> ## Documentation Index
> Fetch the complete documentation index at: https://notikaai.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.
# Dreamlit MCP for Claude Desktop
> Connect Claude Desktop to Dreamlit MCP as a custom connector.
export const clientName_1 = "Claude Desktop"
export const clientSetupName_1 = "Claude Desktop"
export const clientName_0 = "Claude Desktop"
export const agentName_0 = "Claude"
export const clientSetupName_0 = "Claude Desktop"
export const clientSessionName_0 = "Claude Desktop"
Claude Desktop is where you already think out loud, shape copy, and work through ideas in conversation. Dreamlit's Model Context Protocol (MCP) server turns that into a notification workflow you can ship. No code, no separate tool, no leaving the chat.
You can ask Claude Desktop things like:
* *List my published workflows in Dreamlit.*
* *Update the welcome email workflow's copy to match this draft I'm pasting in, then send me a test so I can review it before publishing.*
* *Create a recurring email that sends me a weekly usage digest every Monday at 9 AM America/New\_York. Include new signups, active users, and failed payments from the previous week.*
* *Send me a test of the welcome email draft so I can review it in my inbox before publishing.*
* *Publish the "trial ending" reminder workflow. Check for any warnings or errors before publishing.*
The key advantage is the **closed loop**: Claude can use context from your app, codebase, and data model to understand what you want, work back and forth with Dreamlit to fix issues, and only return a preview URL once the workflow matches your intent and is ready to review.
## Why use Dreamlit MCP with Claude Desktop?
Claude Desktop's strength is conversation: thinking out loud, shaping copy, iterating on tone. Dreamlit MCP turns those conversations into shipped workflows without bringing code, a CLI, or another browser tab into the loop.
* **Copy-first**: shape the message in conversation. Paste a draft, ask for tone changes, regenerate variants, then update the live workflow.
* **No code, no terminal**: founders, PMs, and operators can manage workflows entirely in chat.
* **Test before publishing**: ask Claude Desktop to send you a test through `send_workflow_test` so you see the real email or Slack message in your inbox or channel.
* **One conversation, both sides**: drafting a launch announcement and the email that goes with it can both happen in the same chat.
## Server URL
```txt theme={null}
https://mcp.dreamlit.ai/mcp
```
Dreamlit hosts this as a remote MCP server. Claude Desktop connects through Claude connectors, then Dreamlit asks you to approve workspace access.
## Quick install
In Claude Desktop, open **Settings** -> **Connectors**.
Add a custom connector with:
| Field | Value |
| ----- | ----------------------------- |
| Name | `Dreamlit` |
| URL | `https://mcp.dreamlit.ai/mcp` |
Click **Connect** and complete the Dreamlit browser authorization flow.
Start a new chat after authorization. If Dreamlit tools do not appear, restart Claude Desktop and open a new chat so Claude refreshes the connector tool list.
Ask Claude:
```txt theme={null}
Use Dreamlit to check my MCP status and list my workflows.
```
Use a Dreamlit personal access token when {clientName_1} cannot complete OAuth or when you want one project-scoped credential.
Open Dreamlit, go to **Project Settings** -> **Project Details** -> **MCP Access**, then click **Create token**.
Select the smallest set of permissions {clientName_1} needs.
Dreamlit only shows the token once. Store it securely.
Configure {clientSetupName_1} to send:
```txt theme={null}
Authorization: Bearer dlpt_your_token_here
```
```json theme={null}
{
"mcpServers": {
"dreamlit": {
"url": "https://mcp.dreamlit.ai/mcp",
"headers": {
"Authorization": "Bearer dlpt_your_token_here"
}
}
}
}
```
```json theme={null}
{
"servers": {
"dreamlit": {
"type": "http",
"url": "https://mcp.dreamlit.ai/mcp",
"headers": {
"Authorization": "Bearer dlpt_your_token_here"
}
}
}
}
```
Store the token in an environment variable:
```bash theme={null}
export DREAMLIT_MCP_TOKEN="dlpt_your_token_here"
```
Add the server:
```bash theme={null}
codex mcp add dreamlit --url https://mcp.dreamlit.ai/mcp \
--bearer-token-env-var DREAMLIT_MCP_TOKEN
```
If {clientSetupName_1} asks for an authentication method, choose **API key**, **Bearer token**, or **custom header**. Use `Authorization` as the header name and `Bearer dlpt_your_token_here` as the value.
If custom connectors are not visible in Claude Desktop, update Claude Desktop and confirm your Claude plan supports custom remote MCP connectors.
## What is MCP?
MCP is an open standard that lets {clientName_0} connect to external tools and data sources through one shared protocol. Instead of needing a custom Dreamlit integration, {clientName_0} connects to Dreamlit's MCP server and discovers the tools Dreamlit exposes.
For Dreamlit, MCP means {agentName_0} can work with notification workflows using product-level actions:
* Find the right workspace, project, or workflow
* Understand Dreamlit concepts and project setup state
* Create or update workflow drafts from plain-English prompts
* Return preview links so you can inspect the result in Dreamlit
* Prepare publishing and ask for explicit confirmation before anything goes live
Learn more in the official [Model Context Protocol documentation](https://modelcontextprotocol.io/docs/getting-started/intro).
## What can Dreamlit MCP do?
Dreamlit MCP is focused on workflow authoring and safe workflow operations. It is not a low-level database API.
| Capability | What it means |
| --------------------------- | --------------------------------------------------------------------------------------------------------------------- |
| Inspect setup | Check the approved workspace, project setup, Dreamlit page links, table and column summaries, and prompting guidance. |
| List projects and workflows | Find the project or workflow {agentName_0} should work on. |
| List brand styles | Find saved Brand Style ids and style summaries with pagination before asking Dreamlit to use a specific style. |
| Inspect workflows | Return normalized workflow structure and a Dreamlit preview URL before editing. |
| Create drafts | Ask Dreamlit to create a workflow draft from an outcome-oriented prompt. |
| Update drafts | Continue editing an existing workflow through the same draft history you see in the web app. |
| Test draft messages | Send a draft email or Slack message to yourself or a chosen recipient for review before publishing. |
| Query analytics | Read notification analytics, recipient engagement, and workflow run rows with filters and pagination. |
| Prepare publish | Validate a workflow and return a publish confirmation payload with a preview URL. |
| Confirm publish | Publish only after the user explicitly approves the prepared publish request. |
| Unpublish | Disable a live workflow when {clientName_0} has publish permission. |
| Hand off to the browser | Send you to Dreamlit when setup, unsupported edits, or manual review need the web app. |
## Prerequisites
Before connecting {clientSetupName_0}:
* Create a Dreamlit account at [app.dreamlit.ai](https://app.dreamlit.ai).
* Finish workspace and project setup in Dreamlit.
* Connect a [Supabase](/docs/configuration/data-sources/supabase) or [Postgres](/docs/configuration/data-sources/postgres) database.
* Configure any channels the workflows will need, such as [email domains](/docs/configuration/email/custom-domain), [Brand Styles](/docs/configuration/email/brand-styles), or [Slack](/docs/configuration/slack).
* Confirm {clientName_0} supports remote MCP over Streamable HTTP, or can send MCP requests through an HTTP bridge.
Dreamlit MCP works against existing Dreamlit workspaces and projects. If {clientName_0} says setup is required, open the Dreamlit link it returns and finish setup in the web app before reconnecting.
## How does authorization work?
OAuth is the best option when {clientName_0} supports remote server authentication. {clientName_0} connects to Dreamlit, Dreamlit opens a browser authorization screen, and you approve access to one Dreamlit workspace.
Use the server URL:
```txt theme={null}
https://mcp.dreamlit.ai/mcp
```
{clientName_0} should open a Dreamlit authorization page. Sign in, choose the workspace, review the requested scopes, and click **Allow access**.
Ask {agentName_0}:
> Check Dreamlit MCP status and list my projects.
If {clientName_0} only receives read access, reconnect Dreamlit and approve workflow drafting, publishing, or analytics when prompted. Dreamlit defaults empty OAuth scope requests to the supported v1 scopes.
## Permissions
Dreamlit MCP uses workflow and analytics scopes.
| Scope | Allows | Typical use |
| ------------------- | ---------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------- |
| `workflows:read` | `get_status`, `list_projects`, `list_workflows`, `list_brand_styles`, `get_workflow_and_preview_url` | Inspect setup, find workflows, Brand Styles, drafts, and published state. |
| `workflows:write` | `create_or_update_workflow`, `send_workflow_test` | Create or edit workflow drafts, and send draft message tests. |
| `workflows:publish` | `prepare_publish`, `confirm_publish`, `unpublish_workflow` | Validate, publish, schedule broadcasts, or unpublish workflows. |
| `analytics:read` | `get_analytics` | Query notification analytics, recipient engagement, and workflow runs. |
OAuth grants are scoped to a workspace. Personal access tokens are scoped to one project.
## Tools
{clientName_0} discovers these tools from the server.
| Tool | Required scope | Use it for |
| ------------------------------ | ------------------- | --------------------------------------------------------------------------------------------------------------------------------- |
| `get_status` | `workflows:read` | Learn how Dreamlit MCP works, inspect workspace/project setup, get Dreamlit page links, and retrieve prompting guidance. |
| `list_projects` | `workflows:read` | Find projects in the approved workspace. Project-scoped tokens only return their own project. |
| `list_workflows` | `workflows:read` | Find workflows in a project, optionally filtered by trigger type. |
| `list_brand_styles` | `workflows:read` | Find saved Brand Style ids and style summaries with pagination before asking Dreamlit to use a specific style. |
| `get_workflow_and_preview_url` | `workflows:read` | Inspect draft and published workflow structure before editing or publishing. |
| `get_analytics` | `analytics:read` | Query bounded analytics data with filters, sorting, and pagination. |
| `create_or_update_workflow` | `workflows:write` | Create or update a draft from a natural-language prompt. |
| `send_workflow_test` | `workflows:write` | Send the current draft email or Slack message to yourself or a chosen recipient for review. Doesn't publish or edit the workflow. |
| `prepare_publish` | `workflows:publish` | Validate the workflow and return the exact payload needed for confirmation. |
| `confirm_publish` | `workflows:publish` | Publish only after the user approves the prepared publish request. |
| `unpublish_workflow` | `workflows:publish` | Disable a live workflow. |
Dreamlit also exposes the `dreamlit://mcp/guide` resource. If {clientName_0} supports MCP resources, it can read the guide for prompting guidance, trigger types, unsubscribe guidance, and the recommended Dreamlit MCP flow.
## Recommended workflow
Ask {agentName_0} to work in this order:
Start with `get_status`. This gives {agentName_0} Dreamlit concepts, setup state, project context, and links back to relevant Dreamlit pages.
Use `list_projects` and `list_workflows` if the project or workflow is unclear.
Use `list_brand_styles` when you want a specific saved Brand Style applied.
Use `get_workflow_and_preview_url` before changing an existing workflow.
Use `create_or_update_workflow` with an outcome-oriented prompt.
Open the returned workflow URL to inspect the draft, preview output, and make manual adjustments if needed.
For email or Slack messages that need to look right before going live, ask {agentName_0} to send a test through `send_workflow_test`. Confirm the test before it sends, then review the real message in your inbox or Slack channel.
Use `prepare_publish` first. Only call `confirm_publish` after you explicitly approve the prepared publish request.
## How do I test a draft email or Slack message before publishing?
Use `send_workflow_test` to send the current draft message to yourself (or a chosen recipient) so you can review it in the real channel before going live. Tests don't publish, schedule, or change the workflow draft.
* Email tests default to the authenticated user's email address. Pass `testRecipientEmail` to send to a different inbox.
* Slack tests post to the channel configured for the draft message.
* Dreamlit returns a `confirmation_required` response describing the message and recipient. {agentName_0} only sends after calling `send_workflow_test` again with `confirmSend: true`.
* If a workflow has more than one testable message, Dreamlit returns a `clarification_required` response listing each message by label so you can choose one.
* Test sends count toward the same draft rate limit as workflow authoring.
Example prompt:
```txt theme={null}
Send me a test of the welcome email draft so I can review it
in my inbox before publishing.
```
## Prompting Dreamlit through MCP
Dreamlit works best when you describe the notification outcome, not the internal workflow graph.
Good prompts include:
* The event or schedule that should start the workflow
* The audience or recipient
* The message goal
* Data needed for targeting or personalization
* Timing, timezone, and business rules
* Whether unsubscribe should be enabled
* Tone or brand notes when they matter
Examples:
```txt theme={null}
Check Dreamlit status, then create a workflow for the main project:
when a new order row is inserted, send the customer an order confirmation
with the order number, total, and delivery estimate.
```
```txt theme={null}
List my workflows, inspect the welcome email workflow, and update it so
users who have not created a project after 3 days get a follow-up email.
Keep unsubscribe off because this is account onboarding.
```
```txt theme={null}
Create a repeating workflow that sends admins a weekly usage digest every
Monday at 9 AM America/New_York. Include new signups, active users, and
failed payments from the previous week.
```
```txt theme={null}
Prepare publish for the trial reminder workflow. Show me the preview URL
and warnings before confirming anything.
```
## Safety and control
Dreamlit MCP is designed so {agentName_0} can help with workflows without making surprise production changes.
* Draft changes stay draft-only until you publish.
* Test sends require explicit confirmation and don't publish, schedule, or edit the draft.
* Publishing is always a separate confirmation step with a Dreamlit preview link.
* If an action needs setup or manual review, Dreamlit sends you back to the web app.
* Query steps are read-only against your application data.
* Access is limited by the permissions you approve. Personal access tokens are project-scoped and can be revoked anytime.
## Troubleshooting
### Dreamlit authorization is required
Reconnect the MCP server and complete the browser authorization flow. If you are using a personal access token, confirm the token is still active and that {clientSetupName_0} is sending it as an `Authorization: Bearer ...` header.
### Dreamlit tools do not appear after authorization
Start a new chat or session in {clientSessionName_0}. If the tools still do not appear, restart {clientSetupName_0} or restart the Dreamlit MCP server entry. {clientName_0} can cache the MCP server and tool list for an open session.
### Additional Dreamlit permission is required
The current OAuth grant or personal access token does not include the required scope. Reconnect with the requested access, or create a token with the missing scope.
### Dreamlit says to choose a project
Your approved workspace has multiple projects and {agentName_0} did not specify one. Ask {agentName_0} to call `list_projects`, then retry with the right project.
### Dreamlit says setup is required
Open the returned Dreamlit setup URL, finish workspace and project setup, then reconnect {clientSetupName_0}.
### A workflow edit returns a browser handoff
Some changes still need the Dreamlit web app. Open the returned URL, review the draft, and continue from there.
### Publishing fails after a preview
The workflow may have changed since the publish preview. Ask {agentName_0} to run `prepare_publish` again, review the new preview and warnings, then confirm only if it still looks right.
### Tools are visible but calls time out
Workflow authoring can take longer than read-only calls because Dreamlit is planning and applying a real workflow draft. Retry once. If it keeps failing, open the returned Dreamlit URL if one is present, or contact [support](/docs/resources/getting-support).
## Testing with MCP Inspector
You can use the [MCP Inspector](https://modelcontextprotocol.io/docs/tools/inspector) to verify the server connection.
```bash theme={null}
npx @modelcontextprotocol/inspector
```
Select **Streamable HTTP** as the transport.
```txt theme={null}
https://mcp.dreamlit.ai/mcp
```
Use OAuth if the Inspector supports it, or add a Bearer header:
```txt theme={null}
Authorization: Bearer dlpt_your_token_here
```
Use **List tools** and call `get_status` to confirm the connection.
## Next steps
Connect your database and create your first workflow.
Learn how Dreamlit workflows are structured.
Reach the team if MCP setup blocks you.
***
Last validated: 2026-05-07