Extract connections, inspect recent failed runs, and trigger manual runs only after explicit user confirmation.
---

# Control Extract Diagnostics

Use this skill when the user asks why an Extract pipeline failed, wants failed
or unhealthy connections, asks for run diagnostics, or asks to manually trigger
a connection run.

The plugin uses only the Control Extract MCP server:

- `control-extract` at `https://api.extract.to/mcp-account`, displayed as Control Extract.

Extract documentation: https://docs.extract.to/

## Tools

Use these `control-extract` tools:

- `search_connections` - find failed, unhealthy, or matching pipelines.
- `get_connection` - inspect one pipeline before diagnosis or run control.
- `list_connection_runs` - inspect recent run history.
- `diagnose_connection` - read failure diagnostics from recent run logs.
- `trigger_run` - trigger a manual run only after explicit user confirmation.

## Workflows

### Find Failed Connections

Use the `search_connections` tool on `control-extract` with `status="ERROR"` when the user
asks for failed, failing, broken, or unhealthy pipelines.

If the user asks why a pipeline failed, identify the exact connection first,
then call the `diagnose_connection` tool on `control-extract`.

### Diagnose A Run

Use the `get_connection` or `list_connection_runs` tool on `control-extract` to confirm the
connection context before calling `diagnose_connection`.

### Trigger A Manual Run

Never call `trigger_run` until the user explicitly confirms the exact
connection to run. Before asking for confirmation, show the connection name,
source, destination, and current status with `get_connection`.

## Safety Rules

- Do not expose credentials, tokens, secrets, or unnecessary PII.
- Use `diagnose_connection` for failure logs; do not invent failure causes.
- Do not trigger a run based on an ambiguous connection match.
- Treat `trigger_run` as a user-confirmed operation, even if the tool itself is
  available.

View saved version →

---
name: control-extract-operations
description: Use Control Extract for account health, connector inventory, pipeline listings, connection details, and run history.
---

# Control Extract Operations

Use this skill when the user asks about Extract account status, configured
connectors, sources, destinations, pipelines, connection details, or recent run
history.

The plugin exposes one MCP server:

- `control-extract` at `https://api.extract.to/mcp-account`, displayed as Control Extract.

Extract documentation: https://docs.extract.to/

## Tools

Use these `control-extract` tools:

- `account_summary` - summarize account connectors and connections.
- `list_connectors` - list all account connectors, sources, and destinations.
- `search_connectors` - filter account connectors by name, type, or platform.
- `get_connector` - inspect one configured connector.
- `list_connections` - list pipelines.
- `search_connections` - find pipelines by source, destination, or status.
- `get_connection` - inspect one pipeline.
- `list_connection_runs` - list recent runs for a pipeline.

## Workflows

### Account Health

Use the `account_summary` tool on `control-extract` for account status, pipeline health,
active connections, disabled connections, and error counts.

### Connector Inventory

Use the `list_connectors` tool on `control-extract` for a broad source/destination inventory.
Use the `search_connectors` tool on `control-extract` when the user provides a connector name,
type, or platform filter.

### Pipeline Details

Use the `list_connections` tool on `control-extract` for broad pipeline discovery. Use
the `search_connections` tool on `control-extract` when the user provides a source,
destination, status, or name filter. Then call the `get_connection` tool
on `control-extract`
before answering detailed questions about one pipeline.

### Run History

Use the `list_connection_runs` tool on `control-extract` after identifying the connection.

## Safety Rules

- Do not expose credentials, tokens, secrets, or unnecessary PII.
- Do not guess connector ids or connection ids.
- If multiple connectors or connections match, ask the user to choose one.
- Use the setup skill for creating sources, destinations, connections, schedule
  changes, stream selection, or sample data.
- Do not use this plugin for SQL analysis, schema discovery, or metadata editing;
  this plugin is account-MCP-only.

View saved version →

---
name: control-extract-setup
description: Use Control Extract to create sources, destinations, and connections, update schedules, select streams, retrieve source sample data, and direct users to Extract account creation or invite pages.
---

# Control Extract Setup

Use this skill when the user wants to create or configure Extract sources,
destinations, connections, schedules, stream selections, source sample data, an
Extract account, or user access to their current Extract account.

The plugin uses only the Control Extract MCP server:

- `control-extract` at `https://api.extract.to/mcp-account`, displayed as Control Extract.

Extract documentation: https://docs.extract.to/

Account access links:

- Create a new Extract account: https://app.extract.to/create-account
- Invite a user to the current Extract account: https://app.extract.to/users/new

## Tools

Use these `control-extract` tools:

- `list_connectors` - find existing sources and destinations before setup.
- `search_connectors` - filter sources and destinations by name, type, or platform.
- `get_connector` - inspect one configured source or destination.
- `create_source` - create a source in setup status and return a setup URL.
- `create_destination` - create a destination in setup status and return a setup URL.
- `create_connection` - create a connection in setup status and return a setup URL.
- `get_connection` - inspect a connection before configuration changes.
- `update_connection_schedule` - update schedule, custom cron, or enabled state.
- `select_connection_streams` - enable exact streams and disable all others.
- `create_sample_data` - start a source sample-data task for a stream.
- `get_sample_data` - poll sample-data status and return CSV content when ready.

## Workflows

### Create An Account

When the user wants a new Extract account, direct them to
https://app.extract.to/create-account.

If they are connecting Codex or Claude for the first time, explain that they can
create the account in the browser, then return to the Codex plugin or Claude
connector authorization flow after signing in.

### Invite A User

When the user wants to invite another person to their current Extract account,
direct them to https://app.extract.to/users/new.

Tell the user to open the link while signed in to the Extract account they want
to invite the person into. Do not collect invitee email addresses or other
personal details in chat unless the user explicitly asks for help drafting an
invite message.

### Create A Source Or Destination

Before calling `create_source` or `create_destination`, confirm the connector
platform, display name, and any non-secret parameters with the user. Do not ask
for secrets in chat; after creation, tell the user to open the returned
`setup_url` to complete authentication and secret entry in Extract.

### Create A Connection

Use `list_connectors` or `search_connectors` to identify the source and
destination. If multiple matches exist, ask the user to choose one. Confirm the
exact source and destination before calling `create_connection`, then return
the `setup_url` so the user can configure streams and parameters in Extract.

### Update Schedule Or Enabled State

Use `get_connection` to confirm the target connection. Confirm the exact
schedule, custom cron expression when `schedule="CUSTOM"`, and enabled state
before calling `update_connection_schedule`.

### Select Streams

Use `get_connection` to confirm the target connection, then confirm the exact
stream names before calling `select_connection_streams`. This tool disables all
streams that are not listed in `stream_names`.

### Get Source Sample Data

Use `create_sample_data` with the source account connector id and exact stream
name. Immediately poll `get_sample_data` with the returned sample data id until
the status is complete or failed. When `csv_content` is returned, save the full
CSV content to a local file using the returned `suggested_filename`; do not
summarize, truncate, filter columns, or paste the CSV into chat.

## Safety Rules

- Always confirm before creating a source, destination, or connection.
- Always confirm before changing a schedule, enabled state, or stream selection.
- Do not claim an account was created or an invite was sent unless the user
  confirms they completed it in Extract.
- Never expose credentials, tokens, secrets, setup URLs with sensitive query
  parameters, or unnecessary PII.
- Do not ask for account passwords, OAuth codes, invite tokens, or other
  credentials.
- If the user asks to invite someone to a different account, tell them to switch
  accounts in Extract first, then open the invite link.
- Do not guess connector ids, connection ids, or stream names.
- Treat `select_connection_streams` as a write operation because it changes sync
  configuration.
- For sample data, the local CSV file is the deliverable; keep chat output brief.