# Featureflip (npm · @featureflip/mcp)

Manage Featureflip feature flags, targeting and rollouts from AI agents and editors.

- Trust score: 71/100 (medium)
- Change this week: +32
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-20

## Components

- npm · `@featureflip/mcp`: 71/100 (this document), [markdown](https://verifymcp.io/servers/canopy-labs-featureflip/featureflip-mcp.md), [page](https://verifymcp.io/servers/canopy-labs-featureflip/featureflip-mcp)

## Channel facts

- Registry: `npm`
- Package: `@featureflip/mcp`
- Version: `0.1.7`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-09-20.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 0 of 3 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 48/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (Apache-2.0).
  - Actively maintained (last published 1 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 74/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 1558 tokens (~82/item across 19 items; 19 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 13/100
  - Stability observed for 4 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 80/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 39% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 19 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the Featureflip MCP server?

Featureflip runs locally as an npm package, launched with npx -y @featureflip/mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add canopy-labs-featureflip -- npx -y @featureflip/mcp
```

### Cursor

```json
{
  "mcpServers": {
    "canopy-labs-featureflip": {
      "command": "npx",
      "args": [
        "-y",
        "@featureflip/mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "canopy-labs-featureflip": {
      "command": "npx",
      "args": [
        "-y",
        "@featureflip/mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add canopy-labs-featureflip -- npx -y @featureflip/mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "canopy-labs-featureflip": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@featureflip/mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add canopy-labs-featureflip --command npx --arg -y --arg @featureflip/mcp
```

### Hermes

```yaml
mcp_servers:
  canopy-labs-featureflip:
    command: "npx"
    args: ["-y", "@featureflip/mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "canopy-labs-featureflip": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@featureflip/mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add canopy-labs-featureflip -t stdio -c npx -a -y @featureflip/mcp
```

### Other

```json
{
  "mcpServers": {
    "canopy-labs-featureflip": {
      "command": "npx",
      "args": [
        "-y",
        "@featureflip/mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-09-20 (score 71, +1)

- [functional improvement] Security disclosure: fail → pass

### 2026-09-18 (score 70, +1)

- [functional improvement] Stability: unverified → 0.07
- [functional] Package version: 0.1.6 → 0.1.7

### 2026-09-17 (score 69, +26)

- [security improvement] Malware scan: unverified → pass
- [security improvement] Known CVEs: unverified → pass
- [functional improvement] Dependency health: unverified → 1.00

### 2026-09-16 (score 43, +4)

- [security regression] Known CVEs: pass → unverified
- [security regression] Malware scan: pass → unverified
- [security improvement] Injection markers: unverified → pass
- [security] First check of Judged manipulation: pass
- [security] Tool safety: Tool safety not yet verified: we do not have a sandbox capture of the tool definitions this version of the package serves yet.
- [security] Stability: Stability not yet verified: we do not have a sandbox capture of the MCP schema this version of the package serves yet.
- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional regression] Dependency health: 1.00 → unverified
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] MCP protocol: unverified → pass
- [functional] First check of Schema quality: fail
- [functional] First check of Tool coverage: 38
- [functional] First check of Destructive annotations: 100
- [functional] First check of Schema quality: pass
- [functional] First check of Schema quality: good
- [functional] Capabilities: Protocol version not yet verified: we do not have a sandbox capture of the MCP handshake this version of the package performs yet.
- [functional] Tool coverage: Tool coverage not yet verified: we do not have a sandbox capture of the tool definitions this version of the package serves yet.
- [functional] Schema quality: Schema quality not yet verified: we do not have a sandbox capture of the MCP schema this version of the package serves yet.
- [functional] Package version: 0.1.4 → 0.1.6
- [functional] Package version: 0.1.4 → 0.1.5

### 2026-08-29 (score 39)

First indexed and scored.

## MCP tools (19)

### `list_projects` (~53 tokens)

List projects

List projects in the Featureflip organization. Paginated: pass cursor from next_cursor to continue.

Input parameters:

- `cursor` (string): next_cursor from a previous response
- `limit` (integer): Page size (default 20)

### `list_environments` (~48 tokens)

List environments

List the environments of a project (e.g. development, staging, production).

Input parameters:

- `cursor` (string)
- `limit` (integer)
- `project` (string, required): Project key

### `list_segments` (~51 tokens)

List user segments

List reusable user segments in a project. Segments are referenced from targeting rules via userSegmentId.

Input parameters:

- `cursor` (string)
- `limit` (integer)
- `project` (string, required): Project key

### `get_segment` (~46 tokens)

Get user segment

Get one user segment (its conditions, id, and metadata) by key or id.

Input parameters:

- `project` (string, required): Project key
- `segment` (string, required): Segment key or id

### `list_flags` (~94 tokens)

List feature flags

List feature flags in a project. Filter with search (key/name substring), tag, type, archived. Paginated via cursor.

Input parameters:

- `archived` (boolean): true = only archived, false = only active
- `cursor` (string)
- `limit` (integer)
- `project` (string, required): Project key
- `search` (string)
- `tag` (string)
- `type` (string)

### `get_flag` (~45 tokens)

Get feature flag

Get one feature flag with its variations and metadata. Address by flag key or id.

Input parameters:

- `flag` (string, required): Flag key or id
- `project` (string, required): Project key

### `create_flag` (~155 tokens)

Create feature flag

Create a feature flag. type is one of Boolean|String|Number|Json. Boolean flags get true/false variations automatically; for other types pass initialVariations. The flag is created in every environment of the project (disabled).

Input parameters:

- `clientSideVisible` (boolean): Expose to client-side SDKs (browser/mobile)
- `description` (string)
- `idempotency_key` (string): Idempotency-Key header for safe retries
- `initialVariations` (array)
- `key` (string, required): Unique flag key, e.g. checkout-v2
- `name` (string, required)
- `project` (string, required): Project key
- `tags` (array)
- `type` (string, required)

### `update_flag` (~84 tokens)

Update feature flag metadata

Update flag name/description/tags/clientSideVisible. Key and type are immutable. Use toggle_flag / update_targeting for behavior changes.

Input parameters:

- `clientSideVisible` (boolean)
- `description` (string)
- `flag` (string, required): Flag key or id
- `name` (string)
- `project` (string, required)
- `tags` (array)

### `delete_flag` (~65 tokens)

Delete feature flag

PERMANENTLY delete a flag across all environments. Fails with FLAG_HAS_DEPENDENTS if other flags use it as a prerequisite. Prefer archive_flag unless the flag must be fully removed.

Input parameters:

- `flag` (string, required): Flag key or id
- `project` (string, required)

### `archive_flag` (~135 tokens)

Archive feature flag

Archive a flag (soft-hide, evaluation stops serving it). Reversible with restore_flag. Refused with FLAG_RECENTLY_EVALUATED while live traffic is still evaluating the flag, because archiving makes every caller fall back to its own hardcoded default — normally that means the code removal has merged but not deployed yet, and the refusal clears itself once it has.

Input parameters:

- `flag` (string, required)
- `force` (boolean): Archive even though traffic is still evaluating the flag. Only for clients that can never be updated (old mobile app versions), where traffic will never drain on its own.
- `project` (string, required)

### `restore_flag` (~28 tokens)

Restore archived flag

Restore a previously archived flag.

Input parameters:

- `flag` (string, required)
- `project` (string, required)

### `toggle_flag` (~67 tokens)

Toggle flag in environment

Enable or disable a flag in ONE environment. Affects live evaluation immediately — double-check the environment.

Input parameters:

- `enabled` (boolean, required)
- `environment` (string, required): Environment key, e.g. production
- `flag` (string, required): Flag key or id
- `project` (string, required)

### `update_flag_environment_config` (~160 tokens)

Update flag environment config

Update a flag's per-environment serving config: defaultVariationId (served on fallthrough, required), strategy (SingleVariation | PercentageRollout | TargetedRollout — only SingleVariation is currently supported at the environment level), and prerequisites. Percentage rollouts are configured on targeting rules via update_targeting.

Input parameters:

- `defaultVariationId` (string, required): Variation id to serve on fallthrough — required by the API
- `environment` (string, required)
- `flag` (string, required)
- `prerequisites` (array): Flags that must evaluate to the expected variation before this flag serves. Omit to leave existing prerequisites untouched; pass a list (possibly empty) to replace them wholesale.
- `project` (string, required)
- `strategy` (string)

### `flag_status` (~44 tokens)

Flag status across environments

Compact cross-environment view of one flag: enabled state, strategy, default variation, and prerequisites per environment.

Input parameters:

- `flag` (string, required)
- `project` (string, required)

### `get_targeting` (~48 tokens)

Get targeting rules

Get a flag's current targeting configuration (enabled flag + ordered rules) in one environment.

Input parameters:

- `environment` (string, required)
- `flag` (string, required)
- `project` (string, required)

### `update_targeting` (~74 tokens)

Replace targeting rules

REPLACE all targeting rules of a flag in one environment (full PUT — rules not included are removed). Rules are evaluated in order. Get the current rules first with get_targeting.

Input parameters:

- `environment` (string, required)
- `flag` (string, required)
- `project` (string, required)
- `rules` (array, required)

### `manage_variation` (~133 tokens)

Add, update, or remove a variation

Manage a flag's variations. action=add requires key + value; action=update/remove require variationId (get ids via get_flag). Removing a variation fails with VARIATION_HAS_DEPENDENTS if other flags depend on it.

Input parameters:

- `action` (string, required)
- `description` (string)
- `flag` (string, required)
- `key` (string): Required for add; immutable afterwards
- `name` (string)
- `project` (string, required)
- `value` (string): Variation value serialized as a string; required for add
- `variationId` (string): Required for update/remove

### `find_stale_flags` (~90 tokens)

Find stale flags

Find flags that look ready for code cleanup: not updated in N days AND either enabled in every environment (verify rollout is complete before removing — per-rule percentage ramps are not inspected) or disabled in every environment (dead — remove flag and code path). Checks at most 50 candidates per call.

Input parameters:

- `days` (integer): Minimum age in days since last update
- `project` (string, required)

### `wrap_feature` (~138 tokens)

Wrap a feature in a new flag

Create a Boolean feature flag and get back the SDK code snippet to guard the new code path with it. Returns the snippet only — apply the edit yourself. The flag starts DISABLED in every environment; enable it with toggle_flag when ready.

Input parameters:

- `description` (string): What this flag guards
- `idempotency_key` (string)
- `key` (string, required): Flag key, e.g. new-checkout
- `language` (string, required): SDK language of the codebase being edited
- `name` (string): Display name; defaults to the key
- `project` (string, required): Project key
- `tags` (array)

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/canopy-labs-featureflip/featureflip-mcp#diagnostics

## Score history

- 2026-09-20: 71
- 2026-09-19: 70
- 2026-09-18: 70
- 2026-09-17: 69
- 2026-09-16: 43
- 2026-09-15: 39
- 2026-09-14: 39
- 2026-09-13: 39
- 2026-09-12: 39
- 2026-09-11: 39
- 2026-09-10: 39
- 2026-09-09: 39
- 2026-09-08: 39
- 2026-09-07: 39
- 2026-09-06: 39
- 2026-09-05: 39
- 2026-09-04: 39
- 2026-09-03: 39
- 2026-09-02: 39
- 2026-09-01: 39
- 2026-08-31: 39
- 2026-08-30: 39
- 2026-08-29: 39

## Common questions

### What is the Featureflip MCP server?

Featureflip is an MCP server listed in the public MCP registry as io.github.canopy-labs/featureflip. Manage Featureflip feature flags, targeting and rollouts from AI agents and editors. This page covers its npm package (@featureflip/mcp).

### Is the Featureflip MCP server safe to use?

Featureflip scores 71 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Featureflip MCP server expose?

Featureflip exposes 19 tools: list_projects, list_environments, list_segments, get_segment, list_flags, and 14 more. Their descriptions and schemas cost roughly 1,558 tokens of context every time the server is loaded.

### Is the Featureflip MCP server still maintained?

Featureflip is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the Featureflip MCP server under?

Featureflip declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- npm package: https://www.npmjs.com/package/@featureflip/mcp
- Socket report: https://socket.dev/npm/package/@featureflip/mcp
- Repository: https://github.com/canopy-labs/featureflip-mcp
- Website: https://featureflip.io/docs/integrations/mcp/
- Changelog RSS feed: https://verifymcp.io/servers/canopy-labs-featureflip/featureflip-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/canopy-labs-featureflip/featureflip-mcp.json
- HTML version of this page: https://verifymcp.io/servers/canopy-labs-featureflip/featureflip-mcp