Featureflip

io.github.canopy-labsPublished by GitHub account canopy-labsv0.9.0Updated Nov 7, 2026

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

VerifiedSTDIODesktop onlyProductivity & WorkflowDeveloper Tools

Overview

AI-generated overview

Lets an AI assistant manage Featureflip feature flags, targeting rules, segments and rollouts from the editor or an agent.

What you can do
  • List and manage projects, environments, flags, segments and SDK keys
  • Create, update, toggle, archive, restore and delete flags, and set owners, expiry and permanence
  • Read and change targeting rules, variations and per-environment flag configuration
  • Manage webhooks and inspect webhook deliveries
  • Review cross-environment status, evaluation counts, environment differences, stale flags and removal candidates
  • Create a flag and get the matching SDK snippet for your language
When to use it
Use it when you work with Featureflip feature flags and want an assistant to inspect, change or clean up flags, targeting and rollouts without switching to the dashboard. It suits interactive editor use with a personal token and CI or agent automation with a scoped service token.
Requirements
A local Node.js runtime, since it runs via npx from the npm package. A Featureflip API token in FEATUREFLIP_TOKEN is required; FEATUREFLIP_API_URL and FEATUREFLIP_ORG are optional. Network access to the Featureflip API.
Before you install
The token is a credential: a personal token acts as you, so it carries your permissions. Many tools create, update, toggle, archive or delete flags, targeting, segments, environments, SDK keys and webhooks, and every mutation is audit-logged and attributed to the token. Webhook tools require an admin token. Flag evaluation is not exposed, so runtime serving must use the language SDKs.

Installation

In SourceWeft

  1. Open Featureflip in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

@featureflip/mcp

MCP (Model Context Protocol) server for Featureflip — manage feature flags from AI coding assistants (Claude Code, Cursor, Copilot, Cline) and autonomous agents.

Setup

  1. Create an API token in the Featureflip dashboard:
    • Personal token (ffp_...): Settings → API Tokens — acts as you, for interactive editor use.
    • Service token (ffs_...): Organization Settings → Service Tokens — scoped machine identity for CI/agents.
  2. Add the server to your MCP client:

Claude Code

bash
claude mcp add featureflip -e FEATUREFLIP_TOKEN=ffp_your_token -- npx -y @featureflip/mcp@latest

Cursor / Cline / generic JSON config

json
{  "mcpServers": {    "featureflip": {      "command": "npx",      "args": ["-y", "@featureflip/mcp@latest"],      "env": { "FEATUREFLIP_TOKEN": "ffp_your_token" }    }  }}

Keep the @latest. Without a version, npx reuses the copy it downloaded the first time and never checks npm again, so tools added in later releases would never show up in your client.

Configuration

Env varRequiredDefaultPurpose
FEATUREFLIP_TOKENyes—ffp_/ffs_ API token
FEATUREFLIP_API_URLnohttps://api.featureflip.ioAPI base URL
FEATUREFLIP_ORGnoautoOrg slug (needed only for multi-org personal tokens)

Tools

CRUD: list_projects, list_environments, list_flags, get_flag, create_flag, update_flag, delete_flag, archive_flag, restore_flag, set_flag_expiry, set_flag_owner, set_flag_permanent, toggle_flag, update_flag_environment_config, copy_flag_config, get_targeting, update_targeting, manage_targeting_rule, manage_variation, list_segments, get_segment, manage_segment, manage_project, set_default_flag_lifetime, manage_environment, list_sdk_keys, manage_sdk_key, list_flag_triggers, manage_flag_trigger

Webhooks (Admin token required): list_webhooks, list_webhook_deliveries, manage_webhook, deliver_webhook

Workflows: flag_status (cross-environment view), flag_evaluations (what a flag served in one environment: evaluation counts by variation and rule), compare_environments (which flags differ between two environments), find_stale_flags (cleanup candidates), list_removal_candidates (flags safe to remove, with the prerequisite dependents to remove first), wrap_feature (create flag + get the SDK snippet for your language)

Full reference: https://featureflip.io/docs/integrations/mcp/

Notes

  • Flag evaluation is not exposed over MCP — use the language SDKs in application code.
  • Every mutation is audit-logged and attributed to the token.

License

Apache-2.0

Source: README.md at commit 7123eff

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

15
  1. v0.9.0LatestNov 7, 2026
  2. v0.7.0Nov 5, 2026
  3. v0.6.0Nov 3, 2026
  4. v0.5.0Oct 30, 2026
  5. v0.4.0Oct 29, 2026
  6. v0.3.0Oct 16, 2026
  7. v0.2.0Oct 15, 2026
  8. v0.1.13Oct 13, 2026
  9. v0.1.12Oct 12, 2026
  10. v0.1.11Oct 11, 2026
  11. v0.1.10Oct 3, 2026
  12. v0.1.9Oct 1, 2026
  13. v0.1.8Sep 25, 2026
  14. v0.1.7Sep 18, 2026
  15. v0.1.6Sep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts