Featurebase MCP server

Connect AI tools to your Featurebase workspace and manage feedback, support, and product data through natural language.

Written By Markus from Featurebase

Last updated 1 day ago

Overview

The Featurebase MCP server lets AI tools and assistants like Claude, ChatGPT, and Cursor securely connect to your Featurebase workspace.

Once connected, AI agents can read, create, and update data across Featurebase – no custom integration work required.

What is Featurebase MCP?

MCP (Model Context Protocol) is an open standard for connecting AI tools to external systems, so any MCP-compatible client can talk to Featurebase out of the box.

The MCP server is built directly on top of our public API, which means anything you can do with the Featurebase API, an AI agent can do for you in plain conversation:

  • Easy setup – Connect with OAuth in a few clicks and start managing your workspace through chat

  • Works with any MCP client – Claude, ChatGPT, Cursor, VS Code, Claude Code, and any other client that reads an mcpServers.json (Continue, Zed, Windsurf, etc.)

  • Full workspace access – Manage feedback, support conversations, users, changelogs, Help Center articles, and more

  • Secure by design – AI tools authenticate as your Featurebase user and inherit your existing permissions

Note: AI agents acting through the MCP have the same access you do, so only connect tools you trust.

Reader and Writer: two connectors, one safety boundary

The hosted MCP ships as two separate connectors – Reader and Writer – so mutation tools never share a chat with customer text that could trick an agent into running them. Pick whichever one fits the job.

  • Reader – Read-only access to your workspace: feedback, conversations, contacts, help center. Safe for analytics, reporting, and Q&A agents.

  • Writer – Create, edit, and delete admin-controlled resources (boards, tags, help-center articles, webhooks). Intentionally cannot read customer-supplied content.

Never use Writer in the same chat as Reader:

  • Writer is safe on its own – it can't read customer text, so there's nothing to inject instructions into.

  • The risk only appears when you put it in the same chat as Reader. An attacker can hide instructions inside a feedback post, support reply, or comment that Reader pulls in; the agent then runs those instructions as real writes through Writer's tools – a high chance of compromising your Featurebase organization.

  • Keep Writer in a separate Claude project / ChatGPT chat / Cursor workspace.

What you can do with each connector

Reader (read-only, customer content allowed)

  • Feedback & Roadmaps – Search and read feedback posts, comments, votes, voters

  • Support Inbox – Read conversations, tickets, and customer history

  • Help Center – Read articles and collections

  • Users & companies – Look up customer profiles, segments, and attributes

  • Surveys – Pull responses for analysis

  • Changelog – Read past releases and subscribers

Best for: weekly digests, sentiment analysis, "what are users complaining about", customer-history summaries before a reply, Q&A bots over your help center.

Writer (admin actions, no customer content)

  • Feedback boards – Create, rename, reorder, archive

  • Tags & custom fields – Create, rename, delete, bulk-organize

  • Help Center – Create, read, edit, restructure, and publish articles and collections

  • Changelog – Draft, edit, and publish releases

  • Webhooks & integrations – Register, rotate secrets, remove

  • Post statuses, ticket statuses, conversation tags – Configure

Best for: building out your information architecture, drafting changelogs from notes you paste in, restyling old help articles, bulk admin cleanup.

Tip: Workflows that need both – e.g. "find recurring questions in the inbox and draft new help articles" – are best done in two passes. Use Reader in one chat to extract and summarize, then paste the summary into a separate Writer chat to create the articles. For the full list of available actions per connector, see our API reference.

Getting started

Before connecting Featurebase MCP, ensure you have an active Featurebase workspace (on the Professional plan or higher) and an MCP-compatible AI client (Claude.ai, ChatGPT, Cursor, VS Code, Claude Code, etc.).

Connect Featurebase with your AI tool:

  1. Go to Featurebase Settings → MCP

  2. Pick Reader or Writer, then follow the install card for your AI tool (Claude, ChatGPT, Cursor, VS Code, Claude Code, or Other clients via mcpServers.json)

You can revoke MCP access at any time from your Featurebase account settings.

Notes:

  • If your AI tool doesn't yet support remote MCP servers, you can connect through the mcp-remote proxy package as a bridge.

  • On Claude Team or Enterprise plans?

    • Custom connectors must be enabled at the organization level by an Owner or Primary Owner before individual members can install them. If you see Missing permissions or Failed to add connector when trying to install Featurebase, that's why.

    • The Owner needs to go to Organization settings → Connectors → Add, paste the Featurebase Reader (or Writer) URL, and click Add. Once it's enabled at the org level, individual members can connect from Customize → Connectors as normal. See Claude's documentation on custom connectors for the full flow.

Example use cases

Here are a few ways teams use the Featurebase MCP day-to-day. Each bullet is tagged with the connector it needs.

Research and reporting

  • Analyze feedback trends (Reader) – Identify recurring themes, sentiment, and feature interest across incoming feedback

  • Surface Conversations by customer, topic, or conversation attribute (Reader) – Find open issues for a specific customer or summarize Conversations about a product area, problem, or time period

  • Analyze Survey responses (Reader) – Find patterns and sentiment across open-ended Survey responses

  • Generate recurring digests (Reader) – Create weekly or monthly summaries of feedback, Conversations, support topics, or customer segments

  • Summarize customer history (Reader) – Review a customer’s previous Conversations, feedback, and feature requests before a meeting or reply

Customer support

  • Draft support replies (Reader) – Pull the complete Conversation context and draft a response grounded in the customer’s history

  • Prepare escalation briefs (Reader) – Summarize the issue, previous replies, attempted solutions, and unresolved questions before handing a Conversation to another teammate

  • Identify recurring support questions (Reader) – Group similar Conversations to uncover common problems, confusing workflows, and documentation gaps

  • Chat with your Help Center (Reader) – Ask questions across your documentation and receive answers grounded in your published articles

  • Draft and update Help Center articles (Writer) – Create articles, refresh outdated content, or restyle existing documentation through chat

  • Audit documentation for gaps (Reader + Writer in separate chats) – Compare completed Featurebase posts or product changes with existing Help Center content, then apply approved changes in a separate Writer chat

  • Generate articles from support trends (Reader + Writer in separate chats) – Find recurring questions in Conversations, prepare a clean summary, and use it to create relevant Help Center content in a Writer-only chat

  • Keep Help Center articles current after releases (Reader + Writer in separate chats) – Identify articles affected by completed work, review the recommended changes, and update approved pages in a Writer-only chat

  • Turn Updates into Help Center articles (Writer) – Expand a release announcement into durable setup, reference, or troubleshooting documentation

Feedback operations

  • Turn call transcripts into feedback posts (Writer) – Paste sales or support call notes into a Writer-only chat and turn relevant insights into structured feedback posts

  • Triage incoming feedback (Reader + Writer in separate chats) – Cluster and prioritize posts in a Reader chat, then apply the approved tags, merges, or other changes in a separate Writer chat

  • Organize feedback at scale (Writer) – Create, rename, reorder, or archive feedback boards, tags, and custom fields

  • Turn research into structured feedback (Writer) – Convert reviewed interview notes, research summaries, or imported feedback into organized posts

Updates communication

  • Draft Updates from release notes (Writer) – Turn notes pasted into a Writer-only chat into engaging, properly categorized Outbound Updates

  • Create Updates from completed work (Reader + Writer in separate chats) – Monitor completed Featurebase posts and combine them with any Linear, Jira, release note, or codebase context available to your AI tool, then turn the reviewed brief into an Outbound Update

  • Turn Help Center articles into Updates (Writer) – Condense detailed documentation into a concise release announcement

Workspace administration

  • Manage user data in bulk (Writer) – Update user tags, attributes, or segments using a reviewed list pasted into the chat

  • Clean up Workspace configuration (Writer) – Create, rename, reorder, or archive boards, tags, custom fields, and other administrative resources

  • Manage webhooks and integrations (Writer) – Register webhooks, rotate secrets, or remove obsolete connections through chat

Scheduling these workflows:

  • You can schedule Reader tasks in Claude Code, Codex, ChatGPT, or another automation-capable MCP client to monitor completed work and prepare digests or content briefs.

  • Reader and Writer should remain in separate chats, so review the Reader output and pass it to a clean Writer-only chat before creating or changing Featurebase content.

  • Your AI tool also may need its own access to external sources such as Linear, Jira, or your codebase for some of these examples.

FAQ