Featurebase MCP Server

Featurebase MCP Server

Enables interaction with Featurebase API to manage feature requests, feedback posts, comments, and upvotes. Supports creating, updating, and organizing customer feedback through natural language commands.

Category
访问服务器

README

Featurebase MCP Server

smithery badge

A Model Context Protocol (MCP) server that provides access to the Featurebase API for managing posts and comments.

Features

  • Posts Management

    • List posts with filtering options
    • Create new posts
    • Update existing posts
    • Delete posts
    • Get post upvoters
    • Add upvoters to posts
  • Comments Management

    • Get comments for posts/changelogs
    • Create new comments or replies
    • Update comments
    • Delete comments

Installation

From Smithery (Recommended)

Once published to Smithery, users can install the server easily:

npx featurebase-mcp

Or install globally:

npm install -g featurebase-mcp

From Source

git clone https://github.com/marcinwyszynski/featurebase-mcp.git
cd featurebase-mcp
npm install
npm run build

Usage

Claude Desktop Configuration

Add this server to your Claude Desktop configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%\Claude\claude_desktop_config.json

Using npx (Recommended)

{
  "mcpServers": {
    "featurebase": {
      "command": "npx",
      "args": ["featurebase-mcp"],
      "env": {
        "FEATUREBASE_API_KEY": "your-api-key-here",
        "FEATUREBASE_ORG_URL": "https://your-org.featurebase.app"
      }
    }
  }
}

Using Global Installation

{
  "mcpServers": {
    "featurebase": {
      "command": "featurebase-mcp",
      "env": {
        "FEATUREBASE_API_KEY": "your-api-key-here",
        "FEATUREBASE_ORG_URL": "https://your-org.featurebase.app"
      }
    }
  }
}

Using Local Installation

{
  "mcpServers": {
    "featurebase": {
      "command": "node",
      "args": ["/path/to/featurebase-mcp/build/index.js"],
      "env": {
        "FEATUREBASE_API_KEY": "your-api-key-here",
        "FEATUREBASE_ORG_URL": "https://your-org.featurebase.app"
      }
    }
  }
}

Getting Your API Key

  1. Log in to your Featurebase account
  2. Navigate to your account settings
  3. Generate an API key
  4. Keep it secure - never commit it to version control

Environment Variables

The server requires these environment variables:

Required

  • FEATUREBASE_API_KEY: Your FeatureBase API key

Optional

  • FEATUREBASE_ORG_URL: Your organization's FeatureBase URL (e.g., "https://feedback.spacelift.io"). Required only if using resolve_post_slug tool.
  • FEATUREBASE_BASE_URL: Custom API base URL (defaults to "https://do.featurebase.app/v2")

You can set them:

  1. In your Claude Desktop configuration (recommended)
  2. Export in your shell: export FEATUREBASE_API_KEY="your-api-key-here"
  3. When running the server: FEATUREBASE_API_KEY="your-api-key-here" npx featurebase-mcp

Available Tools

Posts

list_posts

List posts with optional filtering.

Parameters:

  • id: Find specific post by ID
  • q: Search posts by title or content
  • category: Filter by board names (array)
  • status: Filter by status IDs (array)
  • sortBy: Sort order (e.g., "date:desc", "upvotes:desc")
  • startDate: Posts created after this date
  • endDate: Posts created before this date
  • limit: Results per page
  • page: Page number

create_post

Create a new post.

Parameters:

  • title (required): Post title (min 2 characters)
  • category (required): Board/category name
  • content: Post content
  • email: Submitter's email
  • authorName: Name for new users
  • tags: Array of tag names
  • commentsAllowed: Enable/disable comments
  • status: Post status
  • date: Creation date
  • customInputValues: Custom field values

update_post

Update an existing post.

Parameters:

  • id (required): Post ID to update
  • title: New title
  • content: New content
  • status: New status
  • commentsAllowed: Enable/disable comments
  • category: New category
  • sendStatusUpdateEmail: Email upvoters about status change
  • tags: New tags
  • inReview: Put post in review
  • date: Creation date
  • customInputValues: Custom field values

delete_post

Permanently delete a post.

Parameters:

  • id (required): Post ID to delete

get_post_upvoters

Get list of users who upvoted a post.

Parameters:

  • submissionId (required): Post ID
  • page: Page number (default: 1)
  • limit: Results per page (default: 10, max: 100)

add_upvoter

Add an upvoter to a post.

Parameters:

  • id (required): Post ID
  • email (required): Upvoter's email
  • name (required): Upvoter's name

resolve_post_slug

Convert a post slug to post ID and get complete post details.

Parameters:

  • slug (required): Post slug from URL (e.g., "spacectl-stack-local-preview-target")

Returns the complete post data including ID, title, content, and metadata.

get_similar_submissions

Find posts similar to the given query text.

Parameters:

  • query (required): Search query text to find similar submissions
  • locale: Locale for search (default: "en")

Returns a list of similar posts based on content similarity.

Comments

get_comments

Get comments for a post or changelog.

Parameters:

  • submissionId: Post ID or slug (required if no changelogId)
  • changelogId: Changelog ID or slug (required if no submissionId)
  • privacy: Filter by privacy ("public", "private", "all")
  • inReview: Filter for comments in review
  • commentThreadId: Get all comments in a thread
  • limit: Results per page (default: 10)
  • page: Page number (default: 1)
  • sortBy: Sort order ("best", "top", "new", "old")

create_comment

Create a new comment or reply.

Parameters:

  • content (required): Comment content
  • submissionId: Post ID or slug (required if no changelogId)
  • changelogId: Changelog ID or slug (required if no submissionId)
  • parentCommentId: Parent comment ID for replies
  • isPrivate: Make comment private (admins only)
  • sendNotification: Notify voters (default: true)
  • createdAt: Set creation date
  • author: Post as specific user (object with name, email, profilePicture)

update_comment

Update an existing comment.

Parameters:

  • id (required): Comment ID
  • content: New content
  • isPrivate: Make private (admins only)
  • pinned: Pin comment to top
  • inReview: Put comment in review
  • createdAt: Update creation date

delete_comment

Delete a comment (soft delete if it has replies).

Parameters:

  • id (required): Comment ID to delete

Development

# Install dependencies
npm install

# Build TypeScript
npm run build

# Run in development mode
npm run dev

Security

  • Never hardcode your API key
  • Always use environment variables for API keys
  • Keep your API key secure and rotate it regularly
  • The server will not start without a valid FEATUREBASE_API_KEY environment variable

Publishing

This server is available on:

  • Smithery - MCP server registry
  • npm - Node package manager

For publishing instructions, see PUBLISHING.md.

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

License

MIT

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选