Model Context Protocol (MCP)
CoderBuds exposes an MCP server that lets your AI coding assistant access your team's development insights directly. Query active insights, view summaries by category, and mark insights as reviewed — all without leaving your editor.
What is MCP?
The Model Context Protocol is an open standard that allows AI assistants to connect to external data sources and tools. By connecting your AI assistant to CoderBuds via MCP, it gains awareness of your team's insights and can proactively surface relevant information as you work.
Compatible with Claude Code, Claude Desktop, Cursor, Windsurf, and any other MCP-compatible client.
Available Tools
Get My Insights
Retrieve active insights for your team. Filter by category (activity, performance, collaboration, satisfaction) or show only unseen items.
Mark Insight Seen
Mark a specific insight as reviewed. Reduces noise in future queries so you only see what's new.
Team Insight Summary
Get an aggregate overview of active insights for your team, including counts per category, unseen count, and personal insights.
Authentication
The MCP server uses API token authentication. You'll need to generate a personal API token from your CoderBuds account, then provide it when configuring your MCP client.
Generate an API Token
Go to API Tokens in your account settings and create a new token. Give it a descriptive name like "Claude Code" or "Cursor MCP".
Configure Your MCP Client
Use your token to connect to the CoderBuds MCP endpoint. See the client-specific setup guides below.
Endpoint
https://coderbuds.com/mcp/insights
All requests must include an Authorization: Bearer <token> header.
Setup Guides
Claude Code
Run this command in your project directory:
claude mcp add --transport http coderbuds \ https://coderbuds.com/mcp/insights \ --header "Authorization: Bearer YOUR_TOKEN"
Restart Claude Code after adding the server. Verify with /mcp in the session.
Claude Desktop
Add this to your Claude Desktop configuration file (claude_desktop_config.json):
{
"mcpServers": {
"coderbuds": {
"type": "http",
"url": "https://coderbuds.com/mcp/insights",
"headers": {
"Authorization": "Bearer YOUR_TOKEN"
}
}
}
}
Cursor, Windsurf & Other Clients
Add an MCP server with the following settings in your client's configuration:
| Transport | Streamable HTTP |
| URL | https://coderbuds.com/mcp/insights |
| Auth Header | Authorization: Bearer YOUR_TOKEN |
Example Usage
Once connected, your AI assistant can access your insights naturally. Here are some things you can ask:
"What are my team's active insights?"
"Show me any unseen performance insights"
"Give me a summary of my team's insight categories"
"Mark insight #42 as seen"
Data & Privacy
The MCP server only exposes insights that belong to your team. All data is scoped to your authenticated user and their team memberships. Personal insights are only visible to the user they belong to. Your API token can be revoked at any time from your API Tokens page. See our Security documentation for more details.