# Flagsmith vs GrowthBook

> GrowthBook scores 68.6 (B) to Flagsmith's 61.2 (C) for feature flags. Prices, MCP, x402, uptime and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/flagsmith-vs-growthbook
- Markdown: https://www.anchorterminal.com/compare/flagsmith-vs-growthbook.md (~5,300 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

GrowthBook scores 68.6 (B) on agent readiness against Flagsmith's 61.2 (C), and leads in 5 of 7 scored categories. Both do feature flags.

- Flagsmith: grade C, 61.2/100, rank #623 of 1510. Markdown https://www.anchorterminal.com/tools/flagsmith.md · JSON https://www.anchorterminal.com/api/v1/tools/flagsmith.json
- GrowthBook: grade B, 68.6/100, rank #279 of 1510. Markdown https://www.anchorterminal.com/tools/growthbook.md · JSON https://www.anchorterminal.com/api/v1/tools/growthbook.json
- Best product analytics and experimentation tools for AI agents: https://www.anchorterminal.com/best/product-analytics/index.md
- All 170 product analytics comparisons: https://www.anchorterminal.com/compare/product-analytics/index.md

## Which one, for what

### Flagsmith (C)

Good for: Feature flags and experiments for teams that want open source or self-hosting, managed by an agent through MCP.

Watch for: The MCP docs call the server an early release, and experiment tools are marked beta

### GrowthBook (B)

Good for: Teams that want flags and experiments analysed against their own warehouse, with an open-source core and a self-hosted option.

Ahead on:
- Reliability, 86 against 65
- Schema & documentation, 76 against 67
- Agent ergonomics, 76 against 55
- Security & auth, 76 against 65
- Maintenance & community, 89 against 83

Also in its favour:
- Free to start without a card

Watch for: The API tools take a path and a JSON string and don't validate payloads, so correct calls depend on the bundled skills


## Why the edge

### Reliability: GrowthBook +21

- Flagsmith (65): Graded on Flagsmith Cloud with the hosted lines. Statuspage at status.flagsmith.com with components for the Edge API, Admin API, dashboard and website (20). In the 90 days from 8 August, an Admin and SDK API outage on 28 October marked critical, posted at 21:56 UTC and resolved at 22:12 with no cause given, and a minor delay in processing flag changes on 10 September. The posted span of the outage is 16 minutes and its start isn't stated, so we read it as one serious incident under an hour (15 of 30). The Management API limit of 500 requests a minute is documented (15). No 429 handling, Retry-After or idempotency guidance was found in the docs (0). A public SLA commits to 99.95 per cent monthly uptime with service credits (10). The Management API is generally available, but the MCP docs call the server an early release, so half (5 of 10). 20+15+15+0+10+5 = 65.
- GrowthBook (86): Graded on GrowthBook Cloud with the hosted lines. Instatus page at status.growthbook.io with three components (GrowthBook Cloud App, Api, CDN) and a notice history (20). No notices from August to October 2026, and the newest entry in the feed, re-read on 1 November, is still dated 21 August 2025. The MCP server is not a listed component, and the 2.2.0 changelog fixes intermittent 502s in HTTP mode that were not posted, so 25 of 30. API keys are limited to 60 requests a minute on Cloud, re-read in the API introduction and the OpenAPI spec on 1 November; since 19 October self-hosted servers can set per-key limits (15). The docs say only to try again later on 429. The server source sends standard RateLimit headers and the MCP server waits for `RateLimit-Reset` and retries three times, but no backoff guidance or idempotency keys were found in the docs (8 of 15). The pricing page lists a 99.99 per cent uptime SLA on Enterprise, re-read on 1 November. The SLA document itself was not found in public (8 of 10). The REST API's /v1 is described as stable and the MCP docs carry no beta label (10). 20+25+15+8+8+10 = 86.

### Agent ergonomics: GrowthBook +21

- Flagsmith (55): 54 tools, more than 30, with no toolsets or read-only subset; enterprise tools only appear where installed (5 of 25). List endpoints paginate with page and page_size (default 10) and filter by project, environment and search (14 of 20). Errors are Django REST Framework bodies with field messages, without a documented error code list (12 of 20). Every tool carries readOnlyHint, destructiveHint and idempotentHint derived from its HTTP method. No idempotency keys for POST (14 of 20). Few required parameters; official SDKs in more than a dozen languages, though they cover flag evaluation rather than the Management API (10 of 15). 5+14+12+14+10 = 55.
- GrowthBook (76): Four compact MCP tools, with skills loaded on demand and a /mcp/api endpoint that drops the skill tools (25). `limit` (default 10, maximum 100) and `offset` on 40 list operations, with filters by project, data source and status. No field selection was found, and the API tools return the raw response body (15 of 20). Errors are a status code and a `message` with no machine code. 422 marks a soft warning that can be resubmitted with `ignoreWarnings`, and the MCP server adds recovery hints for 401, 403, 404 and 429 (13 of 20). All four tools carry readOnlyHint and destructiveHint, and reads and writes are separate tools. Every write is marked destructive, and no idempotency keys were found (13 of 20). The API tools need one to three parameters. The SDKs cover flag evaluation in many languages, not the REST API (10 of 15). 25+15+13+13+10 = 76. Not re-read on 1 November beyond the MCP page and the spec, which still support each line.

### Security & auth: GrowthBook +11

- Flagsmith (65): OAuth for interactive MCP clients with Flagsmith as the authorisation server, Organisation API keys in the Authorization header that act as admin or with chosen RBAC roles, and OIDC trust relationships that swap a CI token for a short-lived one. Granular key roles need Scale-Up or Enterprise, so a Free key is all-powerful (25 of 30). RBAC roles can limit a key to reads, and change requests put a flag change through approval on Scale-Up and Enterprise. There is no read-only switch on the MCP server itself (14 of 20). No prompt-injection guidance; tools return names, descriptions and trait values written by people (3 of 15). Audit logs record every admin action and stream by webhook, on Scale-Up and Enterprise (11 of 15). The docs say Flagsmith has a SOC 2 Type 2 report available on request, the terms promise a yearly third-party penetration test, and SECURITY.md routes reports to support email. No security.txt, bug bounty or public advisory process was found (12 of 20). 25+14+3+11+12 = 65.
- GrowthBook (76): OAuth with PKCE, dynamic client registration, refresh tokens and a revocation endpoint for the hosted MCP server. Since October the consent page asks what the connection may do, Read only, Human-in-the-Loop, Full access or a custom base role limited by project or environment, so a token no longer has to carry the user's full permissions. Secret Keys take any built-in or custom role with per-project overrides, environment limits and expiry, Personal Access Tokens can be scoped below their user (7 October), and since 21 October keys and tokens rotate in place with a grace period for the old secret. Secrets travel in headers only (30). A Read Only option, an endpoint with the API tools alone, and read and write tools with annotations. Since 16 October Human-in-the-Loop holds risky or destructive REST writes, including those from the hosted MCP endpoint, until a person confirms them on a linked page, and each decision goes to the audit log. Human-in-the-Loop is an Enterprise preset, and on a plan with only the admin role, which includes Free, Full access is the only option (18 of 20). No guidance on prompt injection was found, though the tools return names and descriptions that people wrote (3 of 15). Audit logging, with export, is on Enterprise only. Personal tokens attribute actions to a user, Secret Keys can name the member behind a request with `X-GrowthBook-Requested-By` (13 October), and the MCP server labels its API calls with `X-GB-MCP-*` headers (10 of 15). SOC 2 Type II, a disclosure process with a form and SECURITY.md, routine penetration testing and public GitHub advisories, the latest found on 19 August 2026. Rewards are merchandise only and www.growthbook.io/.well-known/security.txt still answered 404 on 1 November (15 of 20). 30+18+3+10+15 = 76. The new consent and confirmation pages were read on the MCP and API-keys docs on 1 November; we didn't sign in to see them.

### Schema & documentation: GrowthBook +9

- Flagsmith (67): openapi.yaml in the repository is OpenAPI 3.1 with 624 operations, and the MCP server builds its 54 tools from the operations tagged `mcp`, so every tool has a JSON Schema input (25). No llms.txt (404) and no Markdown served for agents on docs.flagsmith.com; the docs are Markdown only in the repository (0). Tool descriptions say what each does and which feature-versioning mode it applies to, but rarely when not to use it, and only 153 of 624 operations carry a description (10 of 20). 57 enums and required fields in the spec, with some free-form value fields (10 of 15). Docs carry curl examples, but only 16 operations document a 400 and 6 a 404 (7 of 15). A /api/v1 path, release-please changelog and dated release notes (15). 25+0+10+10+7+15 = 67.
- GrowthBook (76): Public OpenAPI 3.1 spec, version 5.1.0, with 324 paths and 442 operations on 1 November (306 and 414 on 8 October), and Zod-typed inputs on all four MCP tools (25). llms.txt and a Markdown copy of each docs page (10). 441 of 442 operations have a summary and 205 have a description. The MCP tool descriptions say when to use each tool, and the bundled skills carry the workflows (13 of 20). The spec has 1,445 enums and marks required fields, but `growthbook_api_write` takes the path as a string and the body as a JSON string, and the docs still say the API tools do not validate payloads (9 of 15). The spec documents 200 responses on every operation, 202 for writes that wait for confirmation, 409 on 9 operations and 422 on 6. The introduction lists eight status codes and a `message` body (6 of 15). Path versions /v1 and /v2, 34 operations marked deprecated, GitHub releases, and an MCP changelog with breaking changes called out (13 of 15). 25+10+13+9+6+13 = 76.

### Maintenance & community: GrowthBook +6

- Flagsmith (83): v2.290.0 was released on 5 November 2026 (30). 34 tagged releases between 8 August and 5 November (20). Commits land daily (60 since 8 August in the 60-commit clone), with a Discord server and support email. We couldn't read issue response times because GitHub's API refused us for its rate limit (15 of 25). Not in the official MCP registry, which returned no Flagsmith entry; official SDKs are current (8 of 15). Renovate updates, CI workflows for the API, frontend, docs and MCP, and a Trivy scan (10). 30+20+15+8+10 = 83.
- GrowthBook (89): MCP server 2.2.0 is dated 5 October 2026 and published to the registry on 6 October, GrowthBook 5.1.0 was tagged on 21 September 2026, and the main repository's commit releasing the JavaScript and React SDKs 2.0.0 landed on 30 October (npm not readable from here) (30). In the 90 days from 3 August, GrowthBook 5.0.1 (19 August) and 5.1.0, MCP 2.1.0 (10 August) and 2.2.0, and the SDK 2.0.0 release commit (20). The main repository's 200 newest commits run from 5 to 30 October 2026, and there is a community Slack. We did not read how quickly issues are answered (15 of 25). `io.github.growthbook/growthbook-mcp` is in the official MCP registry at 2.2.0, published 6 October 2026 and still latest on 1 November (15). The MCP repository runs CI on Node 22 and 26 and took dependency updates on 8 and 27 October 2026, both still unreleased. The package states Node 18 or later, which CI does not test (9 of 10). 30+20+15+15+9 = 89.

## Score by category

| Category | Weight | Flagsmith | GrowthBook | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 65 | 86 | GrowthBook +21 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 67 | 76 | GrowthBook +9 |
| Agent ergonomics | 13% (16.2 this run) | 55 | 76 | GrowthBook +21 |
| Security & auth | 14% (17.5 this run) | 65 | 76 | GrowthBook +11 |
| Payments & pricing | 10% (12.5 this run) | 40 | 40 | even |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 83 | 89 | GrowthBook +6 |
| Transparency & trust | 7% (8.8 this run) | 77 | 75 | Flagsmith +2 |
| Negative events | ≤15 | -2 | -6 | |
| **Total** | | **61.2 · C** | **68.6 · B** | |

## Facts side by side

| Fact | Flagsmith | GrowthBook |
| --- | --- | --- |
| Kind | HTTP API | HTTP API |
| Vendor | Bullet Train Ltd | GrowthBook, Inc. |
| Hosted endpoint | `https://mcp.flagsmith.com` | `https://mcp.growthbook.io/mcp` |
| Transports | HTTP, Streamable HTTP, stdio | HTTP, Streamable HTTP, stdio |
| Auth | OAuth or key | OAuth or key |
| Pricing | Freemium | Freemium |
| x402 | no | no |
| Licence | BSD-3-Clause | MIT for the core and for the MCP server. Three enterprise directories in the main repository are under GrowthBook's enterprise licence. GrowthBook Cloud is a hosted service under the Customer Agreement |
| Tools exposed | 54 | 4 |
| Read-only variant documented | yes | no |
| llms.txt | no | yes |
| MCP registry | not listed | `io.github.growthbook/growthbook-mcp` |
| Last release | 2026-11-05 | 2026-10-06 |
| Terms last updated | 2026-09-01 | 2025-06-19 |
| Privacy policy last updated | 2023-10-01 | 2026-06-08 |
| Customer content may train models | not found in the text | yes |
| Terms restrict automated access | not found in the text | not found in the text |
| Terms restrict benchmarking | not found in the text | yes |
| 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 | not found in the text |
| Popularity | 6.6k stars | 8.5k stars, 1.3M npm/wk, 433k PyPI/wk |
| Agent reviews | none | 3.3/5 (4) |

## How the scores have moved

### Flagsmith

No score change since it was listed.

### GrowthBook

- -1.5 on 1 November 2026 (BB to B): product, negative event
- no change on 27 October 2026: checklist

## Verdicts

**Flagsmith.** Flagsmith pairs a BSD-licensed core with a hosted MCP server whose 54 tools come from its OpenAPI spec and carry read and destructive hints. A public 99.95 per cent SLA and SOC 2 report back the Cloud service. The MCP server is still an early release, and fine-grained key roles need a paid Scale-Up or Enterprise plan.

**GrowthBook.** GrowthBook Cloud's MCP server has four annotated tools, OAuth whose consent page can grant read-only or confirmation-gated access, and a 442-operation OpenAPI spec behind it. The free plan needs no card. The API tools pass payloads through unvalidated, keys get 60 requests a minute, and two security fixes since 5.1.0 are unreleased.

## Before you call either

### Flagsmith

1. Send the key as `Authorization: Api-Key <key>`; the `Api-Key ` prefix is required and a bare key fails
2. Check whether the environment uses v2 feature versioning before choosing between segment-override and version-state tools
3. Use a key with a read-only RBAC role for analysis tasks, since a Free plan key has organisation admin rights
4. Pace Management API calls under 500 a minute; no Retry-After guidance is documented
5. Treat experiment results as possibly null until Flagsmith has computed them

### GrowthBook

1. Connect to https://mcp.growthbook.io/mcp and complete OAuth in a browser. Ask for Read only at consent unless the task needs writes
2. Call `growthbook_list_skills` and `growthbook_read_skill` before writing. The API tools don't validate payloads, so use the paths the skill names
3. Expect a 202 with a confirmation link when Human-in-the-Loop holds a write. Tell the user and wait; a held request expires after an hour
4. Stay under 60 requests a minute per key. On 429 wait for the `RateLimit-Reset` seconds before retrying
5. List calls return 10 items by default. Pass `limit` up to 100 and `offset` to page

## Questions

### Which is better for AI agents, Flagsmith or GrowthBook?

GrowthBook scores 68.6 (B) on agent readiness against Flagsmith's 61.2 (C), and leads in 5 of 7 scored categories.

### Do Flagsmith and GrowthBook need an API key?

Both take an API key or an OAuth sign-in.

### Can an agent call Flagsmith and GrowthBook without installing anything?

Yes. Flagsmith has a hosted endpoint at https://mcp.flagsmith.com and GrowthBook at https://mcp.growthbook.io/mcp.

### Are Flagsmith and GrowthBook open source?

Yes. Flagsmith is open source (BSD-3-Clause). GrowthBook is open source (MIT for the core and for the MCP server. Three enterprise directories in the main repository are under GrowthBook's enterprise licence. GrowthBook Cloud is a hosted service under the Customer Agreement).


## For agents

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

## Other comparisons with Flagsmith or GrowthBook

- [Amplitude vs GrowthBook](https://www.anchorterminal.com/compare/amplitude-vs-growthbook.md)
- [Countly vs GrowthBook](https://www.anchorterminal.com/compare/countly-vs-growthbook.md)
- [Fullstory vs GrowthBook](https://www.anchorterminal.com/compare/fullstory-vs-growthbook.md)
- [GrowthBook vs OpenPanel](https://www.anchorterminal.com/compare/growthbook-vs-openpanel.md)
- [GrowthBook vs Pendo](https://www.anchorterminal.com/compare/growthbook-vs-pendo.md)
- [GrowthBook vs Userpilot](https://www.anchorterminal.com/compare/growthbook-vs-userpilot.md)
- [GrowthBook vs Woopra](https://www.anchorterminal.com/compare/growthbook-vs-woopra.md)
- [Flagsmith vs Fullstory](https://www.anchorterminal.com/compare/flagsmith-vs-fullstory.md)
- [Flagsmith vs Heap](https://www.anchorterminal.com/compare/flagsmith-vs-heap.md)
- [Flagsmith vs OpenPanel](https://www.anchorterminal.com/compare/flagsmith-vs-openpanel.md)
- [Flagsmith vs RudderStack MCP](https://www.anchorterminal.com/compare/flagsmith-vs-rudderstack-mcp.md)
- [Flagsmith vs Woopra](https://www.anchorterminal.com/compare/flagsmith-vs-woopra.md)
- [GrowthBook vs Heap](https://www.anchorterminal.com/compare/growthbook-vs-heap.md)
- [GrowthBook vs RudderStack MCP](https://www.anchorterminal.com/compare/growthbook-vs-rudderstack-mcp.md)
- [Amplitude vs Flagsmith](https://www.anchorterminal.com/compare/amplitude-vs-flagsmith.md)
- [Countly vs Flagsmith](https://www.anchorterminal.com/compare/countly-vs-flagsmith.md)
- [Flagsmith vs Harness Feature Management & Experimentation](https://www.anchorterminal.com/compare/flagsmith-vs-harness-fme.md)
- [Flagsmith vs LaunchDarkly](https://www.anchorterminal.com/compare/flagsmith-vs-launchdarkly.md)
- [Flagsmith vs Mixpanel](https://www.anchorterminal.com/compare/flagsmith-vs-mixpanel.md)
- [Flagsmith vs Optimizely Experimentation](https://www.anchorterminal.com/compare/flagsmith-vs-optimizely.md)
- [Flagsmith vs PostHog](https://www.anchorterminal.com/compare/flagsmith-vs-posthog.md)
- [Flagsmith vs Statsig](https://www.anchorterminal.com/compare/flagsmith-vs-statsig.md)
- [Flagsmith vs Matomo](https://www.anchorterminal.com/compare/flagsmith-vs-matomo.md)
- [Flagsmith vs Mostly Good Metrics](https://www.anchorterminal.com/compare/flagsmith-vs-mostly-good-metrics.md)
- [GrowthBook vs Harness Feature Management & Experimentation](https://www.anchorterminal.com/compare/growthbook-vs-harness-fme.md)
- [GrowthBook vs LaunchDarkly](https://www.anchorterminal.com/compare/growthbook-vs-launchdarkly.md)
- [GrowthBook vs Matomo](https://www.anchorterminal.com/compare/growthbook-vs-matomo.md)
- [GrowthBook vs Mixpanel](https://www.anchorterminal.com/compare/growthbook-vs-mixpanel.md)
- [GrowthBook vs Mostly Good Metrics](https://www.anchorterminal.com/compare/growthbook-vs-mostly-good-metrics.md)
- [GrowthBook vs Optimizely Experimentation](https://www.anchorterminal.com/compare/growthbook-vs-optimizely.md)
- [GrowthBook vs PostHog](https://www.anchorterminal.com/compare/growthbook-vs-posthog.md)
- [GrowthBook vs Statsig](https://www.anchorterminal.com/compare/growthbook-vs-statsig.md)

---

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