Arcate MCP Connect
Gives 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.
README
Arcate MCP Connect — Server
The official MCP server for Arcate. Gives AI agents like Claude direct access to your product discovery workspace — reading signals, browsing your roadmap, and writing new feedback back in.
This is a remote HTTP server — no installation required. Configure a URL in your MCP client and connect instantly.
Requires an active Evidence subscription (€129/mo). API keys are generated in
/settings/integrationsinside your Arcate workspace.
Quick Start
1. Generate an API Key
Log in → Settings → Integrations → Generate API Key. Copy the key — shown only once.
2. Configure your MCP client
Claude Desktop (~/Library/Application Support/Claude/claude_desktop_config.json):
{
"mcpServers": {
"arcate": {
"url": "https://mcp.arcate.io",
"headers": {
"Authorization": "Bearer arc_YOUR_KEY_HERE"
}
}
}
}
Cursor → Settings → MCP → Add Server → Type: HTTP → URL:
https://eshuikffwhaxcvkzaewj.supabase.co/functions/v1/mcp-server
Header: Authorization: Bearer arc_YOUR_KEY_HERE
3. Restart your AI client and test
"What are my top 5 unlinked customer signals from the last 30 days?"
Resources (Read-Only)
| URI | Description |
|---|---|
arcate://signals |
Unified Signal Inbox — all customer feedback |
arcate://initiatives |
Product Roadmap — active initiatives with evidence |
Tools
Read
| Tool | Description |
|---|---|
search_signals |
Search signals by keyword, type, or severity |
search_customers |
Look up customer accounts by name |
search_initiatives |
Find initiatives by keyword |
Write
| Tool | Description |
|---|---|
create_signal |
Ingest new customer feedback (tagged ingestion_source: mcp) |
create_customer |
Add a new customer profile (Owner only) |
link_to_initiative |
Connect signals to a roadmap initiative |
enrich_initiative |
Update hypothesis, metrics, and outcomes |
Guided Prompts
| Prompt | Description |
|---|---|
arcate:hello |
Welcome — get workspace overview and available commands |
arcate:ingest |
Log feedback from a call or interview |
arcate:triage |
Find unlinked signals with no initiative assigned |
arcate:enrich |
Strengthen a roadmap initiative with evidence |
Example Prompts
Triage a sales call:
"I just spoke with Acme Corp. They said bulk export times out on datasets over 100k rows. Log this as a signal."
Review initiative evidence:
"Does our Mobile Revamp initiative have enough signal coverage to proceed to active?"
Batch ingest:
"Here are notes from 3 customer calls this week. Create signals for each and link them to relevant initiatives."
Security
- Keys are stored as SHA-256 hashes. The plaintext is shown only once and never stored.
- Every request is re-validated against
billing_statusanduse_mcpcapability. - All queries are hard-scoped to your
organization_id. Cross-tenant access is impossible. - MCP-created signals are tagged with
ingestion_source: mcpfor audit filtering in the UI.
Architecture
The server is deployed as a Supabase Edge Function implementing JSON-RPC 2.0 over HTTP (the MCP Streamable HTTP transport). A GET request to the server URL returns a human-readable info card — no MCP client needed to inspect it.
Source: src/ — TypeScript reference implementation
Deployment: Supabase Edge Functions (Deno)
Database Setup
Apply the migration in supabase/migrations/add_mcp_tables.sql to bootstrap the api_keys table.
推荐服务器
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。
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。