Head to head · Analytics flags · October 2026 research run
LaunchDarkly vs Statsig
Statsig scores 72.3 (BB) on agent readiness against LaunchDarkly's 69.2 (B), and leads in 3 of 7 scored categories. LaunchDarkly leads on schema & documentation and transparency & trust. Both do analytics flags.
Which one, for what
Good for An agent that creates and targets feature flags, runs rollouts and experiments, reads experiment results and cleans up stale flags.
Ahead on
- Schema & documentation, 89 against 82
- Transparency & trust, 80 against 75
Also in its favour
- Runs on your own machine
Watch for
The hosted MCP server lists 141 tools, and no tool filter for it was found in the reviewed documentation
Statsig BB
Good 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 64
- Security & auth, 74 against 66
Also in its favour
- Agent-ready, a grade of BB or better
Watch for
Console API errors carry only status and message, and the spec documents no 429 response
Score by category
| Category | Weight this run | LaunchDarkly | Statsig | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 64 | 79 | Statsig +15 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 89 | 82 | LaunchDarkly +7 |
| Agent ergonomics | 13%16.2 | 69 | 71 | Statsig +2 |
| Security & auth | 14%17.5 | 66 | 74 | Statsig +8 |
| Payments & pricing | 10%12.5 | 40 | 40 | even |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7%8.8 | 82 | 81 | LaunchDarkly +1 |
| Transparency & trust | 7%8.8 | 80 | 75 | LaunchDarkly +5 |
| Negative events | ≤15 | 0 | 0 | |
| Total | 69.2 · B | 72.3 · BB |
Facts side by side
| Fact | LaunchDarkly | Statsig |
|---|---|---|
| Kind | HTTP API | HTTP API |
| Vendor | Catamorphic, Co. (dba LaunchDarkly) | Amplitude, Inc. |
| Hosted endpoint | https://mcp.launchdarkly.com/mcp/launchdarkly | 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 | Proprietary service under LaunchDarkly's terms. The local MCP server is MIT and the ldcli CLI is Apache-2.0 | Proprietary hosted service under Statsig's self-service or enterprise terms. The SDKs and the agent skills repository on GitHub are ISC |
| Tools exposed | 141 | 18 |
| Read-only variant documented | no | no |
| llms.txt | yes | yes |
| MCP registry | not listed | com.statsig/statsig-mcp-server |
| Last release | 2026-10-06 | 2026-09-28 |
| Terms last updated | 2025-09-08 | 2025-08-04 |
| Privacy policy last updated | 2025-04-08 | 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 | yes | 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 | 3.3M npm/wk, 2.2M PyPI/wk | 4.2M npm/wk, 894k PyPI/wk |
Verdicts
LaunchDarkly
LaunchDarkly suits agents that manage feature flags, rollouts and experiments. The hosted MCP server uses OAuth with dynamic client registration and marks its tools read-only or destructive, and the Developer plan is free without a card. The server lists 141 tools, numeric rate limits are unpublished, and the web application was unavailable for over an hour on 10 July 2026.
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
LaunchDarkly
- Connect to https://mcp.launchdarkly.com/mcp/launchdarkly over streamable HTTP with OAuth. On the EU or federal instance run the local
@launchdarkly/mcp-serverwith--server-url - Authorise with a Reader role or the
readerscope unless the task writes. A 403 after consent means the member's role lacks access - Send
LD-API-Version: 20240415on every REST call, andLD-API-Version: betafor beta resources, which answer 403 without it - Read
X-Ratelimit-Global-Remaining,X-Ratelimit-Route-RemainingandX-Ratelimit-Reseton each response, and waitRetry-Afterseconds on an IP limit - Send
Content-Type: application/json; domain-model=launchdarkly.semanticpatchfor semantic patches, or the body is read as JSON patch and answers 400
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, LaunchDarkly or Statsig?
Statsig scores 72.3 (BB) on agent readiness against LaunchDarkly's 69.2 (B), and leads in 3 of 7 scored categories. LaunchDarkly leads on schema & documentation and transparency & trust.
Do LaunchDarkly and Statsig need an API key?
Both take an API key or an OAuth sign-in.
Can an agent call LaunchDarkly and Statsig without installing anything?
Yes. LaunchDarkly has a hosted endpoint at https://mcp.launchdarkly.com/mcp/launchdarkly and Statsig at https://api.statsig.com/v3/mcp.
Other comparisons with LaunchDarkly or Statsig
Machine-readable
- This page as Markdown
/compare/launchdarkly-vs-statsig.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/launchdarkly.json·/api/v1/tools/statsig.json - From a terminal
anchor compare launchdarkly statsig(the CLI) - Over MCP
compare_tools {"a": "launchdarkly", "b": "statsig"}at/mcp, no key