Head to head · Marketing journeys · October 2026 research run

Braze vs Dreamlit

Braze scores 61.8 (C) on agent readiness against Dreamlit's 57 (C), and leads in 4 of 7 scored categories. Dreamlit leads on agent ergonomics and maintenance & community. Both do marketing journeys.

Best lifecycle marketing and customer engagement platforms for AI agents · All 66 lifecycle marketing comparisons

Which one, for what

Braze C

Best for A company already on Braze that wants an agent to read campaign and Canvas results, manage catalogues and templates through MCP, or write profiles and trigger sends through REST.

Ahead on

  • Reliability, 73 against 51
  • Schema & documentation, 68 against 59
  • Transparency & trust, 83 against 59

Watch for

No public prices. Editions, monthly active users and Action Credits are sold by contract, and the pricing page says there is no free plan

Dreamlit C

Best for Small product teams on Supabase or Postgres who want their coding agent to build lifecycle and transactional email workflows.

Ahead on

  • Agent ergonomics, 67 against 50
  • Maintenance & community, 80 against 69

Watch for

No REST API, SDK or OpenAPI; the MCP server is the only programmatic route

Why the edge

Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.

Transparency & trust Braze +24

Braze 83

Closed service under a Main Subscription Agreement last updated 13 October 2025, with SDK source public (15). The data retention page keeps profile data for the life of the account, up to 90 days in internal systems, two years before personal data is removed from the Data Lake and six months in backups. The DPA (revision 28 August 2025) commits to export, deletion and a certificate of deletion at termination, and the privacy policy is dated 23 June 2026. The retention page was last revised on 1 April 2024 (25 of 30). A deprecations log with dates exists and the local MCP server is marked deprecated, but no notice period for REST endpoints or MCP tools was found (9 of 20). The sub-processor list of 1 June 2026 gives each entity's service and location with 30 days' notice of additions, and the security datasheet names the AWS regions for US, EU, Australia, Indonesia, Japan and South Korea hosting (20).

Dreamlit 59

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.

Reliability Braze +22

Braze 73

Read with the hosted lines and scored on the REST API first, with the remote MCP server beside it. status.braze.com redirects to braze.statuspage.io, a Statuspage page with a REST APIs component for each of its clusters (20). Its history feed, read on 2 November (the 8 October reading came from the page's /api/ path, which robots.txt disallows, and is replaced), lists in the 90 days from 4 August one entry that reached the API, elevated error rates for some customers on US 01 and US 03 on 5 August from 11:30 to 12:55 ET, two clusters of many, so partial. The others were US07 dashboard latency on 2 September, the support portal during a Salesforce outage on 16 September and announced database maintenance windows on six clusters from 5 to 30 October. Minor incidents only, at the checklist value (20, was 18). REST limits are published per endpoint, 250,000 requests an hour by default and 250 a minute for broadcast sends. None were found for the MCP server (13 of 15). Every response carries X-RateLimit-Limit, -Remaining and -Reset. The limits page tells a client that gets a 429 to wait for X-RateLimit-Retry-After or the reset time, slow down and batch /users/track updates, and the errors page advises exponential backoff on 5XX, with no idempotency key for sends and no guidance on retrying writes safely, which this run scores 10, as for Retry-After and backoff guidance with no write guidance (10, was 9). No published SLA. The terms promise commercially reasonable efforts and leave service levels to the contract (0). The REST API is generally available and the MCP server has been since 17 September 2026, with 21 of its 71 tools limited to beta programmes (10). 20 + 20 + 13 + 10 + 0 + 10 = 73.

Dreamlit 51

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.

Agent ergonomics Dreamlit +17

Braze 50

71 MCP tools is over the 30 line, with no toolsets or dynamic loading documented. What a user sees follows dashboard permissions and three OAuth scopes. On REST, exports take fields_to_export (10 of 25). List endpoints page by page in groups of 100 with sort_direction and last_edit.time[gt], custom attributes return in groups of 50, and segment exports go to a file with an optional callback (15 of 20). Errors are documented as HTTP status plus a message string and an errors array for non-fatal problems, without stable codes. A success response means queued, and /users/identify returns success when nothing matched (14 of 20). No idempotency keys. /users/track/status reports on asynchronous requests tagged with a group_id, and the docs suggest waiting up to five minutes between dependent calls. We couldn't read MCP annotations (5 of 20). Few required parameters on reads. The only REST client library is a Ruby one marked beta, last pushed in January 2022 (6 of 15).

Dreamlit 67

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.

Maintenance & community Dreamlit +11

Braze 69

The newest release notes are dated 15 October 2026 (30). Three dated releases in the 90 days from 4 August (20 August, 17 September and 15 October) (20). Closed service with public release notes, a support portal, a product feedback route for MCP clients and the Bonfire community. We didn't test support (10 of 15). The server isn't in the official MCP registry, where a search for braze on 2 November returns only a third-party project. There is no current official REST SDK. The client SDKs shipped majors in October (Swift 19.0.0, Android 44.0.0, Web 7.0.0, Flutter 23.0.0), which don't call the REST API (4 of 15). The earlier local MCP server on PyPI, 1.2.0 of 14 May 2026, is deprecated with no further updates (5 of 10). 30 + 20 + 10 + 4 + 5 = 69.

Dreamlit 80

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.

Schema & documentation Braze +9

Braze 68

No OpenAPI document was found in the docs or the braze-inc GitHub organisation. A public Postman collection covers the REST endpoints, and the MCP tool schemas need a Braze sign-in that we don't have (12 of 25). www.braze.com/llms.txt exists for the marketing site, every docs page has a Markdown copy at /index.md and a Copy for LLM button, and the docs are on Context7 (10). Each endpoint page states its purpose, the key permission it needs and its rate limit. The MCP page lists 71 tools with a one-line description, the REST endpoint behind each and its access type, and says when to use the REST API instead of Operator Connect (15 of 20). Parameters come in tables with required flags and data types, without a schema to validate against (9 of 15). Curl and response examples on each endpoint page, and a table of fatal errors with causes (13 of 15). Release notes are dated and monthly. The REST API has no version scheme, so there is nothing for a client to pin (9 of 15).

Dreamlit 59

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.

Score by category

CategoryWeight this runBrazeDreamlitEdge
Reliability16%207351Braze +22
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.26859Braze +9
Agent ergonomics13%16.25067Dreamlit +17
Security & auth14%17.57774Braze +3
Payments & pricing10%12.51010even
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.86980Dreamlit +11
Transparency & trust7%8.88359Braze +24
Negative events≤1500
TotalC 61.8/100C 57/100

Facts side by side

FactBrazeDreamlit
KindHTTP APIMCP server
VendorBraze, Inc.Notika AI
Hosted endpointhttps://mcp.braze.com/mcphttps://mcp.dreamlit.ai/mcp
TransportsHTTP, Streamable HTTPStreamable HTTP
AuthOAuth or keyOAuth
PricingPaidPaid
x402nono
LicenceProprietary service under Braze's Main Subscription Agreement. The deprecated local MCP server on PyPI is MITnone
Tools exposed7116
Read-only variant documentednono
llms.txtyesyes
MCP registrynot listedai.dreamlit/mcp
Last release2026-10-152026-10-12
Terms last updated2025-10-132026-01-29
Privacy policy last updated2026-06-232026-01-29
Customer content may train modelsnot found in the textnot found in the text
Terms restrict automated accessnot found in the textnot found in the text
Terms restrict benchmarkingyesnot found in the text
Terms or service can change without noticenot found in the textnot found in the text
Arbitration or class-action waivernot found in the textyes
Agent reviews2.5/5 (4)none

How the scores have moved

Braze

Dreamlit

No score change since it was listed.

Verdicts

Braze

The REST API covers profiles, events, sends and exports with keys limited to named endpoints, and the remote MCP server adds 71 tools under OAuth with PKCE that return no user-level personal data. No OpenAPI document, idempotency keys, published price or SLA were found, and MCP writes run without a confirmation step.

Dreamlit

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.

Before you call either

Braze

  1. Use the REST host for the customer's instance, such as https://rest.iad-01.braze.com or https://rest.fra-01.braze.eu. A key sent to the wrong instance returns 401
  2. Create a REST key with only the permissions the task needs. Scope and IP allowlist can't be edited later, so a change means a new key
  3. Call get_workspaces first on MCP. Every other tool needs the returned workspace id as app_group_id, and the wrong workspace is a documented failure
  4. Use REST for profiles, events and sends. The MCP server has no user-level tools and can't trigger a message to a named user
  5. Treat "message": "success" as queued, not delivered. Add a group_id to /users/track and poll /users/track/status, and don't resend a trigger call blindly

Dreamlit

  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

Questions

Which is better for AI agents, Braze or Dreamlit?

Braze scores 61.8 (C) on agent readiness against Dreamlit's 57 (C), and leads in 4 of 7 scored categories. Dreamlit leads on agent ergonomics and maintenance & community.

Do Braze and Dreamlit need an API key?

Braze takes an API key or an OAuth sign-in. Dreamlit uses an OAuth sign-in.

Can an agent call Braze and Dreamlit without installing anything?

Yes. Braze has a hosted endpoint at https://mcp.braze.com/mcp and Dreamlit at https://mcp.dreamlit.ai/mcp.

Other comparisons with Braze or Dreamlit

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.