# Dreamlit > Dreamlit is a lifecycle email service that runs notification workflows from a connected Supabase or Postgres database. AI agents build, test and publish those workflows and read their analytics through a hosted MCP server. - Canonical: https://www.anchorterminal.com/tools/dreamlit - Pricing: https://www.anchorterminal.com/tools/dreamlit#pricing - Reviews: https://www.anchorterminal.com/tools/dreamlit#reviews - Markdown: https://www.anchorterminal.com/tools/dreamlit.md (~7,350 tokens) - Slim: https://www.anchorterminal.com/tools/dreamlit.min.md (~1,530 tokens, same facts, less prose, for token-sensitive contexts) - JSON: https://www.anchorterminal.com/tools/dreamlit.json (this page as data, same URL with Accept: application/json) - Site index for agents: https://www.anchorterminal.com/llms.txt (the key docs and every listing in one file, at most 16 MB, about 4 million tokens: https://www.anchorterminal.com/llms-full.txt) - API: https://www.anchorterminal.com/api/v1/index.json - MCP: https://www.anchorterminal.com/mcp (the whole catalogue as tools, no key) - DNS: dig +short TXT dreamlit.grade.anchorterminal.com (the grade as a DNS TXT record, for a sandbox with no HTTP where names still resolve; also top., best.. and .vs.. under the zone, and the same under grade.letme.dev) - Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data) - Updated: 2026-11-07 ## Overview **Grade C · 57/100 · rank #809 of 1486 · #9 in Lifecycle marketing & customer engagement · not agent-ready · confidence medium** ## Assessment Scoped OAuth and a two-step prepare-then-confirm publish let an agent draft and test lifecycle workflows without sending anything live by mistake. There is no REST API or published rate limit, tool schemas aren't public outside a session, there's no free plan, and its security page and privacy policy disagree on retention. ## Facts | Field | Value | | --- | --- | | Vendor | Notika AI (https://dreamlit.ai) | | Kind | MCP server | | Category | Lifecycle marketing & customer engagement (https://www.anchorterminal.com/categories/lifecycle-marketing) | | Transport | Streamable HTTP | | Endpoint | `https://mcp.dreamlit.ai/mcp` | | Auth | OAuth · OAuth from the MCP client to one Dreamlit workspace, with scopes `workflows:read`, `workflows:write`, `workflows:publish` and `analytics:read`. Clients that can't do OAuth use a project-scoped personal access token (`dlpt_`) with chosen scopes, shown once, sent as a Bearer header. Accounts and database connections are set up in the web app first. | | Pricing | Paid ($20 / mo) · Pro $20 a month ($16 billed yearly) with 30,000 emails and 250 agent credits; Scale $99 ($79 yearly) with 100,000 emails; Enterprise custom. No free plan for new accounts. MCP calls carry no extra charge. Autopilot, a done-for-you service, is priced separately. | | x402 | No · No x402, MPP or L402 in llms.txt, pricing.md or the MCP docs (checked 2026-11-06). | | Licence | unknown | | Tools exposed | 16 | | MCP registry name | `ai.dreamlit/mcp` | | Source | https://github.com/dreamlit-ai/dreamlit-mcp | | Docs | https://dreamlit.ai/docs/resources/mcp-server | | llms.txt | https://dreamlit.ai/llms.txt | | Last release | 2026-10-12 | | Surface listed | The hosted MCP server at mcp.dreamlit.ai/mcp, read from dreamlit.ai docs, llms.txt, pricing.md, the security and legal pages, the status page, the changelog, the MCP registry and the dreamlit-ai/dreamlit-mcp metadata repository on 6 November 2026. No account was made and no session was opened | | MCP tools | 16 tools: get_status, list_projects, list_workflows, list_brand_styles, get_workflow_and_preview_url, get_analytics, get_lifecycle_report, get_recommendations, create_or_update_workflow, edit_workflow_steps, rename_workflow, move_workflow_to_folder, send_workflow_test, prepare_publish, confirm_publish, unpublish_workflow | | Data sources | Supabase or Postgres, connected in the web app with a dedicated database user; Shopify is also documented | | Sending | Email through AWS SES on Dreamlit's domain or the customer's, and Slack messages | | Category | Lifecycle-marketing, since it runs triggered and recurring lifecycle workflows and broadcasts with analytics rather than a sending API | | Legal entity | Notika AI, doing business as Dreamlit AI, per the terms and privacy policy of 29 January 2026 | | Capabilities | marketing.journeys, marketing.campaigns, marketing.events, email.send, email.templates, email.analytics | | Tags | hosted, closed-source, mcp, remote-mcp, mcp-registry, oauth, llms-txt, approvals, status-page, supabase, postgres | | JSON | https://www.anchorterminal.com/api/v1/tools/dreamlit.json | ## Score breakdown (methodology v0.7, October 2026 research run) Assessed 2026-11-06 from public evidence against the published checklist (https://www.anchorterminal.com/benchmark/#checklist). Confidence: medium. Performance and Task success pending (no score, not in the total); the total is Σ(score × weight) ÷ 80 over the 7 assessed categories. "This run" is each category's share of the 100 points. | Category | Weight | This run | Score (0–100) | Points | | --- | --- | --- | --- | --- | | Reliability | 16% | 20 | 51 | 10.2 | | Performance | 10% | pending | pending | n/a | | Schema & documentation | 13% | 16.2 | 59 | 9.6 | | Agent ergonomics | 13% | 16.2 | 67 | 10.9 | | Security & auth | 14% | 17.5 | 74 | 12.9 | | Payments & pricing | 10% | 12.5 | 10 | 1.2 | | Task success | 10% | pending | pending | n/a | | Maintenance & community | 7% | 8.8 | 80 | 7.0 | | Transparency & trust (editorial 42, provenance 75) | 7% | 8.8 | 59 | 5.2 | | Negative events | up to −15 | up to −15 | none recorded | 0 | | **Total** | | | | **57 → C** | ### Why each score - Reliability 51 (checked 2026-11-06): Graded with the hosted lines. A Better Stack status page at status.dreamlit.ai with 90 days of history for the Web App and the Workflow Engine, but no component for the MCP server (16 of 20). The record shows 100% for the web app and 99.992% for the workflow engine over 90 days, about ten minutes, with no written incidents (25 of 30). No rate limits found in the MCP or pricing docs (0). No 429, retry or idempotency guidance found (0). Scale includes dedicated support with an SLA and Enterprise has custom SLAs, but no published availability commitment (0). The MCP server, introduced on 5 May 2026, carries no beta label (10). Total 51. - Performance: Pending. Latency is measured per call by our probes, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until the first probe window closes. - Schema & documentation 59 (checked 2026-11-06): The registry entry and the dreamlit-ai/dreamlit-mcp repository carry metadata only, so tool JSON Schemas are readable only inside a session; the docs give each tool's purpose and required scope (5 of 25). llms.txt, pricing.md and Markdown copies of docs pages (10). Tool descriptions say when to use each, such as `edit_workflow_steps` for exact edits without AI, and the publish pair's order (16 of 20). Parameter types aren't published beyond names such as `includeEmailHtml` and `startNewChat` (5 of 15). Example prompts and a troubleshooting section for each documented error state (10 of 15). A dated changelog; server version 0.1.0 in the registry (13 of 15). Total 59. - Agent ergonomics 67 (checked 2026-11-06): 16 tools, the 11 to 30 band; tools follow the granted scopes, so a read-only grant sees fewer (20 of 25). Analytics take filters, sorting and pagination, and brand styles paginate (18 of 20). The docs describe the errors an agent will meet, such as authorization required, choose a project and browser hand-off, without codes (12 of 20). Publishing is prepare then confirm, and tests don't publish; no idempotency or annotations documented (10 of 20). Empty scope requests default to the v1 scopes and `get_status` gives a first call; no SDK or REST route (7 of 15). Total 67. - Security & auth 74 (checked 2026-11-06): OAuth to one workspace with four scopes, and project-scoped personal access tokens with chosen scopes, shown once (30). A read-only grant is possible, publishing needs its own scope, `confirm_publish` runs only after the user approves the prepared payload, and a dedicated least-privilege database user reads the customer's data (20). The docs warn that AI clients can be tricked by untrusted prompts and tell users to review edit, publish and unpublish calls (8 of 15). The security page lists access logs for database operations and for the platform, and analytics expose run rows; no customer-facing log of MCP calls was described (8 of 15). The security page claims penetration testing and a bug bounty programme without a link, SOC 2 is coming soon, no security.txt (404), and the MCP repository's SECURITY.md routes reports to support (8 of 20). Total 74. - Payments & pricing 10 (checked 2026-11-06): No x402, MPP or L402 (0). Plan prices with included emails are public in pricing.md, no per-email overage price (10 of 20). No free plan for new accounts (0). Signup, database connection and payment happen in the web app (0). Total 10. - Task success: Pending. Task success needs the category task suites run through each tool, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until then. A data provider's data-quality score is published on its listing now and becomes half of this category when it's scored. - Maintenance & community 80 (checked 2026-11-06): The latest changelog entry is 12 October 2026, custom repeating schedules (30). Eight dated entries between 10 August and 12 October (20). Priority support on Pro, dedicated support on Scale and a public changelog (10 of 15). ai.dreamlit/mcp is in the official MCP registry under its domain namespace (15). The metadata repository has validate and publish workflows; there's no package to check (5 of 10). Total 80. - Transparency & trust 59 (checked 2026-11-06): A closed service under terms that name Notika AI (d/b/a Dreamlit AI) (15 of 30). The privacy policy keeps workflow execution history and delivery events for up to a year, while the security docs say Dreamlit retains no copy of customer data and cleans up after processing, which don't agree (15 of 30). No deprecation policy or dated notices found (0). The privacy policy points to a current subprocessor list and SCCs in a DPA, and names the United States and other countries as locations (12 of 20). Total 42. Fix list, everything this grade says the listing lacks, the biggest gain first (15 items). What it covers is at https://www.anchorterminal.com/fixes/dreamlit.md (JSON https://www.anchorterminal.com/fixes/dreamlit.json). The whole list for a coding agent comes from `POST https://www.anchorterminal.com/api/v1/fix-list` with `{"listing": "dreamlit", "plan": "read"}`, free while the beta runs ### What we couldn't check - unchecked: the MCP tools' input schemas and annotations, which are only available inside an MCP session - The security page's no-retention claim and the privacy policy's one-year retention disagree - The bug bounty programme claimed on the security page wasn't found - RDAP gave no registration date for dreamlit.ai ### Sources - MCP server docs: (seen 2026-11-06) - llms.txt: (seen 2026-11-06) - pricing: (seen 2026-11-06) - security docs: (seen 2026-11-06) - status page: (seen 2026-11-06) - changelog: (seen 2026-11-06) - terms: (seen 2026-11-06) - privacy policy: (seen 2026-11-06) - about page: (seen 2026-11-06) - MCP metadata repository: (seen 2026-11-06) - official MCP registry: (seen 2026-11-06) ## Score history Every move of a score since the listing was graded, newest first, with its cause. A score can't move without an entry here. JSON: https://www.anchorterminal.com/api/v1/tools/dreamlit/history.json - 2026-11-06: graded 57 C (methodology 0.7) ## Who's behind it (provenance 75/100, checked 2026-11-06) | Check | Finding | Points | | --- | --- | --- | | Legal entity named | Notika AI (d/b/a Dreamlit AI) | 20/20 | | Domain age | dreamlit.ai, no registry record we could read | 0/15 | | Endpoint on the vendor's domain | mcp.dreamlit.ai | 15/15 | | Terms of service | read, states 4 of the 7 things a reader expects | 7.4/10 | | Privacy policy | read, states 7 of the 8 things a reader expects | 9.3/10 | | Status page | status.dreamlit.ai | 10/10 | | Changelog | published | 10/10 | | security.txt | not found | 0/10 | | People named | 2 named with their role, 2 with a public profile | 10/10 | | Support route | a support address, help pages | 5/5 | The terms and privacy policy, both last updated 29 January 2026, name Notika AI (d/b/a Dreamlit AI). dreamlit.ai/robots.txt allows all paths with Content-Signal ai-input=yes. The terms contain no clause on automated access to the website that we found. RDAP for dreamlit.ai returned a transfer event (8 June 2025) but no registration date. /.well-known/security.txt returns 404. The security page claims penetration testing and a bug bounty programme without a link; the MCP repository's SECURITY.md routes reports to the support address. The privacy policy says subprocessors are listed and SCCs are offered in a DPA at dreamlit.ai/dpa. ### Terms and privacy, as read A reading by a fixed set of rules, each answered with the vendor's own sentence. Not legal advice. **Terms of service** (https://dreamlit.ai/terms-of-service), read 2026-11-06, dated 2026-01-29, states 4 of the 7 things a reader expects. - To know. Requires arbitration or waives class actions. "DISPUTES RELATED TO THESE TERMS OR THE SERVICE MUST BE RESOLVED THROUGH BINDING ARBITRATION." - Gives the date it was last updated. Last updated 2026-01-29. - Not found in the text. Names the governing law or courts. - States a limit on its liability. Rules out indirect and consequential losses, with no cap named in this sentence. - Not found in the text. Says how the agreement or account can be ended. - Says how changes to the terms are announced. Changes are posted, with no other notice named. - Not found in the text. Refers to a service level or uptime commitment. **Privacy policy** (https://dreamlit.ai/privacy-policy), read 2026-11-06, dated 2026-01-29, states 7 of the 8 things a reader expects. - Gives the date it was last updated. Last updated 2026-01-29. - Not found in the text. Says how long data is kept. - Gives a privacy contact. support@dreamlit.ai. - Says where data is transferred or stored. Relies on standard contractual clauses. ## Humans behind the project (researched 2026-11-06 from public pages, not part of the grade) ### Key people - Ajay Sohmshetty, Co-founder and CEO. LinkedIn: https://www.linkedin.com/in/ajaysohmshetty/. X: https://x.com/AjaySohmshetty - Andrew Kim, Co-founder and CTO. LinkedIn: https://www.linkedin.com/in/andrewk17/ - Note: The about page names the two founders with their roles and links their LinkedIn accounts, and Ajay's X account. Ajay was previously co-founder and CTO of Harmonic AI and an engineer at Google; Andrew built partner integrations at Netflix. The terms name Notika AI (d/b/a Dreamlit AI). The about page shows a 'Backed by' row of logos; no round, amount or date was found on dreamlit.ai. Cloudflare Workers Launchpad is shown in the same row but is a startup programme, so it isn't listed as an investor. On 6 November 2026 the dreamlit.ai sitemap (26 pages) and all 13 blog posts were read for a funding announcement and a web search was run; no round amount, total raised or valuation is stated on Dreamlit's pages or in a reputable report, so totalRaised and valuation are left out. - Notika AI: LinkedIn https://www.linkedin.com/company/dreamlit-ai X https://x.com/DreamlitAI GitHub https://github.com/dreamlit-ai ### Ownership and investors - Backed by: Abstraction Capital, Saxecap, Kanosei, Forum Ventures, Austin Nasso ### Getting support - Support email: support@dreamlit.ai - Help: https://dreamlit.ai/docs/resources/getting-support - Help: https://status.dreamlit.ai/ - Sources: https://dreamlit.ai/about, https://dreamlit.ai/terms-of-service, https://dreamlit.ai/pricing.md ## Live (updated 2026-11-07 18:20 UTC) - Right now: up, HTTP 200, 209 ms, checked 2026-11-07 18:20 UTC (mcp-initialize on `https://mcp.dreamlit.ai/mcp`) - Uptime 24h 100.0% (200 probes) · 30 days 100.0% (200 probes) · p50 155 ms · p95 303 ms - Vendor status page: not read, no machine-readable status found - mcp-registry `ai.dreamlit/mcp` 0.1.0 - security.txt: none - Watching changelog - Watching privacy - Watching terms - Tools it lists (16, about 69,715 tokens of context, `tools/list` without credentials over MCP 2025-11-25, checked 2026-11-07 01:43 UTC): - `get_status` (read-only): Read-only. Use first when the agent needs Dreamlit product guidance, prompting guidance, approved workspace context, project setup, schema hints, workflow… - `create_or_update_workflow` (writes): Creates a new Dreamlit workflow draft or updates an existing draft from an outcome-oriented natural-language prompt. Use after get_status; use… - `edit_workflow_steps` (writes): Applies up to 5 exact edits to existing steps in a workflow draft, instantly and without AI: email subject, preview text, HTML, sender, reply-to, and… - `rename_workflow` (writes): Use when the user asks to rename an existing Dreamlit workflow. Side effect: changes only the workflow name; the draft, published version, and live triggers… - `move_workflow_to_folder` (writes): Use when the user asks to put a workflow or broadcast in a folder, move it to another folder, or take it out of a folder. Folders are per list: the Published… - `list_projects` (read-only): Read-only. Use when the target project is unknown or the user names a project instead of providing an id. Returns accessible Dreamlit projects in the approved… - `list_workflows` (read-only): Read-only. Use to find workflows in a project by name, description, or trigger type before inspection or editing. Trigger filters include database, auth email,… - `list_brand_styles` (read-only): Read-only. Use when the user wants to inspect saved project brand styles for generated email drafts. Returns paginated project brand style summaries, ids,… - `get_workflow_and_preview_url` (read-only): Read-only. Use before editing, verifying, or preparing publish for an existing workflow. Returns normalized draft and published workflow structure, liveStatus,… - `get_analytics` (read-only): Read-only. Use get_analytics to query raw notification analytics: email and Slack sends and deliveries, email opens, clicks and bounces, overview metrics,… - `get_lifecycle_report` (writes): Side effect: creates a preparation request when no report is ready or refresh is true and the latest report became ready more than 24 hours ago; repeat calls… - `get_recommendations` (writes): Side effect: creates a preparation request when no report is ready or refresh is true and the latest report became ready more than 24 hours ago; repeat calls… - `send_workflow_test` (writes): Side effect when confirmSend is true: sends one current draft email or Slack message for review, but does not publish, schedule, or edit the workflow. Use… - `prepare_publish` (read-only): Read-only validation step before publishing. Use after the user asks to publish and after inspecting the workflow if needed. Returns validation status, publish… - `confirm_publish` (writes): Use only after explicit user confirmation and a prior prepare_publish result to publish or schedule a Dreamlit workflow. Side effect: installs live… - `unpublish_workflow` (writes): Use after explicit user intent to unpublish a Dreamlit workflow. Side effect: disables live triggers or schedules so no new runs start. Runs already in… - How its tools read to an agent (0 errors, 18 warnings, 0 notes, about 69,715 tokens; rules at https://www.anchorterminal.com/check.md; not part of the score): - warn TC18 prepare_publish: readOnlyHint is true but the name says "publish" - warn TC22 confirm_publish: the definition is about 4,360 tokens - warn TC22 create_or_update_workflow: the definition is about 4,866 tokens - warn TC22 edit_workflow_steps: the definition is about 4,839 tokens - warn TC22 get_analytics: the definition is about 5,580 tokens - warn TC22 get_lifecycle_report: the definition is about 4,217 tokens - warn TC22 get_recommendations: the definition is about 4,188 tokens - warn TC22 get_status: the definition is about 4,209 tokens - warn TC22 get_workflow_and_preview_url: the definition is about 4,164 tokens - warn TC22 list_brand_styles: the definition is about 4,071 tokens - warn TC22 list_projects: the definition is about 3,956 tokens - warn TC22 list_workflows: the definition is about 4,289 tokens - warn TC22 move_workflow_to_folder: the definition is about 4,148 tokens - warn TC22 prepare_publish: the definition is about 3,999 tokens - warn TC22 rename_workflow: the definition is about 4,022 tokens - warn TC22 send_workflow_test: the definition is about 4,420 tokens - warn TC22 unpublish_workflow: the definition is about 4,231 tokens - warn TC23 server: 16 tools, about 69,559 tokens of definitions - Always current: https://www.anchorterminal.com/api/v1/live/dreamlit.json ## Probe metrics Not measured yet. Our benchmark probes haven't run, so there's no availability, latency or error rate from a run and Performance is pending. Live uptime, where we poll the endpoint, is under Live and doesn't change the score. ## Prices | Item | Price | Unit | Note | | --- | --- | --- | --- | | Pro | $20 | per month (plan) | 30,000 emails a month, 250 agent credits; $16 billed yearly | | Scale | $99 | per month (plan) | 100,000 emails a month, 500 agent credits; $79 billed yearly | Across all listings: https://www.anchorterminal.com/prices/index.md ## Strengths - Separate OAuth scopes for reading, drafting, publishing and analytics, and project-scoped tokens - Nothing goes live without `prepare_publish` followed by an approved `confirm_publish` - `send_workflow_test` sends a draft to the user or a chosen address without publishing - Better Stack status page with 90 days of history for the web app and workflow engine - Dated changelog with eight entries between 10 August and 12 October 2026 ## Weaknesses - No REST API, SDK or OpenAPI; the MCP server is the only programmatic route - No rate limits, 429 guidance or idempotency documented for MCP calls - No free plan for new accounts; Pro starts at $20 a month - The status page has no component for the MCP server - The security page says no copy of data is kept, while the privacy policy keeps workflow history and delivery events for up to a year ## Before you call it (notes for agents) 1. Call `get_status` first to see the workspace, project setup state and prompting guidance 2. Use `send_workflow_test` to the user before `prepare_publish`, and call `confirm_publish` only after the user approves the returned payload 3. Request `workflows:read` and `analytics:read` only when the task is reporting, so the grant can't publish 4. Expect a browser hand-off link when setup or an unsupported edit needs the web app, and pass it to the user ## Connect Claude Code: ```bash claude mcp add --transport http dreamlit https://mcp.dreamlit.ai/mcp ``` MCP client configuration: ```json { "mcpServers": { "dreamlit": { "url": "https://mcp.dreamlit.ai/mcp" } } } ``` Through letme: https://letme.dev/dreamlit. letme answers with the pick and how to call it direct. How it works: https://www.anchorterminal.com/letme/index.md ## Similar tools Ranked by shared capabilities, then score. Same-category tools with no shared capability key are listed last. | Tool | Grade | Score | Rank | Shared capabilities | x402 | Markdown | | --- | --- | --- | --- | --- | --- | --- | | Customer.io | BB | 75.6 | 57 | marketing.events, marketing.campaigns, marketing.journeys, email.send, email.templates | no | https://www.anchorterminal.com/tools/customer-io.md | | Nitrosend | B | 69.4 | 248 | marketing.events, marketing.campaigns, marketing.journeys, email.send, email.templates | no | https://www.anchorterminal.com/tools/nitrosend.md | | Sequenzy | B | 63.7 | 504 | marketing.events, marketing.campaigns, marketing.journeys, email.send, email.templates | no | https://www.anchorterminal.com/tools/sequenzy.md | | AhaSend API + MCP | BB | 75.4 | 62 | email.send, email.templates, email.analytics, marketing.campaigns | no | https://www.anchorterminal.com/tools/ahasend.md | | Klaviyo API + MCP | BB | 73.8 | 97 | marketing.events, marketing.campaigns, marketing.journeys, email.templates | no | https://www.anchorterminal.com/tools/klaviyo.md | | Omnisend | B | 65.8 | 398 | marketing.events, marketing.campaigns, marketing.journeys, email.templates | no | https://www.anchorterminal.com/tools/omnisend.md | ## Panel reviews (0) Reviewed by the Anchor panel (https://www.anchorterminal.com/reviewers/index.md): . Desk reviews, written from public documentation, pricing, terms, source and status history on 1 October 2026. No calls made. For a desk review, the outcome says whether the reviewer's questions could be answered from public material: success, partial or failure. How reviews work: https://www.anchorterminal.com/reviews/how-it-works.md ## Notable - Publishing is two calls: `prepare_publish` validates and returns a confirmation payload with a preview URL, and `confirm_publish` runs only after the user approves (source: ) - Four OAuth scopes separate reading, drafting, publishing and analytics, and personal access tokens are limited to one project (source: ) - Workflows read from the customer's own Supabase or Postgres through a dedicated `dreamlit_app` database user (source: ) - Listed in the official MCP registry as ai.dreamlit/mcp since 7 May 2026, under its domain namespace (source: ) - The security page says Dreamlit retains no copy of customer data, while the privacy policy says it keeps workflow history and delivery events for up to a year (source: ) - #9 of 12 in Best lifecycle marketing and customer engagement platforms for AI agents: https://www.anchorterminal.com/best/lifecycle-marketing/index.md - All 66 lifecycle marketing comparisons: https://www.anchorterminal.com/compare/lifecycle-marketing/index.md ## Compare - [ActiveCampaign vs Dreamlit](https://www.anchorterminal.com/compare/activecampaign-vs-dreamlit.md): E 43.9 vs C 57 - [Braze vs Dreamlit](https://www.anchorterminal.com/compare/braze-vs-dreamlit.md): C 61.8 vs C 57 - [Customer.io vs Dreamlit](https://www.anchorterminal.com/compare/customer-io-vs-dreamlit.md): BB 75.6 vs C 57 - [Dreamlit vs Iterable](https://www.anchorterminal.com/compare/dreamlit-vs-iterable.md): C 57 vs C 56.3 - [Dreamlit vs Klaviyo API + MCP](https://www.anchorterminal.com/compare/dreamlit-vs-klaviyo.md): C 57 vs BB 73.8 - [Dreamlit vs Mailchimp Marketing API](https://www.anchorterminal.com/compare/dreamlit-vs-mailchimp-marketing.md): C 57 vs C 60.2 - [Dreamlit vs MoEngage](https://www.anchorterminal.com/compare/dreamlit-vs-moengage.md): C 57 vs B 65.7 - [Dreamlit vs Nitrosend](https://www.anchorterminal.com/compare/dreamlit-vs-nitrosend.md): C 57 vs B 69.4 - [Dreamlit vs Omnisend](https://www.anchorterminal.com/compare/dreamlit-vs-omnisend.md): C 57 vs B 65.8 - [Dreamlit vs Sequenzy](https://www.anchorterminal.com/compare/dreamlit-vs-sequenzy.md): C 57 vs B 63.7 - [CleverTap vs Dreamlit](https://www.anchorterminal.com/compare/clevertap-vs-dreamlit.md): D 50.4 vs C 57 ## Verify this listing For the vendor. The badge or a plain link to this page verifies the listing, from a page on dreamlit.ai or one of its subdomains, or the README at the root of github.com/dreamlit-ai/dreamlit-mcp. It shows the listing is the vendor's and that the vendor knows it's here, and it never changes a grade, rank or review. The vendor sends the page's address to `POST https://www.anchorterminal.com/api/v1/verify` as `{"slug": "dreamlit", "url": "…"}`, or calls the `verify_listing` tool at https://www.anchorterminal.com/mcp. We fetch the page once, then again every week; two failed checks in a row and the verification lapses, and a later pass restores it. What we check: https://www.anchorterminal.com/builders/index.md#verify HTML badge: ```html Dreamlit on Anchor Terminal ``` Markdown badge, for a README: ```markdown [![Dreamlit on Anchor Terminal](https://www.anchorterminal.com/badges/dreamlit.svg)](https://www.anchorterminal.com/tools/dreamlit) ``` Plain link: ```html Dreamlit on Anchor Terminal ``` ## Share this listing For the vendor. Sharing assets for social media, two PNGs of 1200 × 630 that say Dreamlit is listed on Anchor Terminal, with the vendor's logo and this page's address and no grade or score. - Dark: https://www.anchorterminal.com/assets/share/dreamlit-dark.png - Light: https://www.anchorterminal.com/assets/share/dreamlit-light.png --- Query this catalogue directly over MCP: https://www.anchorterminal.com/mcp (Streamable HTTP, no key). How: https://www.anchorterminal.com/agents/#mcp