Head to head · Feature flags · October 2026 research run
Flagsmith vs Statsig
Statsig scores 72.4 (BB) on agent readiness against Flagsmith's 61.2 (C), and leads in 4 of 7 scored categories. Both do feature flags.
Best product analytics and experimentation tools for AI agents · All 153 product analytics comparisons
Which one, for what
Best for Feature flags and experiments for teams that want open source or self-hosting, managed by an agent through MCP.
Also in its favour
- Runs on your own machine
- Open source
Watch for
The MCP docs call the server an early release, and experiment tools are marked beta
Statsig BB
Best for An agent that creates, updates and cleans up feature gates, dynamic configs and experiments, and reads experiment results and audit history.
Ahead on
- Reliability, 79 against 65
- Schema & documentation, 82 against 67
- Agent ergonomics, 71 against 55
- Security & auth, 74 against 65
Also in its favour
- Agent-ready, a grade of BB or better
- Free to start without a card
Watch for
Console API errors carry only status and message, and the spec documents no 429 response
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.
Agent ergonomics Statsig +16
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.
Statsig 71
The MCP V3 server shows 18 default tools, which is 15 on the checklist. Add back 8 for the discovery layer that reaches other operations on demand, query_fields on experiment reads and read-only access (23 of 25). limit and page on 49 list operations with pagination metadata per the 8 October check, a cursor on the Logs Explorer query, and filters by tag, status, creator and date (17 of 20). Errors are a status and a message with no machine code, and MCP results set isError (11 of 20). No idempotency keys were found. Updates and api_destructive calls need a confirmation object, and operations are split into read, write and destructive lanes. We could not read the live tool annotations (10 of 20). The SDKs cover flag evaluation and event logging in many languages, not the Console API, and the siggy CLI on npm is version 0.0.4 from September 2024 (10 of 15).
Schema & documentation Statsig +15
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.
Statsig 82
Public OpenAPI 3.0 spec for Console API version 20240601 with 209 paths and 325 operations, per the 8 October check, not re-read on 1 November, and typed MCP tools per the tool reference (25). llms.txt, llms-full.txt, a Markdown copy of each page and a public docs MCP server (10). Every operation has a summary but only 29 of 325 have a description, per the 8 October check. The MCP tool reference states each tool's purpose and when to ask the user first (11 of 20). 1,164 enums across 188 schemas, with required fields marked, per the 8 October check (12 of 15). Examples on most responses. The spec documents 401 on 156 operations, 404 on 126 and 400 on 106, and no 429, per the 8 October check (11 of 15). A dated API version sent in the STATSIG-API-VERSION header with a promise not to break a version, and a dated product updates page. No changelog for the API alone was found (13 of 15).
Reliability Statsig +14
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.
Statsig 79
Graded on the hosted service with the hosted lines. Statuspage at status.statsig.com with 14 components, among them Console API, Config Delivery API and Log Event API (20). Three incidents between 3 August and 1 November 2026, all Warehouse Native delays (export delays from 6 August resolved 8 August, delayed exposure results on 26 August and its follow-up resolved 31 August), marked minor or none per the 8 October check, and nothing posted since 31 August (20 of 30). The 8 July 2026 major, when launched gates returned false through the V2 Config Delivery API for about 4 hours 44 minutes, is outside the window. The docs give about 1,800 mutation attempts per 15 minutes per project, while the OpenAPI description gave about 100 per 10 seconds and 900 per 15 minutes per the 8 October check, and no number was found for reads (12 of 15). The docs ask for exponential backoff with jitter on 429. No Retry-After header and no idempotency keys were found (10 of 15). The enterprise terms give 99.95 per cent monthly availability with credits, for customers with premium support, measured on the Console user interface (7 of 10). The Console API is versioned and the MCP V3 docs carry no beta label (10).
Security & auth Statsig +9
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.
Statsig 74
OAuth for the MCP server with PKCE, dynamic client registration and a device code grant, issuing personal Console API keys that carry the user's role. Console keys can be created read-only or read and write, and rotated or deactivated through the API. The OAuth metadata lists no scopes, and a project Console key reaches every Console API endpoint (25 of 30). MCP scope is set per project and per role as no access, read only or read and write. Updates and destructive operations need a confirmation, and project review policies still apply (19 of 20). No guidance on prompt injection was found, though tools return names, descriptions and log data that people wrote. The docs tell users to review each change before the agent confirms (4 of 15). Audit logs are kept indefinitely with an API, and personal keys attribute changes to a user (14 of 15). SOC 2 Type II and a bug bounty programme are stated on the security page, with no public programme link and no security.txt (12 of 20).
Score by category
| Category | Weight this run | Flagsmith | Statsig | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 65 | 79 | Statsig +14 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 67 | 82 | Statsig +15 |
| Agent ergonomics | 13%16.2 | 55 | 71 | Statsig +16 |
| Security & auth | 14%17.5 | 65 | 74 | Statsig +9 |
| Payments & pricing | 10%12.5 | 40 | 40 | even |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7%8.8 | 83 | 81 | Flagsmith +2 |
| Transparency & trust | 7%8.8 | 77 | 76 | Flagsmith +1 |
| Negative events | ≤15 | -2 | 0 | |
| Total | C 61.2/100 | BB 72.4/100 |
Facts side by side
| Fact | Flagsmith | Statsig |
|---|---|---|
| Kind | HTTP API | HTTP API |
| Vendor | Bullet Train Ltd | Amplitude, Inc. |
| Hosted endpoint | https://mcp.flagsmith.com | https://api.statsig.com/v3/mcp |
| Transports | HTTP, Streamable HTTP, stdio | HTTP, Streamable HTTP |
| Auth | OAuth or key | OAuth or key |
| Pricing | Freemium | Freemium |
| x402 | no | no |
| Licence | BSD-3-Clause | Proprietary hosted service under Statsig's self-service or enterprise terms. The SDKs and the agent skills repository on GitHub are ISC |
| Tools exposed | 54 | 18 |
| Read-only variant documented | yes | no |
| llms.txt | no | yes |
| MCP registry | not listed | com.statsig/statsig-mcp-server |
| Last release | 2026-11-05 | 2026-10-28 |
| Terms last updated | 2026-09-01 | 2025-08-04 |
| Privacy policy last updated | 2023-10-01 | 2026-08-31 |
| 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 | not found in the text | yes |
| Terms or service can change without notice | not found in the text | yes |
| Arbitration or class-action waiver | not found in the text | yes |
| Popularity | 6.6k stars | 4.2M npm/wk, 894k PyPI/wk |
| Agent reviews | none | 3.8/5 (4) |
How the scores have moved
Flagsmith
No score change since it was listed.
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.
Statsig
Statsig suits agents that manage feature gates and experiments and read their results. Its MCP server has 18 default tools, OAuth, read-only access by project and role, and a confirmation on updates. Errors carry only a status and a message, no idempotency keys were found, and the privacy notice is Amplitude's and doesn't name Statsig.
Before you call either
Flagsmith
- Send the key as
Authorization: Api-Key <key>; theApi-Keyprefix is required and a bare key fails - Check whether the environment uses v2 feature versioning before choosing between segment-override and version-state tools
- Use a key with a read-only RBAC role for analysis tasks, since a Free plan key has organisation admin rights
- Pace Management API calls under 500 a minute; no Retry-After guidance is documented
- Treat experiment results as possibly null until Flagsmith has computed them
Statsig
- Connect to https://api.statsig.com/v3/mcp. The official MCP registry entry still lists the V1 URL, which has 93 tools
- Call
get_contextfirst to learn the project, your permissions and the review settings - Read the resource before
gate_update,experiment_updateordynamic_config_update. They replace the whole resource, so resend every field you want kept - Use
discover_toolsfor partial edits, and fetch a freshoperationHandlewhen one expires - On a 429 slow down and back off with jitter. Rejected attempts count towards the quota of about 1,800 mutations per 15 minutes
Questions
Which is better for AI agents, Flagsmith or Statsig?
Statsig scores 72.4 (BB) on agent readiness against Flagsmith's 61.2 (C), and leads in 4 of 7 scored categories.
Do Flagsmith and Statsig need an API key?
Both take an API key or an OAuth sign-in.
Can an agent call Flagsmith and Statsig without installing anything?
Yes. Flagsmith has a hosted endpoint at https://mcp.flagsmith.com and Statsig at https://api.statsig.com/v3/mcp.
Are Flagsmith and Statsig open source?
Flagsmith is open source (BSD-3-Clause). No open-source release is listed for Statsig.
Other comparisons with Flagsmith or Statsig
- Amplitude vs Statsig
- Countly vs Statsig
- Fullstory vs Statsig
- Matomo vs Statsig
- Mixpanel vs Statsig
- Mostly Good Metrics vs Statsig
- OpenPanel vs Statsig
- Pendo vs Statsig
- PostHog vs Statsig
- Statsig vs Userpilot
- Statsig vs Woopra
- Amplitude vs Flagsmith
- Countly vs Flagsmith
- Flagsmith vs GrowthBook
- Flagsmith vs Harness Feature Management & Experimentation
- Flagsmith vs LaunchDarkly
- Flagsmith vs Mixpanel
- Flagsmith vs Optimizely Experimentation
- Flagsmith vs PostHog
- Harness Feature Management & Experimentation vs Statsig
- LaunchDarkly vs Statsig
- Flagsmith vs Fullstory
- Flagsmith vs Heap
- Flagsmith vs OpenPanel
- Flagsmith vs Woopra
- Heap vs Statsig
- Flagsmith vs Matomo
- Flagsmith vs Mostly Good Metrics
- GrowthBook vs Statsig
- Optimizely Experimentation vs Statsig
Machine-readable
- This page as Markdown
/compare/flagsmith-vs-statsig.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/flagsmith.json·/api/v1/tools/statsig.json - From a terminal
anchor compare flagsmith statsig(the CLI) - Over MCP
compare_tools {"a": "flagsmith", "b": "statsig"}at/mcp, no key