# CleverTap vs Dreamlit

> Dreamlit scores 57 (C) to CleverTap's 50.4 (D) for marketing events. Prices, MCP, x402, uptime and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/clevertap-vs-dreamlit
- Markdown: https://www.anchorterminal.com/compare/clevertap-vs-dreamlit.md (~4,600 tokens)
- 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 <slug>.grade.anchorterminal.com (the grade as a DNS TXT record, for a sandbox with no HTTP where names still resolve; also top., best.<category>. and <a>.vs.<b>. 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

Dreamlit scores 57 (C) on agent readiness against CleverTap's 50.4 (D), and leads in 5 of 7 scored categories. CleverTap leads on payments & pricing and transparency & trust. Both do marketing events.

- CleverTap: grade D, 50.4/100, rank #1066 of 1510. Markdown https://www.anchorterminal.com/tools/clevertap.md · JSON https://www.anchorterminal.com/api/v1/tools/clevertap.json
- Dreamlit: grade C, 57/100, rank #813 of 1510. Markdown https://www.anchorterminal.com/tools/dreamlit.md · JSON https://www.anchorterminal.com/api/v1/tools/dreamlit.json
- 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

## Which one, for what

### CleverTap (D)

Good for: A team already on CleverTap that wants an agent to load profiles and events, read them back, create or stop API campaigns and pull campaign reports.

Ahead on:
- Payments & pricing, 25 against 10
- Transparency & trust, 66 against 59

Watch for: No OpenAPI file was found. The contract is prose tables plus a Postman collection published as a zip on GitHub

### Dreamlit (C)

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

Ahead on:
- Reliability, 51 against 37
- Agent ergonomics, 67 against 53
- Security & auth, 74 against 56
- Maintenance & community, 80 against 73

Also in its favour:
- A hosted endpoint, with nothing to install

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


## Why the edge

### Security & auth: Dreamlit +18

- CleverTap (56): Up to 100 named account passcodes with optional expiry, shown once and deletable, or per-user passcodes an admin can reset and revoke. No scopes or OAuth were found, and the secret travels in a header (22). No read-only passcode was found. The docs say campaigns created via API are not restricted by RBAC settings. A dashboard approval workflow exists, and `draft` lets an API caller save without sending (6). The API returns customer-supplied profile and event content, and no guidance for agents reading it was found (3). Audit logs record API key creation and revocation and API access logs, with CSV download and a daily export for SIEM tools (13). ISO/IEC 27001, ISO/IEC 27017, SOC 2 Type II, CSA STAR Level 2 and HIPAA are named on the pricing and security pages. The pricing page, re-read on 4 November, still names ISO/IEC 27001, ISO/IEC 27017, SOC 2 Type II and CSA STAR Level 2 and says reports are on the trust portal. clevertap.com/.well-known/security.txt answered 404 on 4 November, no disclosure policy or bug bounty was found, and the trust portal answered 403 on 9 October (12). Total 56.
- Dreamlit (74): 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: CleverTap +15

- CleverTap (25): No x402, MPP or L402 (0). The Core plan's entry price is public at 85 dollars a month, re-read on 4 November, for up to 5,000 monthly active users. The larger tiers were not readable and Pro and Ultimate need a demo, so this is plan-only pricing (10). Core has a 30-day free trial. The account docs say billing details are needed before the last seven days, so 5 of the 20 points come off (15). A person signs up in a browser and creates the passcode in the dashboard (0). Total 25.
- Dreamlit (10): 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.

### Reliability: Dreamlit +14

- CleverTap (37): Graded on the REST API, with the hosted lines. No status page is linked from the home page, the pricing, security, terms or privacy pages or either docs index, re-read on 4 November, and no address was guessed (0). With no page there is no readable incident history, which this run scores 5 (from 0). Concurrent request limits are published with numbers for 23 API groups (15 on uploads, 3 elsewhere) with 1,000 records a call, re-read on 4 November, but the Create Campaign page gives 3 requests a second, per the 9 October check, and the Get User Profiles page, re-read on 4 November, says limits are account-specific (13). HTTP 429 is in the errors table, re-read on 4 November, and the Get User Profiles page asks for exponential backoff of 1 to 16 seconds with at most 5 retries and says a cursor survives a timeout. That page, re-read on 4 November (updated 3 July 2026), still gives the backoff schedule for 429, 500 and 503. No Retry-After header and no idempotency key or safe-retry guidance for writes were found, so this run's value for backoff guidance alone applies (10, from 8). The terms, re-read on 4 November, leave service levels to each order, and no SLA is published (0). The API is generally available, with the External Trigger API in Public Beta, per the 9 October check (9). 0+5+13+10+0+9 = 37.
- 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 +14

- CleverTap (53): Get User Profiles takes `batch_size` and `app`, `events` and `profile` flags, and reports take date ranges. No field selection was found (12). Profiles and events page by cursor with `next_cursor`, valid for 4 days. Get Campaigns filters only by date range and lists only API-created campaigns (14). Errors use `status`, `error` and `code` with per-API code lists and per-record results on uploads, but Get User Profiles returns some throttling errors with HTTP 200 (13). No idempotency key was found. `dryRun=1` validates uploads, `estimate_only` and `draft` hold a campaign back, and stopping a stopped campaign returns success (8). One current server library, Node.js `clevertap` 1.3.1. The linked Python wrapper was last changed in 2017 (6). Total 53.
- 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 +7

- CleverTap (73): The Web SDK tagged v3.1.2 on 2 November 2026, and the iOS SDK 7.9.1 on 30 October (30). Since 6 August the Web SDK has tagged v3.0.0, v3.0.1, v3.0.2, v3.0.3, v3.1.0, v3.1.1 and v3.1.2, the Android SDK core 8.4.1, push templates 2.6.0 and core 8.5.0 with templates 2.7.0, and the iOS SDK 7.8.1, 7.8.2, 7.9.0 and 7.9.1, read from clones on 4 November (20). Public monthly SDK changelogs (September 2026 is the newest page) and product release notes, with support through a dashboard ticket. GitHub issue handling was not read (9). Client SDKs are current. The Node.js server library's last release is still 1.3.1 (7 July 2026), and the Python wrapper dates from 2017 (10). The Node.js library ships a Travis CI file and depends on node-fetch 2. Its CI state was not read (4). 30+20+9+10+4 = 73.
- 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.

### Transparency & trust: CleverTap +7

- CleverTap (66): Closed service with public Terms of Service, last updated 30 April 2021 and re-read on 4 November, that name WizRocket Inc. and state the restrictions plainly (15). The privacy policy of 9 April 2026, unchanged on 4 November, covers CleverTap as processor, with deletion within 60 days of termination, and the docs give three years' default retention on Core and backup deletion within 60 days. The Data Processing Addendum the policy cites was not found in public (22). No API deprecation policy was found. The only dated notice read is the 2021 end of TLS 1.1 (3). Six hosting regions are documented and AWS is named as host. The sub-processor list sits on the trust portal, which answered 403 and was not read (10). Total 50.
- 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.

## Score by category

| Category | Weight | CleverTap | Dreamlit | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 37 | 51 | Dreamlit +14 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 57 | 59 | Dreamlit +2 |
| Agent ergonomics | 13% (16.2 this run) | 53 | 67 | Dreamlit +14 |
| Security & auth | 14% (17.5 this run) | 56 | 74 | Dreamlit +18 |
| Payments & pricing | 10% (12.5 this run) | 25 | 10 | CleverTap +15 |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 73 | 80 | Dreamlit +7 |
| Transparency & trust | 7% (8.8 this run) | 66 | 59 | CleverTap +7 |
| Negative events | ≤15 | 0 | 0 | |
| **Total** | | **50.4 · D** | **57 · C** | |

## Facts side by side

| Fact | CleverTap | Dreamlit |
| --- | --- | --- |
| Kind | HTTP API | MCP server |
| Vendor | WizRocket Inc. | Notika AI |
| Hosted endpoint | no (local only) | `https://mcp.dreamlit.ai/mcp` |
| Transports | HTTP | Streamable HTTP |
| Auth | API key | OAuth |
| Pricing | Paid | Paid |
| x402 | no | no |
| Licence | Proprietary service under CleverTap's Terms of Service. The Node.js API library on GitHub is MIT | none |
| Tools exposed | none | 16 |
| Read-only variant documented | no | no |
| llms.txt | yes | yes |
| MCP registry | not listed | `ai.dreamlit/mcp` |
| Last release | 2026-10-01 | 2026-10-12 |
| Terms last updated | 2021-04-30 | 2026-01-29 |
| Privacy policy last updated | 2026-04-09 | 2026-01-29 |
| Customer content may train models | not found in the text | not found in the text |
| Terms restrict automated access | not found in the text | not found in the text |
| Terms restrict benchmarking | yes | not found in the text |
| Terms or service can change without notice | not found in the text | not found in the text |
| Arbitration or class-action waiver | not found in the text | yes |
| Popularity | 3k npm/wk | none |

## How the scores have moved

### CleverTap

- +1.4 on 4 November 2026: correction
- +0.2 on 27 October 2026: checklist

### Dreamlit

No score change since it was listed.

## Verdicts

**CleverTap.** CleverTap's REST API uploads and reads profiles and events, creates and stops campaigns and reports results, with Markdown docs, numeric concurrency limits and a 30-day Core trial. No OpenAPI file or public status page was found, passcodes carry no scopes, and the docs say campaigns created through the API are not restricted by role-based access control.

**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

### CleverTap

1. Call the host for the account's region, such as `in1.api.clevertap.com` or `us1.api.clevertap.com`. `api.clevertap.com` is the Europe region
2. Send `X-CleverTap-Account-Id` and `X-CleverTap-Passcode` headers on every call, and ask for a named passcode with an expiry date
3. Check `status` in the body as well as the HTTP code. Get User Profiles can answer 200 with `"status":"fail"` when throttled
4. Add `dryRun=1` to an upload URL to validate up to 1,000 records without storing them
5. Set `estimate_only` or `draft` to true on Create Campaign before a real send. API campaigns bypass dashboard role restrictions

### 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, CleverTap or Dreamlit?

Dreamlit scores 57 (C) on agent readiness against CleverTap's 50.4 (D), and leads in 5 of 7 scored categories. CleverTap leads on payments & pricing and transparency & trust.

### Do CleverTap and Dreamlit need an API key?

CleverTap needs an API key. Dreamlit uses an OAuth sign-in.

### Can an agent call CleverTap and Dreamlit without installing anything?

No hosted endpoint is listed for CleverTap. Dreamlit has a hosted endpoint at https://mcp.dreamlit.ai/mcp.


## For agents

- This comparison as JSON: https://www.anchorterminal.com/compare/clevertap-vs-dreamlit.json, and with the fewest tokens: https://www.anchorterminal.com/compare/clevertap-vs-dreamlit.min.md
- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {"a": "clevertap", "b": "dreamlit"}`. From a terminal: `anchor compare clevertap dreamlit`
- Each listing in full: https://www.anchorterminal.com/api/v1/tools/clevertap.json and https://www.anchorterminal.com/api/v1/tools/dreamlit.json

## Other comparisons with CleverTap or Dreamlit

- [ActiveCampaign vs CleverTap](https://www.anchorterminal.com/compare/activecampaign-vs-clevertap.md)
- [Braze vs CleverTap](https://www.anchorterminal.com/compare/braze-vs-clevertap.md)
- [CleverTap vs Customer.io](https://www.anchorterminal.com/compare/clevertap-vs-customer-io.md)
- [CleverTap vs Iterable](https://www.anchorterminal.com/compare/clevertap-vs-iterable.md)
- [CleverTap vs Klaviyo API + MCP](https://www.anchorterminal.com/compare/clevertap-vs-klaviyo.md)
- [CleverTap vs Mailchimp Marketing API](https://www.anchorterminal.com/compare/clevertap-vs-mailchimp-marketing.md)
- [CleverTap vs MoEngage](https://www.anchorterminal.com/compare/clevertap-vs-moengage.md)
- [CleverTap vs Nitrosend](https://www.anchorterminal.com/compare/clevertap-vs-nitrosend.md)
- [CleverTap vs Omnisend](https://www.anchorterminal.com/compare/clevertap-vs-omnisend.md)
- [CleverTap vs Sequenzy](https://www.anchorterminal.com/compare/clevertap-vs-sequenzy.md)
- [ActiveCampaign vs Dreamlit](https://www.anchorterminal.com/compare/activecampaign-vs-dreamlit.md)
- [Braze vs Dreamlit](https://www.anchorterminal.com/compare/braze-vs-dreamlit.md)
- [Customer.io vs Dreamlit](https://www.anchorterminal.com/compare/customer-io-vs-dreamlit.md)
- [Dreamlit vs Iterable](https://www.anchorterminal.com/compare/dreamlit-vs-iterable.md)
- [Dreamlit vs Klaviyo API + MCP](https://www.anchorterminal.com/compare/dreamlit-vs-klaviyo.md)
- [Dreamlit vs Mailchimp Marketing API](https://www.anchorterminal.com/compare/dreamlit-vs-mailchimp-marketing.md)
- [Dreamlit vs MoEngage](https://www.anchorterminal.com/compare/dreamlit-vs-moengage.md)
- [Dreamlit vs Nitrosend](https://www.anchorterminal.com/compare/dreamlit-vs-nitrosend.md)
- [Dreamlit vs Omnisend](https://www.anchorterminal.com/compare/dreamlit-vs-omnisend.md)
- [Dreamlit vs Sequenzy](https://www.anchorterminal.com/compare/dreamlit-vs-sequenzy.md)

---

Query this catalogue directly over MCP: https://www.anchorterminal.com/mcp (Streamable HTTP, no key). How: https://www.anchorterminal.com/agents/#mcp