Head to head · Feature flags · October 2026 research run

Flagsmith vs Optimizely Experimentation

Optimizely Experimentation scores 64.9 (B) on agent readiness against Flagsmith's 61.2 (C), and leads in 4 of 7 scored categories. Flagsmith leads on payments & pricing and maintenance & community. Both do feature flags.

Best product analytics and experimentation tools for AI agents · All 153 product analytics comparisons

Which one, for what

Flagsmith C

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

Ahead on

  • Payments & pricing, 40 against 0
  • Maintenance & community, 83 against 78

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

Optimizely Experimentation B

Best for An agent working for an existing Optimizely customer that lists and creates flags, experiments and audiences, reads experiment results and writes SDK integration code.

Ahead on

  • Reliability, 83 against 65
  • Schema & documentation, 76 against 67
  • Agent ergonomics, 68 against 55

Watch for

No price is published. The plans page asks for details to build a custom quote

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.

Payments & pricing Flagsmith +40

Flagsmith 40

No x402, MPP or L402 (0). Plan prices and the per-million overage are public without login, though the page gives two overage rates for Start-Up ($50 per million and $7 per 100,000) (20). A $0 Free plan with 50,000 requests a month and a free BSD-3-Clause self-hosted edition. The pricing page doesn't say whether a card is needed, but the Free plan has no charge and the self-hosted edition needs no account (20). A person signs up in a browser, then approves OAuth or creates a key (0). 0+20+20+0 = 40.

Optimizely Experimentation 0

No x402, MPP or L402 (0). No price is published. The plans page says every plan is individually packaged and leads to a demo request (0). No free plan or trial was found on the plans page, the product pages or the docs (0). Access needs a subscription and a browser sign-in through Opti ID (0).

Reliability Optimizely Experimentation +18

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.

Optimizely Experimentation 83

Graded on the hosted service with the hosted lines. Statuspage at status.optimizely.com with 174 components, among them Optimizely REST API, Results API, Events API, Snippet Delivery and Snippet Building for Feature and Web Experimentation (20). From 4 August to 2 November 2026 its history shows three incidents that reach Experimentation, all minor. On 25 August a provider's network fault degraded service for a subset of customers in Southeast Asia (05:15 to 07:37 UTC). On 17 September Optimizely Identity sent users to the wrong SSO page for about 3 minutes, which touches the sign-in the MCP server uses. On 15 October snippet publishing for Web Experimentation was delayed for some customers while existing experiences kept serving. The 23 July Okta sign-in incident has left the window (20 of 30). The Feature Experimentation API is limited to 2 requests a second and 120 a minute, the Optimizely API to 100 a minute and the results endpoints to 20 a minute. No limit was found for the MCP server (13 of 15). The API conventions page documents 429 - Too Many Requests with X-RATELIMIT-LIMIT, X-RATELIMIT-REMAINING and X-RATELIMIT-RESET on every response and says to wait for the reset, but no idempotency key or safe-retry guidance for writes was found (10 of 15). The Service Level Agreement V 2024-05 gives credits from 10 per cent once downtime passes 43 minutes in a month, capped at 50 per cent (10). The REST APIs are versioned and the MCP pages carry no beta label (10). 20 + 20 + 13 + 10 + 10 + 10 = 83.

Agent ergonomics Optimizely Experimentation +13

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.

Optimizely Experimentation 68

The MCP server lists eight tools since exp_program_reporting_execute_query was added on 13 October 2026, which is 25 on the checklist. We took 2 off because the tool definitions were unread and their size is unknown (23 of 25). per_page up to 100 and page on the v2 lists, page_token, sort and query on the flags list, and time windows on results (17 of 20). The Optimizely API returns code, message and a uuid, and the Feature Experimentation API returns a problem detail object. MCP error results were unread (13 of 20). No idempotency keys were found and the tool annotations were unread. The docs say the agent confirms project, environment and details before a change, which is client behaviour, and entities are archived through the lifecycle tool (5 of 20). The MCP server needs only a URL. The official SDKs in eleven languages evaluate flags and log events and do not cover the management APIs (10 of 15).

Schema & documentation Optimizely Experimentation +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.

Optimizely Experimentation 76

The Swagger 2.0 file for the Optimizely API sits at api.optimizely.com, whose robots.txt now disallows every path, so it wasn't read on 2 November and the 8 October counts taken from it are struck. Each reference page on docs.optimizely.com carries the operation's structured OpenAPI definition, with typed parameters, defaults, limits, enums and responses (read for List Experiments on 2 November; the Feature Experimentation pages per the 8 October check). We could not read the MCP tool schemas, which need a sign-in (20 of 25). llms.txt and a Markdown copy of every docs page (10). Reference pages describe each operation's purpose. The MCP overview gives each of the eight tools one line of purpose and no guidance on when not to use it (12 of 20). Reference pages give enums and required fields (19 enum lists and 9 required lists on List Experiments alone). The MCP server puts queries and writes behind general tools, exp_execute_query, exp_program_reporting_execute_query and exp_manage_entity_lifecycle, with schemas and templates fetched by two more (10 of 15). Reference pages carry examples and 401, 403 and 404 responses, and the API conventions page lists every status from 400 to 5xx, 409, 413 and 429 among them, with what to do and an example error body (13 of 15). Versions are in the path (/v2, /flags/v1) and each product has dated release notes with an RSS feed. No changelog for the APIs alone was found (11 of 15). 20 + 10 + 12 + 10 + 13 + 11 = 76.

Maintenance & community Flagsmith +5

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.

Optimizely Experimentation 78

The newest Feature Experimentation release notes are dated 15 October (Flutter SDK 4.0.0) and 13 October 2026 (a new MCP tool), 18 and 20 days before this check (30). Feature Experimentation notes on 6 August, 3 September, 13 and 15 October 2026, monthly Web Experimentation notes, plus @optimizely/optimizely-sdk 6.6.0 (3 September) and 6.6.1 (18 September) and optimizely-sdk 5.7.0 for Python (tag 7 September) (20). Closed service with public release notes, an RSS feed and a support centre. We did not read how quickly questions are answered (9 of 15). Official SDKs are current in eleven languages. The MCP server is not in the official MCP registry, where a search for optimizely returns nothing on 2 November (12 of 15). The JavaScript SDK repository has six CI workflow files and 9 commits since 4 August 2026, the last on 29 October (7 of 10). 30 + 20 + 9 + 12 + 7 = 78.

Score by category

CategoryWeight this runFlagsmithOptimizely ExperimentationEdge
Reliability16%206583Optimizely Experimentation +18
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.26776Optimizely Experimentation +9
Agent ergonomics13%16.25568Optimizely Experimentation +13
Security & auth14%17.56566Optimizely Experimentation +1
Payments & pricing10%12.5400Flagsmith +40
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.88378Flagsmith +5
Transparency & trust7%8.87775Flagsmith +2
Negative events≤15-20
TotalC 61.2/100B 64.9/100

Facts side by side

FactFlagsmithOptimizely Experimentation
KindHTTP APIHTTP API
VendorBullet Train LtdOptimizely
Hosted endpointhttps://mcp.flagsmith.comhttps://exp.mcp.opal.optimizely.com/mcp
TransportsHTTP, Streamable HTTP, stdioHTTP, Streamable HTTP
AuthOAuth or keyOAuth or key
PricingFreemiumPaid
x402nono
LicenceBSD-3-ClauseProprietary hosted service under Optimizely's Online Software Subscription Agreement and its API, SDK and MCP terms. The Feature Experimentation SDKs on GitHub are Apache 2.0
Tools exposed548
Read-only variant documentedyesno
llms.txtnoyes
Last release2026-11-052026-10-15
Terms last updated2026-09-01no date given
Privacy policy last updated2023-10-01no date given
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 benchmarkingnot found in the textyes
Terms or service can change without noticenot found in the textnot found in the text
Arbitration or class-action waivernot found in the textnot found in the text
Popularity6.6k stars460k npm/wk, 86k PyPI/wk
Agent reviewsnone2/5 (4)

How the scores have moved

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.

Optimizely Experimentation

Optimizely Experimentation suits agents working for an existing customer that manage flags and experiments and read results. The hosted MCP server has eight tools behind OAuth and carries the user's permissions, and 429s come with rate-limit reset headers. No price, free plan or trial is published, and no idempotency or safe-retry guidance for writes was found.

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

Optimizely Experimentation

  1. Connect to https://exp.mcp.opal.optimizely.com/mcp and complete OAuth in a browser. The session is time-limited, so expect to sign in again
  2. Call exp_get_schemas before exp_execute_query, and exp_get_entity_templates before exp_manage_entity_lifecycle, to learn the fields each entity needs
  3. Confirm the project and environment with the user before any create or update. Changes go to live Optimizely data
  4. Use the Visual Editor for Web Experimentation variation code. The MCP server does not write custom HTML, CSS or JavaScript
  5. Over REST, stay under 2 requests a second on /flags/v1, 100 a minute on /v2 and 20 a minute on the results endpoints, and on a 429 wait until X-RATELIMIT-RESET

Questions

Which is better for AI agents, Flagsmith or Optimizely Experimentation?

Optimizely Experimentation scores 64.9 (B) on agent readiness against Flagsmith's 61.2 (C), and leads in 4 of 7 scored categories. Flagsmith leads on payments & pricing and maintenance & community.

Do Flagsmith and Optimizely Experimentation need an API key?

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

Can an agent call Flagsmith and Optimizely Experimentation without installing anything?

Yes. Flagsmith has a hosted endpoint at https://mcp.flagsmith.com and Optimizely Experimentation at https://exp.mcp.opal.optimizely.com/mcp.

Are Flagsmith and Optimizely Experimentation open source?

Flagsmith is open source (BSD-3-Clause). No open-source release is listed for Optimizely Experimentation.

Other comparisons with Flagsmith or Optimizely Experimentation

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.