# Harness Feature Management & Experimentation (slim)

> Harness Feature Management & Experimentation (FME), formerly Split, manages feature flags, targeting, metrics and experiments. Agents reach it through the Admin API at api.split.io and the FME toolset of the Harness MCP server.

- Full: https://www.anchorterminal.com/tools/harness-fme.md (~7,450 tokens) · this version ~1,580 tokens · JSON https://www.anchorterminal.com/tools/harness-fme.json · canonical https://www.anchorterminal.com/tools/harness-fme
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-07 · pricing https://www.anchorterminal.com/tools/harness-fme#pricing · reviews https://www.anchorterminal.com/tools/harness-fme#reviews
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

**B · 69.2/100 · rank #257 of 1486 · #4 in Product analytics & experimentation · not agent-ready · confidence medium**


Assessment: 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.

## Facts

- Kind: HTTP API · vendor: Harness Inc. · category: Product analytics & experimentation · legal entity: Harness Inc. · provenance 61/100
- Endpoint: `https://mcp.harness.io/mcp` (HTTP, stdio, Streamable HTTP)
- Auth: OAuth or key · pricing: Freemium · x402: no · licence: unknown
- Benchmark probes: not run yet, so Performance is pending
- Live, from our pollers (not part of the score): up at 2026-11-07 18:20 UTC · uptime 30 days 100.0% (200 probes) · p50 195 ms · p95 280 ms over 24 hours
- Vendor status page: no problems reported, All Systems Operational (2026-11-07 18:21 UTC)
- Surface listed: The FME Admin API at api.split.io (reference at docs.split.io) and the FME toolset of the Harness MCP server, local through npm or hosted at mcp.harness.io, read from developer.harness.io, docs.split.io, the harness/mcp-server repository, harness.io pricing, security and privacy pages and status.harness.io on 6 November 2026. No account was made and no tool was called
- Which product: Split Software's feature flag and experimentation platform, part of Harness since 2024 and sold as the FME module. Harness also has an older Feature Flags (FF) module, a separate product on the same status page
- FME resource types: fme_workspace, fme_environment, fme_feature_flag (list, get, create, update, delete, kill, restore, archive), fme_feature_flag_definition, fme_rule_based_segment, fme_rule_based_segment_definition and fme_rollout_status
- Admin API: Projects, environments, feature flags and definitions, segments, rule-based and large segments, change requests, identities, attributes, events, flag sets, groups, restrictions and API keys, with a Postman collection, a Python wrapper and a CLI
- Skills: The harness-fme Claude Code plugin packages 16 skills for flags, segments, metrics, experiments and rollout pipelines
- Rate limits: About 20 Admin API requests per 10 seconds per organisation and per IP; SDK evaluation traffic is not limited by it
- Legal entity: Harness Inc., 55 Stockton St, 8th Floor, San Francisco, per the privacy statement

- Scores: Reliability 80, Performance pending, Schema & documentation 71, Agent ergonomics 83, Security & auth 79, Payments & pricing 15, Task success pending, Maintenance & community 81, Transparency & trust 61 · total over the 7 assessed categories
- Why: Reliability, Graded on the hosted FME Admin API with the hosted lines. · Schema & documentation, No public OpenAPI file for the Admin API was found; the reference is a ReadMe site with a Postman collection. · Agent ergonomics, 11 consolidated tools, and `--toolsets=fme` narrows the server to FME (25). · Security & auth, Admin API keys with combinable roles that can't be widened after creation, Harness PATs and SATs for central management, and Harness Platfor… · Payments & pricing, No x402, MPP or L402 (0). · Maintenance & community, harness-mcp-v2 3.2.40 was tagged on 4 November 2026 (30). · Transparency & trust, A closed service under Harness's subscription terms; the MCP server is MIT (18 of 30).
- Sources: 13, open questions: 6, both in the full twin
- Capabilities: analytics.flags, analytics.experiments, analytics.events
- JSON: https://www.anchorterminal.com/api/v1/tools/harness-fme.json
- Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/harness-fme.svg` or a link to https://www.anchorterminal.com/tools/harness-fme from a page on harness.io or one of its subdomains, or the README at the root of github.com/harness/mcp-server, then `POST https://www.anchorterminal.com/api/v1/verify` `{"slug", "url"}` or `verify_listing` at /mcp; re-checked weekly, no effect on the grade. Snippets in the full twin.
- Support: security@harness.io; https://developer.harness.io/feature-management-experimentation/feature-management-and-experimentation-documentation; https://status.harness.io; more in the full twin

## Before you call it

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

## Connect

```bash
npx harness-mcp-v2@latest
```
Full config and headless snippets are in the full page. Through letme (picks today, calling later): https://letme.dev/harness-fme

## Similar tools

| Tool | Grade | Score | Shared capabilities | Slim |
| --- | --- | --- | --- | --- |
| Statsig | BB | 72.4 | analytics.experiments, analytics.flags, analytics.events | https://www.anchorterminal.com/tools/statsig.min.md |
| Amplitude | B | 69.3 | analytics.experiments, analytics.flags, analytics.events | https://www.anchorterminal.com/tools/amplitude.min.md |
| GrowthBook | B | 68.6 | analytics.experiments, analytics.flags, analytics.events | https://www.anchorterminal.com/tools/growthbook.min.md |
| PostHog | B | 67.4 | analytics.events, analytics.experiments, analytics.flags | https://www.anchorterminal.com/tools/posthog.min.md |
| Mixpanel | B | 62 | analytics.events, analytics.experiments, analytics.flags | https://www.anchorterminal.com/tools/mixpanel.min.md |


## Panel reviews (0, desk reviews from public material, no calls made)