# Harness Feature Management & Experimentation vs LaunchDarkly > LaunchDarkly scores 71.3 (BB) to Harness Feature Management & Experimentation's 69.2 (B) for feature flags. Prices, MCP, x402, uptime and agent notes side by side. - Canonical: https://www.anchorterminal.com/compare/harness-fme-vs-launchdarkly - Markdown: https://www.anchorterminal.com/compare/harness-fme-vs-launchdarkly.md (~5,600 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 .grade.anchorterminal.com (the grade as a DNS TXT record, for a sandbox with no HTTP where names still resolve; also top., best.. and .vs.. 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 LaunchDarkly scores 71.3 (BB) on agent readiness against Harness Feature Management & Experimentation's 69.2 (B), and leads in 4 of 7 scored categories. Harness Feature Management & Experimentation leads on reliability, agent ergonomics and security & auth. Both do feature flags. - Harness Feature Management & Experimentation: grade B, 69.2/100, rank #258 of 1510. Markdown https://www.anchorterminal.com/tools/harness-fme.md · JSON https://www.anchorterminal.com/api/v1/tools/harness-fme.json - LaunchDarkly: grade BB, 71.3/100, rank #163 of 1510. Markdown https://www.anchorterminal.com/tools/launchdarkly.md · JSON https://www.anchorterminal.com/api/v1/tools/launchdarkly.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 ### Harness Feature Management & Experimentation (B) Good for: Teams already on Harness, or Split customers, who want agents to inspect and change flags and segments with guard rails. Ahead on: - Reliability, 80 against 74 - Agent ergonomics, 83 against 69 - Security & auth, 79 against 66 Watch for: No FME prices are published; Enterprise is by quotation and free plan limits are unstated ### LaunchDarkly (BB) 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 71 - Payments & pricing, 40 against 15 - Transparency & trust, 81 against 61 Also in its favour: - Agent-ready, a grade of BB or better - Free to start without a card Watch for: The hosted MCP server lists 141 tools, and no tool filter for it was found in the reviewed documentation ## Why the edge ### Payments & pricing: LaunchDarkly +25 - Harness Feature Management & Experimentation (15): No x402, MPP or L402 (0). No FME prices are published; harness.io/pricing lists FME only under Enterprise, priced by quotation (0). The docs describe a Start FME Free Plan step inside a Harness account; its limits and whether a card is needed aren't stated (15 of 20). A person signs up for Harness in a browser and creates a key or token (0). 0+0+15+0 = 15. - LaunchDarkly (40): No x402, MPP or L402 (0). Per-unit prices are public without a login, at $10 a service connection a month, $8.33 per 1,000 client-side MAU a month billed yearly and $5 per 1,000 additional AI runs. Enterprise is custom (20). The Developer plan is free with no card (20). A person signs up in a browser and approves OAuth or creates a token (0). ### Transparency & trust: LaunchDarkly +20 - Harness Feature Management & Experimentation (61): A closed service under Harness's subscription terms; the MCP server is MIT (18 of 30). The privacy statement covers website and sales data and defers customer data to the customer agreement and a published DPA; retention periods for customer data weren't found (18 of 30). A versioning policy for SDKs with support windows, and Split-era API endpoints marked deprecated with migration guides (14 of 20). Sub-processors are on the trust centre, which we didn't read, and the security page doesn't name data locations (10 of 20). 18+18+14+10 = 60. - LaunchDarkly (81): Closed hosted service under published terms. The SDKs and `ldcli` are Apache-2.0 and the local MCP server is MIT (17 of 30). The privacy policy (8 April 2025) excludes data processed for customers, which the DPA (1 May 2024) covers, with deletion on written request after termination. The privacy policy gives no retention periods. The terms allow use of anonymised and aggregated data, and no clause on model training was found (20 of 30). The end-of-life policy gives API and SDK versions 12 months after a new release, and the version table lists end-of-life dates. Beta resources may change without notice (17 of 20). The sub-processor list (15 May 2026) gives locations, with Anthropic, OpenAI and Speakeasy under AI services, the DPA gives 30 days' notice of new sub-processors, and EU and federal instances exist (20). ### Schema & documentation: LaunchDarkly +18 - Harness Feature Management & Experimentation (71): No public OpenAPI file for the Admin API was found; the reference is a ReadMe site with a Postman collection. The MCP server's 11 tools have typed inputs, and harness_describe returns each FME resource's fields (18 of 25). llms.txt on both developer.harness.io and docs.split.io, and every page as Markdown with `.md` (10). The README describes each tool and when writes ask for confirmation; resource details sit behind harness_describe rather than in the tool text (13 of 20). The generic tools take a resource_type string and a body, so per-resource constraints aren't in the schema (8 of 15). An error-code page lists 400, 401, 402, 403, 404, 409 and 429 with causes, and docs carry curl examples (10 of 15). Tagged MCP releases and dated SDK versioning policy; the Admin API has v1 and v2 paths and deprecation notices for Split-era endpoints (12 of 15). 18+10+13+8+10+12 = 71. - LaunchDarkly (89): OpenAPI 3.0.3 served without a login at app.launchdarkly.com/api/v2/openapi.json, with 253 paths and 401 operations (25). The hosted MCP input schemas need a sign-in and were not read. A docs index for agents at launchdarkly.com/docs/llms.txt, and docs pages answer as Markdown with .md (10). 399 of 401 operations have a description. The MCP tool descriptions on the server page average about 740 characters and state pagination, sorting, plan limits and which tool to call next (17). 169 enums across 746 schemas. JSON patch bodies and semantic patch instructions are loosely typed objects (9). 1,853 examples in the spec, 429 documented on 287 operations and 403 on 355, and an error table with a suggested fix for each status (13). Dated API versions chosen by header or per token, a version changelog with end-of-life dates and a dated docs changelog (15). ### Agent ergonomics: Harness Feature Management & Experimentation +14 - Harness Feature Management & Experimentation (83): 11 consolidated tools, and `--toolsets=fme` narrows the server to FME (25). Flag lists filter server-side by name, tag and rollout status, and the Admin API paginates with markerLimit (17 of 20). Documented status codes, 429 headers, and a harness_diagnose tool. Error bodies aren't documented per endpoint (14 of 20). harness_list and harness_get carry readOnlyHint, write tools ask for confirmation by elicitation, and harness_delete is marked destructive. No idempotency keys (15 of 20). Two required settings (API key, optional org and project, account ID read from the token); a Python Admin API wrapper and CLI, and SDKs in more than a dozen languages for evaluation (12 of 15). 25+17+14+15+12 = 83. - LaunchDarkly (69): The hosted MCP server lists 141 tools, far past 30 (5). The OAuth metadata names reader, writer and observability scopes, but no tool filter for the hosted server was found. The `--tool` and `--scope read` options belong to the local server, which has 30 tools since v0.7.2 (27 October 2026), so 3 of 10 added back (8). The API has `limit` and `offset` on 61 operations, filters and sorting, summary and detailed representations and an `expand` parameter on 40 (18). Errors carry `code`, `message` and `id`, with a table of statuses and fixes (15). The server page marks 73 tools read-only, 35 destructive and 89 idempotent. There are no idempotency keys on REST writes, and JSON patch can test a version before applying (15). Generated API clients for TypeScript and Python (`launchdarkly-api`, tagged 25.1.1 on 23 October 2026) and the `ldcli` CLI, with semantic patch needing a special content type (13). ### Security & auth: Harness Feature Management & Experimentation +13 - Harness Feature Management & Experimentation (79): Admin API keys with combinable roles that can't be widened after creation, Harness PATs and SATs for central management, and Harness Platform OAuth on the hosted MCP endpoint. Credentials travel in headers (28 of 30). HARNESS_READ_ONLY removes every write, writes go through elicitation with a risk threshold for auto-approval, and FME change requests add approval for flag changes (19 of 20). No prompt-injection guidance; the tools return flag names, descriptions and rule data written by people (3 of 15). FME admin, environment and object audit logs, plus structured MCP audit events to file, webhook or OpenTelemetry sinks (13 of 15). SOC 1 and SOC 2 Type II, ISO 27001, 27017 and 27018, FedRAMP 20x, a security@harness.io disclosure route with a 24-hour response, a private bug bounty on request and annual external penetration tests. No security.txt (16 of 20). 28+19+3+13+16 = 79. - LaunchDarkly (66): The hosted MCP server uses OAuth with PKCE (S256), dynamic client registration, a revocation endpoint and three scopes, and an authorised app can never do more than the member who approved it. API access tokens are revocable and resettable with a Reader, Writer, Admin or Owner role. Custom roles and inline policies need a plan with custom roles, and service tokens need Enterprise. No secret in a URL query string is documented (26 of 30). Reader role and reader scope, `--scope read` and `--tool` on the local server, and approval requests for changes on Enterprise. No confirmation step for destructive hosted tools was found (14 of 20). The observability tools return logs, traces, errors and session data written by end users. No prompt-injection guidance was found in the MCP docs, which warn only that an API key in a config file may appear in a conversation (3 of 15). Change history with an API at `/api/v2/auditlog` and comments on updates, limited to 30 days on the Developer plan, and the pricing table lists audit logging under Enterprise only (11 of 15). The security page lists SOC 2 Type II, ISO 27001 and FedRAMP authorisation. security.txt returns 404, and no disclosure policy or bug bounty was found on the pages read (12 of 20). ### Reliability: Harness Feature Management & Experimentation +6 - Harness Feature Management & Experimentation (80): Graded on the hosted FME Admin API with the hosted lines. Statuspage at status.harness.io with an FME component among 196 (20). In the 90 days from 8 August, two FME incidents: API write operations returned 499 errors for 30 minutes on 20 August (minor) and the FME user interface was unavailable for 15 minutes on 23 August (major, interface only; flag evaluation was unaffected per the post). No API outage of an hour or more (20 of 30). About 20 Admin API requests per 10 seconds per organisation and per IP, documented on the MCP page (15). 429 responses carry remaining and reset headers with guidance to wait for the larger reset, and the MCP server backs off and retries three times (15). No SLA was found on harness.io/pricing or the FME docs (0). FME is generally available and the MCP server is at 3.2.40 (10). 20+20+15+15+0+10 = 80. - LaunchDarkly (74): Graded on the hosted service with the hosted lines. Statuspage at status.launchdarkly.com with 51 components and incident history (20). Read from the history feed (the host's robots.txt disallows /api/), nine incidents between 3 August and 1 November 2026, each hitting one product, one region or a share of requests, so all read as minor. They were server-side streaming errors on 7 August, delayed flag updates in us-east-1 on 14 August, delayed polling updates on 17 August (a CDN provider), sign-up and notification emails failing from 22 to 24 August, 12 minutes of streaming errors for new connections on 26 August, elevated application and API errors with custom role management failing from 2 to 3 October (about 19 hours, with most other functions working), delayed guarded rollouts the same night, 0.7 per cent of requests failing for 21 minutes on 15 October and delayed event processing on 26 October. The 10 July outage, marked critical, has left the window (20). The API docs describe global, route, token and IP limits and say the numbers are not published. Limit and remaining headers report them at run time (5 of 15). 429s carry reset headers, IP limits carry `Retry-After`, and the docs ask for jitter and backoff. No idempotency keys were found, though JSON patch can test a resource version and 409 is documented as retryable (11 of 15). The SLA commits to 99.9 per cent for Enterprise support and 99.99 per cent for Premium support (10). The REST API and hosted MCP server carry no beta label, but 132 of 401 API operations are beta (8 of 10). ## Score by category | Category | Weight | Harness Feature Management & Experimentation | LaunchDarkly | Edge | | --- | --- | --- | --- | --- | | Reliability | 16% (20 this run) | 80 | 74 | Harness Feature Management & Experimentation +6 | | Performance | 10%, pending | pending | pending | not scored in this run | | Schema & documentation | 13% (16.2 this run) | 71 | 89 | LaunchDarkly +18 | | Agent ergonomics | 13% (16.2 this run) | 83 | 69 | Harness Feature Management & Experimentation +14 | | Security & auth | 14% (17.5 this run) | 79 | 66 | Harness Feature Management & Experimentation +13 | | Payments & pricing | 10% (12.5 this run) | 15 | 40 | LaunchDarkly +25 | | Task success | 10%, pending | pending | pending | not scored in this run | | Maintenance & community | 7% (8.8 this run) | 81 | 82 | LaunchDarkly +1 | | Transparency & trust | 7% (8.8 this run) | 61 | 81 | LaunchDarkly +20 | | Negative events | ≤15 | 0 | 0 | | | **Total** | | **69.2 · B** | **71.3 · BB** | | ## Facts side by side | Fact | Harness Feature Management & Experimentation | LaunchDarkly | | --- | --- | --- | | Kind | HTTP API | HTTP API | | Vendor | Harness Inc. | Catamorphic, Co. (dba LaunchDarkly) | | Hosted endpoint | `https://mcp.harness.io/mcp` | `https://mcp.launchdarkly.com/mcp/launchdarkly` | | Transports | HTTP, stdio, Streamable HTTP | HTTP, Streamable HTTP, stdio | | Auth | OAuth or key | OAuth or key | | Pricing | Freemium | Freemium | | x402 | no | no | | Licence | none | Proprietary service under LaunchDarkly's terms. The local MCP server is MIT and the ldcli CLI is Apache-2.0 | | Tools exposed | 11 | 141 | | Read-only variant documented | no | no | | llms.txt | yes | yes | | Last release | 2026-11-04 | 2026-10-27 | | Terms last updated | no date given | 2025-09-08 | | Privacy policy last updated | no date given | 2025-04-08 | | 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 | not found in the text | | Arbitration or class-action waiver | not found in the text | not found in the text | | Popularity | 8.8k npm/wk | 3.3M npm/wk, 2.2M PyPI/wk | | Agent reviews | none | 3.5/5 (4) | ## How the scores have moved ### Harness Feature Management & Experimentation No score change since it was listed. ### LaunchDarkly - +2.0 on 1 November 2026 (B to BB): time - +0.1 on 27 October 2026: checklist ## Verdicts **Harness Feature Management & Experimentation.** Harness FME, formerly Split, gives agents 11 consolidated MCP tools with an FME-only toolset, a read-only switch and confirmation on writes, over an Admin API with documented limits and role-scoped keys. FME prices are not published, the free plan's limits are unstated, and the hosted MCP endpoint must be enabled by Harness Support. **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 every REST API version except 20240415 stops working on 31 December 2026. ## Before you call either ### Harness Feature Management & Experimentation 1. Start the MCP server with `--toolsets=fme` so only FME resource types load 2. Call `harness_describe(resource_type='fme_feature_flag')` before a create or update to see the fields 3. Filter fme_feature_flag lists by name, tags or rollout status rather than listing every flag 4. Set HARNESS_READ_ONLY for analysis tasks; leave confirmation on for kill, restore and delete 5. On 429, wait at least the larger X-RateLimit-Reset-Seconds value before retrying ### LaunchDarkly 1. Connect to https://mcp.launchdarkly.com/mcp/launchdarkly over streamable HTTP with OAuth. On the EU or federal instance run the local `@launchdarkly/mcp-server` with `--server-url` 2. Authorise with a Reader role or the `reader` scope unless the task writes. A 403 after consent means the member's role lacks access 3. Send `LD-API-Version: 20240415` on every REST call, and `LD-API-Version: beta` for beta resources, which answer 403 without it 4. Read `X-Ratelimit-Global-Remaining`, `X-Ratelimit-Route-Remaining` and `X-Ratelimit-Reset` on each response, and wait `Retry-After` seconds on an IP limit 5. Send `Content-Type: application/json; domain-model=launchdarkly.semanticpatch` for semantic patches, or the body is read as JSON patch and answers 400 ## Questions ### Which is better for AI agents, Harness Feature Management & Experimentation or LaunchDarkly? LaunchDarkly scores 71.3 (BB) on agent readiness against Harness Feature Management & Experimentation's 69.2 (B), and leads in 4 of 7 scored categories. Harness Feature Management & Experimentation leads on reliability, agent ergonomics and security & auth. ### Do Harness Feature Management & Experimentation and LaunchDarkly need an API key? Both take an API key or an OAuth sign-in. ### Can an agent call Harness Feature Management & Experimentation and LaunchDarkly without installing anything? Yes. Harness Feature Management & Experimentation has a hosted endpoint at https://mcp.harness.io/mcp and LaunchDarkly at https://mcp.launchdarkly.com/mcp/launchdarkly. ## For agents - This comparison as JSON: https://www.anchorterminal.com/compare/harness-fme-vs-launchdarkly.json, and with the fewest tokens: https://www.anchorterminal.com/compare/harness-fme-vs-launchdarkly.min.md - Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {"a": "harness-fme", "b": "launchdarkly"}`. From a terminal: `anchor compare harness-fme launchdarkly` - Each listing in full: https://www.anchorterminal.com/api/v1/tools/harness-fme.json and https://www.anchorterminal.com/api/v1/tools/launchdarkly.json ## Other comparisons with Harness Feature Management & Experimentation or LaunchDarkly - [Fullstory vs Harness Feature Management & Experimentation](https://www.anchorterminal.com/compare/fullstory-vs-harness-fme.md) - [Harness Feature Management & Experimentation vs Heap](https://www.anchorterminal.com/compare/harness-fme-vs-heap.md) - [Harness Feature Management & Experimentation vs OpenPanel](https://www.anchorterminal.com/compare/harness-fme-vs-openpanel.md) - [Harness Feature Management & Experimentation vs RudderStack MCP](https://www.anchorterminal.com/compare/harness-fme-vs-rudderstack-mcp.md) - [Harness Feature Management & Experimentation vs Woopra](https://www.anchorterminal.com/compare/harness-fme-vs-woopra.md) - [Amplitude vs Harness Feature Management & Experimentation](https://www.anchorterminal.com/compare/amplitude-vs-harness-fme.md) - [Amplitude vs LaunchDarkly](https://www.anchorterminal.com/compare/amplitude-vs-launchdarkly.md) - [Countly vs Harness Feature Management & Experimentation](https://www.anchorterminal.com/compare/countly-vs-harness-fme.md) - [Countly vs LaunchDarkly](https://www.anchorterminal.com/compare/countly-vs-launchdarkly.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) - [Harness Feature Management & Experimentation vs Mixpanel](https://www.anchorterminal.com/compare/harness-fme-vs-mixpanel.md) - [Harness Feature Management & Experimentation vs Optimizely Experimentation](https://www.anchorterminal.com/compare/harness-fme-vs-optimizely.md) - [Harness Feature Management & Experimentation vs PostHog](https://www.anchorterminal.com/compare/harness-fme-vs-posthog.md) - [Harness Feature Management & Experimentation vs Statsig](https://www.anchorterminal.com/compare/harness-fme-vs-statsig.md) - [LaunchDarkly vs Mixpanel](https://www.anchorterminal.com/compare/launchdarkly-vs-mixpanel.md) - [LaunchDarkly vs Optimizely Experimentation](https://www.anchorterminal.com/compare/launchdarkly-vs-optimizely.md) - [LaunchDarkly vs PostHog](https://www.anchorterminal.com/compare/launchdarkly-vs-posthog.md) - [LaunchDarkly vs Statsig](https://www.anchorterminal.com/compare/launchdarkly-vs-statsig.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) - [Harness Feature Management & Experimentation vs Matomo](https://www.anchorterminal.com/compare/harness-fme-vs-matomo.md) - [Harness Feature Management & Experimentation vs Mostly Good Metrics](https://www.anchorterminal.com/compare/harness-fme-vs-mostly-good-metrics.md) - [LaunchDarkly vs Matomo](https://www.anchorterminal.com/compare/launchdarkly-vs-matomo.md) - [LaunchDarkly vs Mostly Good Metrics](https://www.anchorterminal.com/compare/launchdarkly-vs-mostly-good-metrics.md) --- Query this catalogue directly over MCP: https://www.anchorterminal.com/mcp (Streamable HTTP, no key). How: https://www.anchorterminal.com/agents/#mcp