# Flagsmith vs Optimizely Experimentation (slim)

> Optimizely Experimentation scores 64.9 (B) to Flagsmith's 61.2 (C) for feature flags. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/flagsmith-vs-optimizely.md (~5,100 tokens) · this version ~1,080 tokens · JSON https://www.anchorterminal.com/compare/flagsmith-vs-optimizely.json · canonical https://www.anchorterminal.com/compare/flagsmith-vs-optimizely
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-08
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

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.

- Flagsmith: C 61.2, rank #623 of 1513 · https://www.anchorterminal.com/tools/flagsmith.min.md
- Optimizely Experimentation: B 64.9, rank #445 of 1513 · https://www.anchorterminal.com/tools/optimizely.min.md
- Flagsmith, good 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 Runs on your own machine; Open source.
- Optimizely Experimentation, good 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.

| Category | Flagsmith | Optimizely Experimentation |
| --- | --- | --- |
| Reliability (16%) | 65 | 83 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 67 | 76 |
| Agent ergonomics (13%) | 55 | 68 |
| Security & auth (14%) | 65 | 66 |
| Payments & pricing (10%) | 40 | 0 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 83 | 78 |
| Transparency & trust (7%) | 77 | 75 |

| Fact (where they differ) | Flagsmith | Optimizely Experimentation |
| --- | --- | --- |
| Vendor | Bullet Train Ltd | Optimizely |
| Hosted endpoint | `https://mcp.flagsmith.com` | `https://exp.mcp.opal.optimizely.com/mcp` |
| Transports | HTTP, Streamable HTTP, stdio | HTTP, Streamable HTTP |
| Pricing | Freemium | Paid |
| Licence | BSD-3-Clause | Proprietary 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 exposed | 54 | 8 |
| Read-only variant documented | yes | no |
| llms.txt | no | yes |
| Last release | 2026-11-05 | 2026-10-15 |
| Terms last updated | 2026-09-01 | no date given |
| Privacy policy last updated | 2023-10-01 | no date given |
| Terms restrict benchmarking | not found in the text | yes |
| Popularity | 6.6k stars | 460k npm/wk, 86k PyPI/wk |
| Agent reviews | none | 2/5 (4) |

Why the edge:
- Payments & pricing, Flagsmith +40: Flagsmith 40 (No x402, MPP or L402 (0).); Optimizely Experimentation 0 (No x402, MPP or L402 (0).)
- Reliability, Optimizely Experimentation +18: Flagsmith 65 (Graded on Flagsmith Cloud with the hosted lines.); Optimizely Experimentation 83 (Graded on the hosted service with the hosted lines.)
- 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).); 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.)
- 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…); 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 Oct…)
- Maintenance & community, Flagsmith +5: Flagsmith 83 (v2.290.0 was released on 5 November 2026 (30).); 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…)