# Redash MCP connector

The Redash connector brings your dashboards, alerts, subscriptions and access lists into Elaichi, so Claude, ChatGPT, Cursor, Microsoft Copilot or the Elaichi Agent can find, update and share them as the person who signed in.

Source: https://elaichi.ai/connectors/redash/

## Facts

| | |
| --- | --- |
| Application | Redash |
| Category | Analytics |
| AI tools | 109 |
| Authentication | Connects with an API key |
| Bring your own OAuth app | No |
| MCP endpoint | https://api.elaichi.ai/mcp |
| Works with | Claude, ChatGPT, Cursor, Microsoft Copilot, any MCP client, and the Elaichi Agent |
| Tools advertised by name | No. Connected tools are never listed one by one, however few there are. The endpoint advertises `search_tools` and `execute_tool` instead |

## What you can ask once Redash is connected

- Which Redash alerts fired this week and who subscribes to them?
- List the dashboards tagged finance and who they are shared with
- Mute the churn alert until Monday and tell me who subscribes

## Connect Redash in Elaichi

This happens once for the organization, before any client is involved.

1. Open Connections, choose Add connection, and pick Redash.
2. Optionally set Share with, then press Connect.
3. Paste a Redash API key. One person generates a token in Redash and pastes it once. Everyone else works through Share with, and never sees it.

Credentials are vaulted and nobody, including the AI, reads them back. The connection becomes a toolbox immediately, so you can curate which Redash tools are exposed, rename them, or freeze arguments before anyone points a client at it.

## Redash MCP connector for Claude

Endpoint: https://api.elaichi.ai/mcp

1. Open Customize, then Connectors.
2. Press Add.
3. Name it, paste the MCP server URL, then Continue.
4. Sign in and approve.

On Team and Enterprise, an Owner adds it once. Everyone else turns it on for themselves.

## Redash MCP connector for Claude Code

Endpoint: https://api.elaichi.ai/mcp

1. In a terminal, run `claude mcp add` with the endpoint.
2. Start Claude Code and run `/mcp`.
3. Pick elaichi, then sign in and approve in the browser.

```bash
claude mcp add --transport http elaichi --scope user https://api.elaichi.ai/mcp
```

Use `--scope project` instead to share it with the repository through `.mcp.json`.

## Redash MCP connector for ChatGPT

Endpoint: https://api.elaichi.ai/mcp

1. Open Plugins, then press the + button.
2. Name it and paste the endpoint into Server URL.
3. Leave Authentication on OAuth, then tick the risk acknowledgement.
4. Press Create, then sign in and approve.

Works on the web. The plugin directory lives at chatgpt.com/plugins.

## Redash MCP connector for Cursor

Endpoint: https://api.elaichi.ai/mcp

1. Open `~/.cursor/mcp.json`.
2. Add the endpoint under `mcpServers`.
3. Reload Cursor, then sign in and approve.

Set up per machine, so repeat it on each computer you work from.

## Redash MCP connector for Microsoft Copilot

Endpoint: https://api.elaichi.ai/mcp

1. In Copilot Studio, open your agent, then Tools, Add a tool, New tool and Model Context Protocol.
2. Paste the endpoint into Server URL, choose OAuth 2.0, then Dynamic discovery, and press Create.
3. Create a new connection, sign in and approve, then press Add to agent.
4. Under Channels, open Teams and Microsoft Copilot and make the agent available in Microsoft Copilot.

Microsoft Copilot was called Microsoft 365 Copilot. Keep the tool on end-user credentials, so each person signs in as themselves.

## Connect Redash to any MCP client

Endpoint: https://api.elaichi.ai/mcp

1. Add the endpoint as a remote MCP server.
2. Sign in and approve.

The Elaichi Agent already has these tools, with nothing to set up.

## What the consent screen decides

Every scope the client asks for starts ticked except "Delete things", which you tick yourself. Calling a Redash tool needs "Use your connected apps". Over MCP there is no trusted place to confirm a write in the moment, so the consent screen is the standing approval rather than a formality. Think hard before granting Use your connected apps, which can also delete in connected apps and cannot be undone.

## What teams do with Redash through Elaichi

### Tidy up dashboards before the quarterly review

Data. Ask which Redash dashboards carry the finance tag, rename the stale ones and share the right ones with leadership, without clicking through each page by hand.

### Find out which alerts fired overnight

Operations. Get a plain summary of the Redash alerts that triggered, who subscribes to each one and which are currently muted, before the morning standup.

### Fork a dashboard for the new cost center

Finance. Copy the existing spend dashboard in Redash, retitle it for the new cost center and hand the fork to the team that owns it.

### Mute a noisy alert during planned maintenance

Support. Tell the agent to mute the queue depth alert in Redash for the maintenance window, then confirm who is subscribed so nobody is surprised when it comes back.

### Share the pipeline dashboard with a new rep

Sales. Give a new hire access to the Redash pipeline dashboard and the alert on stalled deals, and check the access list reads the way the manager expects.

### See what the company is actually watching

Leadership. List the favorite Redash dashboards across the organization and the alerts tied to them, so you know which numbers people check every day.

## Elaichi vs Zapier MCP vs Composio for Redash

All three can connect Redash to an AI assistant, and all three have admin controls. They differ in where access lives and how you pay.

| What to check | Elaichi | Zapier MCP | Composio |
| --- | --- | --- | --- |
| Where the AI connects | One address for the whole organization. Endpoint: https://api.elaichi.ai/mcp | A server per member, created at sign-in. | An MCP endpoint per team, or an SDK. |
| Control over Redash tools | Allow or restrict single Redash tools, per role or user. | App and action restrictions on the account. | Role permissions, down to the action. |
| Record of calls | One audit entry per Redash call. | A History tab of tool calls. | A log of every tool call. |
| Single sign-on | SAML or OIDC, plus SCIM, on Gold. | SAML on Enterprise. | SAML and OIDC on Enterprise. |
| Price | Free for one person; $15 per user per month on Gold. | 2 tasks per successful call. | Billed per tool call. |

Sources: Zapier MCP [docs](https://docs.zapier.com/mcp/get-started/quickstart), [security](https://docs.zapier.com/mcp/manage/security), [usage](https://docs.zapier.com/mcp/features/usage); Composio [docs](https://docs.composio.dev/docs/composio-connect), [gateway](https://composio.dev/mcp-gateway), [enterprise](https://composio.dev/enterprise), [pricing](https://composio.dev/pricing). Checked September 2026.

Longer take: [Zapier MCP alternative](/blog/zapier-mcp-alternative/) and [when you don't need an MCP gateway](/blog/when-you-dont-need-an-mcp-gateway/).

## Frequently asked questions

### How do I connect Redash to Claude?

Connect Redash in Elaichi by pasting your Redash API key, the one found under your Redash profile, and nothing else, since there is no client ID or secret to generate. Then open Claude, go to Customize, then Connectors, then Add, and paste https://api.elaichi.ai/mcp. Sign in to Elaichi when Claude asks, and your Redash dashboards and alerts are available in the chat.

### Does Redash work with ChatGPT and Cursor as well as Claude?

Yes. Once Redash is connected in Elaichi, the same endpoint, https://api.elaichi.ai/mcp, works in Claude, ChatGPT, Cursor, Microsoft Copilot, any MCP client and the Elaichi Agent. You connect Redash once and every client sees it.

### What can an AI agent actually do with my Redash data?

It can list, open, create, update, fork and share Redash dashboards, add and remove tags and favorites, and set up or change alerts, alert subscriptions and mutes. It can also read and update the access lists that say who can see what in Redash. Short, concrete asks such as "mute the churn alert until Monday" work better than long paragraphs.

### Does connecting Redash give the AI access to every dashboard and alert?

No. The agent works inside the Redash access of the person who signed in, so it sees the dashboards and alerts that person could already open in Redash. Elaichi can narrow that further with roles and restrictions, and it never widens it beyond what Redash itself allows.

### Can my team share one Redash connection?

Yes. One person connects Redash with their API key, shares the connection with a team in Elaichi, and nobody else ever handles the key. Each teammate still signs in to Elaichi as themselves, so the audit log names the real person behind every Redash change.

### Can I stop an agent from deleting or changing things in Redash?

Yes. Restrictions in Elaichi apply per action, so you can restrict deleting Redash dashboards or alerts for a role or for one person while leaving reading and sharing open. A restricted action still appears in Elaichi's tool search, flagged as restricted, but no client can run it whatever the prompt says.

### What happens to a Redash connection when someone leaves?

Offboarding that person in Elaichi ends their access to Redash through every client at once. A Redash connection shared with the team keeps working for everyone else. If you want it gone entirely, disconnecting Redash once in Elaichi removes it from Claude, ChatGPT, Cursor, Microsoft Copilot and every other client.

### Does the Redash MCP connector work with Gemini, Codex, Claude Code or other MCP clients?

Yes. Redash is reached over the same MCP endpoint every client uses, so anything that speaks MCP can call it — Gemini, Codex, Claude Code, Windsurf, Cline, Zed and OpenCode among them — alongside Claude, ChatGPT, Cursor, Microsoft Copilot, and the Elaichi Agent. The tools on offer and the access behind them are identical whichever client asks. Only the setup screen differs.

### Is Elaichi an alternative to Zapier MCP for Redash?

Yes. Both let Claude, ChatGPT or Cursor use Redash. Zapier MCP fits a team that already automates in Zapier, since each person signs in and acts as themselves in that account. Elaichi fits when IT wants one address for the whole company, per-tool rules by role, and a record of every Redash call.

### How is Elaichi different from Composio for Redash?

Composio gives AI agents tools and sign-in handling across 1,000+ apps, for developers building agents or people using an assistant, billed per tool call. Elaichi gives a company's own people governed access to Redash: one address, restrictions per role or user, and $15 per user per month. Both have role permissions and a log of every call.

## All 109 Redash tools

Every tool below is callable through https://api.elaichi.ai/mcp once Redash is connected, subject to the toolbox it is in and the restrictions on the caller.

- **Get single Redash acl by ID** (Get). Get the access control list of a Redash query or dashboard. Returns an object keyed by access type (e.g. modify), each holding the list of users granted that access. Required: id (object id), object_type.
- **Create a Redash acl** (Create). Grant a Redash user access to an object. Required: object_type, object_id.
- **List all Redash acls** (List). Check whether the authenticated user has the given access type on a Redash query or dashboard. Returns {response: true|false}; it does not list users. Required: object_type, object_id, access_type.
- **Redash acls bulk delete** (Delete). Revoke one user's access of one type on a Redash query or dashboard (admin or owner only). Send user_id and access_type in the JSON body. Returns 200 with an empty (null) body. Required: object_type, object_id, user_id, access_type.
- **List all Redash alerts** (List). List Redash alerts. Returns the alert records in the collection: id, created_at, updated_at.
- **Create a Redash alert** (Create). Create a Redash alert bound to a query. Returns the created alert object: id, created_at, updated_at.
- **Get single Redash alert by ID** (Get). Get a Redash alert by id. Returns the alert object: id, created_at, updated_at. Required: id.
- **Update a Redash alert by ID** (Update). Update an existing Redash alert by id. Returns the updated alert object: id, created_at, updated_at. Required: id.
- **Delete a Redash alert by ID** (Delete). Delete a Redash alert by id. Returns a 200 OK response on success; the response body shape is not documented in the upstream OpenAPI spec. Required: id.
- **List all Redash alert subscriptions** (List). List alert subscriptions attached to an alert in Redash. Returns an array of subscription records; the response body is not enumerated in the discovered source, so each record is documented generically as id plus content-type-specific attributes. Required: alert_id.
- **Create a Redash alert subscription** (Create). Subscribe to a Redash alert, either through an alert destination (destination_id) or, when destination_id is omitted, as the calling user by email. A JSON body is always required; send {} at minimum. Returns the created subscription: id, user, alert_id, destination. Required: alert_id.
- **Delete a Redash alert subscription by ID** (Delete). Detach a subscription from an alert in Redash. Returns an empty 200 response on success. Required: alert_id and id.
- **Create a Redash alert eval** (Create). Trigger evaluation of a Redash alert by id. Returns a 200 OK response with no documented body on success. Required: alert_id. Takes no request body.
- **Create a Redash alert mute** (Create). Mute a Redash alert by id. Returns an empty 200 response on success. Required: alert_id. Takes no request body.
- **Redash alert mutes bulk delete** (Delete). Unmute a Redash alert by id (DELETE on the mute endpoint). Returns an empty 200 response on success. Required: alert_id.
- **List all Redash dashboards** (List). List Redash dashboards the caller can access. Returns dashboard records with id, slug, name, user, layout, options, tags, is_draft, is_archived, is_favorite, version and timestamps; widgets is always null here (use dashboards.get). Filter with q and tags, sort with order. Max 250 per page.
- **Create a Redash dashboard** (Create). Create a Redash dashboard. Only name is read; Redash always creates it as a draft with an empty layout (publish with dashboards.update and is_draft false). Returns the created dashboard: id, slug, name, user, layout, options, tags, version and timestamps. Required: name.
- **Get single Redash dashboard by ID** (Get). Get a Redash dashboard by id (pass legacy to look up by slug). Returns the dashboard with widgets, layout, options, tags, version, user, can_edit and, when shared, public_url and api_key. Required: id.
- **Update a Redash dashboard by ID** (Update). Modify a Redash dashboard. Returns the updated dashboard object including id, name, slug, version, layout, widgets, and options. Required: id.
- **Delete a Redash dashboard by ID** (Delete). Archive a Redash dashboard. Returns the archived dashboard object including id, name, slug, is_archived, and updated_at. Required: id. Redash archives the record (is_archived=true) rather than removing it.
- **List all Redash dashboards favorites** (List). List Redash dashboards marked as favorites by the current user. Returns an array of favorited dashboard objects via the `results` envelope.
- **List all Redash dashboards tags** (List). List all Redash dashboard tags. Returns one record per tag with name and count (number of dashboards carrying it). Not paginated.
- **Create a Redash dashboard fork** (Create). Fork a Redash dashboard into a new dashboard owned by the caller. Returns a 200 OK response on success; the OpenAPI does not enumerate response fields. Required: dashboard_id. Takes no request body.
- **Create a Redash dashboard share** (Create). Enable anonymous access to a redash dashboard. Returns: public_url, api_key. Required: dashboard_id. Takes no request body.
- **Redash dashboard shares bulk delete** (Delete). Disable anonymous access to a redash dashboard. Returns an empty 200 response on success. Required: dashboard_id.
- **Create a Redash dashboard favorite** (Create). Mark a Redash dashboard as a favorite. Returns a 200 OK response on success with no documented body. Required: object_id. Takes no request body.
- **Redash dashboard favorites bulk delete** (Delete). Remove a Redash dashboard from the user's favorites. Returns a 200 OK response on success with no documented body. Required: object_id.
- **List all Redash my dashboards** (List). List dashboards created by the authenticated Redash user. Returns dashboard records with id, slug, name, layout, options, tags, is_draft, is_archived, version and timestamps; widgets is always null here. Filter with q (not search) and tags, sort with order. Max 250 per page.
- **List all Redash data sources** (List). List Redash data sources the caller can access. Returns id, name, type, syntax, paused, pause_reason, supports_auto_limit and view_only for each; options are not included (use data_sources.get as an admin). Not paginated.
- **Create a Redash data source** (Create). Create a Redash data source (admin only). options is a JSON object validated against the type configuration_schema from data_sources_types.list; invalid options return 400. Returns the created data source with masked options. Required: name, type, options.
- **Get single Redash data source by ID** (Get). Get a Redash data source by id. Returns id, name, type, syntax, paused, pause_reason, supports_auto_limit and view_only; options (masked), queue names and groups are included only for admins. Required: id.
- **Update a Redash data source by ID** (Update). Replace a Redash data source name, type and options (admin only); all three are required, and the options keys sent are merged into the stored options. Returns the data source with masked options. Required: id, name, type, options.
- **Delete a Redash data source by ID** (Delete). Delete a Redash data source by id. Returns an empty 204 response on success. Required: id.
- **Redash data sources pause** (Pause). Pause a Redash data source. Returns a 200 OK response on success. Required: data_source_id.
- **Redash data sources resume** (Resume). Resume a paused Redash data source. Returns a 200 OK response on success. Required: data_source_id.
- **List all Redash data sources types** (List). List the data source types (query runners) available in this Redash instance, such as PostgreSQL, MySQL and BigQuery (admin only). Returns an array with name, type and configuration_schema (the JSON schema for the data source options) for each type.
- **Get single Redash data source schema by ID** (Get). Get the table and column schema of a Redash data source. Returns {schema} (list of tables with columns) when a cached schema exists, otherwise {job}: poll jobs.get until status is 3. Pass refresh to force a new fetch. Required: id.
- **Create a Redash data source test** (Create). Test a Redash data source connection. Returns 200 OK on success. Required: data_source_id. Takes no request body.
- **Get single Redash databricks database by ID** (Get). List the databases of a Databricks data source (id = data source id). Returns the cached list when Redash has one; otherwise returns {job}: poll jobs.get until status 3 and read job.result. Fails with 400 for non-Databricks data sources.
- **List all Redash destinations** (List). List Redash alert destinations. Returns id, name, type and icon for each; options are not included here (use destinations.get). Not paginated.
- **Create a Redash destination** (Create). Create a Redash alert destination (admin only). options is a JSON object validated against the type configuration_schema from destinations_types.list; invalid options return 400. Returns the created destination with id, name, type, icon and masked options. Required: name, type, options.
- **Get single Redash destination by ID** (Get). Get a Redash destination by id. Returns the destination object including its id. Required: id.
- **Update a Redash destination by ID** (Update). Replace a Redash alert destination name, type and options (admin only); all three are required, and the options keys sent are merged into the stored options. Returns the destination with id, name, type, icon and masked options. Required: id, name, type, options.
- **Delete a Redash destination by ID** (Delete). Delete a Redash alert destination (admin only). Returns 204 No Content with an empty body. Required: id.
- **List all Redash destinations types** (List). List the alert destination types available in this Redash instance (admin only), such as email, Slack and webhook. Returns an array with name, type, icon and configuration_schema (the JSON schema for the destination options) for each type.
- **List all Redash events** (List). List audit events recorded in Redash, newest first (admin only). Returns event records with org_id, user_id, user_name, action, object_type, object_id, created_at, browser, location and details. Events have no id. Paginated with page and page_size (max 250) from the results envelope.
- **Create a Redash event** (Create). Record one or more events in Redash. The body is a JSON array of event objects (action, object_type, object_id, plus any extra keys); Redash overwrites user_id, org_id, user_agent and ip. Returns 200 with an empty (null) body.
- **List all Redash groups** (List). List groups in Redash. Returns each group with id, name, permissions, type and created_at. Not paginated.
- **Create a Redash group** (Create). Create a group in Redash (admin only). Returns the created group: id, name, permissions, type, created_at. Required: name.
- **Get single Redash group by ID** (Get). Get a single group in Redash by id. The Redash API does not document return fields for this endpoint; consult upstream docs for the response shape. Required: id.
- ...and 59 more tools. Call `tools/list` via the MCP endpoint, or see the full catalog via the API, for the complete set.
