featuriq
featuriq-mcp
一个用于 Featuriq(专为产品经理打造的产品反馈和路线图工具)的 MCP (Model Context Protocol) 服务器。
将您的 Featuriq 工作区连接到任何兼容 MCP 的 AI 客户端(Claude Desktop、Cursor 等),即可通过自然语言查询功能请求、搜索客户反馈、运行 AI 优先级排序、更新状态并通知用户。
安装
选项 1 — 直接使用 npx 运行(无需安装)
npx featuriq-mcp选项 2 — 全局安装
npm install -g featuriq-mcp
featuriq-mcpRelated MCP server: Feedbucket MCP Server
设置
1. 获取您的 API 密钥
登录 featuriq.io,前往 Settings → API,然后复制您的 API 密钥。
2. 设置环境变量
export FEATURIQ_API_KEY=fq_live_xxxxxxxxxxxxxxxxxxxx或者,如果您的客户端支持 .env 文件,请将 .env.example 复制到 .env 并填入您的密钥。
变量 | 必需 | 默认值 | 描述 |
| 是 | — | 您的 Featuriq API 密钥 |
| 否 |
| 覆盖 API 基础 URL |
3. 添加到您的 MCP 客户端
Claude Desktop
编辑 ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) 或 %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"featuriq": {
"command": "npx",
"args": ["featuriq-mcp"],
"env": {
"FEATURIQ_API_KEY": "fq_live_xxxxxxxxxxxxxxxxxxxx"
}
}
}
}Cursor
添加到您的 Cursor MCP 设置中:
{
"featuriq": {
"command": "npx featuriq-mcp",
"env": {
"FEATURIQ_API_KEY": "fq_live_xxxxxxxxxxxxxxxxxxxx"
}
}
}可用工具
get_top_requests
返回按投票数或收入影响排序的热门功能请求。
参数:
limit(number, 默认 10) — 返回结果的数量sort_by("votes" | "revenue_impact", 默认 "votes") — 排序方式
示例提示:
"What are the top 5 most-requested features?"
"Show me the highest revenue impact requests."
search_feedback
使用自然语言对所有反馈帖子进行语义搜索——即使确切词汇不匹配也能找到相关结果。
参数:
query(string) — 要搜索的内容limit(number, 默认 10) — 最大结果数
示例提示:
"Find feedback about slow dashboard loading."
"Search for requests related to CSV export."
"What are users saying about mobile performance?"
get_feature_feedback
返回特定功能请求的所有评论和讨论。
参数:
feature_id(string) — 功能的唯一 ID
示例提示:
"Show me all feedback on feature feat_01j8k..."
"What are users saying about the API rate limit request?"
get_prioritization
返回一个 AI 优先级排序的功能列表,根据您选择的因素进行评分。
参数:
factors(array) — 以下一项或多项:"votes", "revenue", "effort", "strategic_fit"limit(number, 默认 10)
示例提示:
"Prioritize our backlog by votes and revenue impact."
"Give me the top 10 features ranked by votes, effort, and strategic fit."
"What should we build next quarter based on revenue and strategic alignment?"
update_feature_status
更新功能请求的状态。
参数:
feature_id(string) — 功能的唯一 IDstatus("planned" | "in_progress" | "shipped" | "closed")
示例提示:
"Mark feature feat_01j8k as in_progress."
"Set the dark mode request to shipped."
"Close the feature request for legacy IE support."
notify_requesters
向所有投票支持某项功能的用户发送个性化通知。
参数:
feature_id(string) — 要通知哪些功能的投票者message(string) — 要发送的消息(Featuriq 会为每位收件人进行个性化处理)
示例提示:
"Notify everyone who requested CSV export that it's now live."
"Tell the users who voted for dark mode that we're starting work on it next sprint."
create_post
在 Featuriq 看板上创建新的反馈帖子。
参数:
board_id(string) — 要发布到的看板title(string) — 帖子的简短标题description(string) — 完整描述
示例提示:
"Log a feature request for bulk CSV import on the features board."
"Create a post for the Slack integration idea from today's customer call."
可用资源
资源是 AI 可以随时读取以获取上下文的数据源。
featuriq://roadmap
按状态分组的当前路线图:进行中 (In Progress)、已计划 (Planned) 和 最近发布 (Recently Shipped)。
示例提示:
"What's on our current roadmap?"
"What features are in progress right now?"
featuriq://changelog
最近 20 个已发布的功能,包含发布日期和发行说明。
示例提示:
"What have we shipped recently?"
"Write a summary of our last month's product updates."
对话示例
您: 我们有哪些尚未开始的热门功能请求?根据投票数和收入影响,我们应该优先考虑哪些?
Claude: (调用
get_top_requests和get_prioritization) 以下是您尚未开始的热门请求...
您: 很好。将排名第一的标记为“进行中”,并通知所有投票支持它的用户。
Claude: (调用
update_feature_status然后调用notify_requesters) 完成!状态已更新,已通知 47 位用户。
开发
git clone https://github.com/carlosalvite/featuriq-mcp
cd featuriq-mcp
npm install
npm run build
FEATURIQ_API_KEY=your_key node dist/index.js在开发过程中监视更改:
npm run dev许可证
MIT © Featuriq
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseBqualityDmaintenanceEnables interaction with Featurebase API to manage feature requests, feedback posts, comments, and upvotes. Supports creating, updating, and organizing customer feedback through natural language commands.125058MIT
- AlicenseAqualityDmaintenanceEnables AI assistants to manage website feedback from Feedbucket, including listing, filtering, commenting on, and resolving feedback items through natural language interactions.617MIT
- AlicenseAqualityDmaintenanceEnables AI assistants to manage Featureflow feature flags, including creating and updating features, controlling feature states across environments, and managing projects, environments, and targeting rules through natural language.2218MIT
- FlicenseNot gradedqualityDmaintenanceGives AI agents direct access to your Arcate product discovery workspace to read signals, browse roadmaps, and ingest new customer feedback. It enables users to search existing data and link signals to initiatives through natural language commands.
Related MCP Connectors
Connect AI assistants to your GitHub-hosted Obsidian vault to seamlessly access, search, and analy…
Connect AI assistants to Stellary projects, boards, documents, and governed agent workflows.
Give AI agents access to form submissions — read, search, update, and process file attachments.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/carlosalvite/featuriq-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server