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.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.