"Open Collective" matching MCP servers:

Open source MCP server for OpenProject aimed at community edition users

A local MCP server that gives AI agents read access to Roblox experience analytics via the Open Cloud API, exposing 168 metrics and analysis tools for retention, engagement, monetization, and more.

Turns product feedback pinned to a live UI into an actionable backlog for Claude Code — list comments, open one with its target element's HTML, computed styles and screenshot, and update its status.

Mogut — open-source, read-only MCP server for Apple App Store ASO and growth intelligence: keyword research, competitor analysis, review mining, pricing, localization, and reports.

MCP server for reading public Featurebase feedback boards, enabling agents to query user feedback, posts, comments, and statistics.

Enables Claude Code to run multi-round grilling sessions in a browser UI, publishing rounds of questions with options and recommendations that users answer with buttons or free text. Supports per-question asides (re-pitch, visual diagram, plain-language explainer), chat notes between rounds, and a polling contract so sessions can stay open without blocking the client.

Lets AI clients draft, inspect, edit and review wireframe/storyboard boards over MCP, sharing one live board with the app the user has open. It also supports loading boards back, resolving review notes, and exporting realistic previews so specs can be iterated from natural language.

Manages and authoring of business rules in a scenario studio tool, enabling agents to read, update, link rules, and assign them to capabilities via MCP tools.

Provides MCP tools for AI agents to create and read decision decks, propose cards and build plans, and retrieve finished tasks, enabling local decision review workflows with portable task handoffs.

Turns the five Playing to Win boxes into queryable data over MCP: list all positions, open one position with its supporting, opposing, and complicating evidence, adopt or reject it with a note, record new evidence, add positions into a box, and organize several cascades of boxes. Read and write tools share the same core and query layer as the CLI and web pages, so every surface stays consistent.

Turns a rambling app idea into a structured planning canvas of screens, flows, systems, data and open questions inside an existing Claude Code or Codex session, then writes the settled plan back to that session as a spec to build from. Plans are stored in the project's .doan/ folder alongside the code.

MCP server for Open Feedback, enabling AI assistants to submit, list, get, update status of, and analyze product feedback via a local HTTP API and JSONL storage.