MCP Integration

The Model Context Protocol (MCP) lets AI assistants query your Qplane traffic data directly. Ask natural language questions about connections, requests, errors, and PII exposure—your AI translates them into structured queries against your live data.

What You Can Do

With MCP, AI assistants can:

• Investigate incidents by querying real-time traffic patterns

• Audit security by checking authentication failures and PII exposure

• Debug performance by analyzing latency and error rates

• Discover shadow IT by identifying unexpected API connections

MCP provides read-only access to your traffic data. It cannot modify configurations or affect traffic flow.

Connection Details

Setting	Value
Endpoint	https://pulse.qpoint.io/mcp/v1
Transport	Streamable HTTP
Authentication	Bearer token

Get Your Token

1. Log in to app.qpoint.io

2. Navigate to Settings → Deployments

3. Click + New Registration Token

4. Name it (e.g., "MCP Access")

5. Copy the generated Auth Token

Store your token securely. It provides access to your organization's traffic data.

Connect Your MCP Client

Use your token as a Bearer token with the MCP endpoint. Configuration varies by client:

Claude Code:

claude mcp add qpoint --transport http https://pulse.qpoint.io/mcp/v1 \
  --header "Authorization: Bearer YOUR_TOKEN"

Codex CLI (~/.codex/config.toml):

[mcp_servers.qpoint]
url = "https://pulse.qpoint.io/mcp/v1"
bearer_token_env_var = "QPOINT_TOKEN"

Then set export QPOINT_TOKEN=your-token in your shell.

Other Clients:

Configure your MCP client with:

• URL: https://pulse.qpoint.io/mcp/v1

• Header: Authorization: Bearer YOUR_TOKEN

Example Queries

Once connected, try:

"What endpoints have I connected to in the last hour?"

"Show me any 500 errors from today"

"Is there PII detected in outbound traffic?"

Next Steps

• MCP Tools Reference — Complete reference for all available queries