The Tusk Drift MCP server enables AI assistants to search, analyze, and debug API traffic data captured by Tusk Drift, including HTTP requests, database queries, and distributed traces.
Core Capabilities:
Search and Filter API Traffic (query_spans) - Find specific API calls using flexible criteria like endpoint names, HTTP methods, status codes, duration, errors, and custom JSON path filters with pagination support
Get Schema Information (get_schema) - Understand available fields and structure for different instrumentation types (HTTP, database, gRPC, etc.) with example payloads
Discover Available Data (list_distinct_values) - List unique and frequently occurring values for fields like endpoints, instrumentation packages, environments, status codes, and JSONB values to assist in query building
Calculate Aggregated Metrics (aggregate_spans) - Compute statistics including latency percentiles (p50, p95, p99), error rates, request counts, performance comparisons across endpoints or environments, and time-series trends (hourly, daily, weekly)
View Distributed Traces (get_trace) - Retrieve complete end-to-end traces as hierarchical trees showing the full call chain, timings, and dependencies to identify bottlenecks
Fetch Specific Spans (get_spans_by_ids) - Get detailed information and full request/response payloads for individual span recordings by ID
Common Use Cases: Debug failed or slow API requests, analyze endpoint performance patterns, track errors across distributed systems, understand API traffic and usage patterns, monitor database query performance, and investigate specific requests end-to-end.
Setup: Connect via remote server (recommended) or local installation with API key authentication. Supports multiple AI assistants including Cursor and Claude Desktop with easy configuration.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Tusk Drift MCP show me the slowest API endpoints from the last hour"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
An MCP server for querying API traffic data captured by Tusk Drift. This enables AI assistants to search, analyze, and debug your application's API traffic, including HTTP requests, database queries, and distributed traces.
New to Tusk Drift? Check out our docs and sign up for an account.
Connect directly to the hosted Tusk Drift MCP server. This is the easiest setup and doesn't require running anything locally.
For Cursor:
Add to your Cursor MCP settings (~/.cursor/mcp.json or workspace .cursor/mcp.json):
{
"mcpServers": {
"tusk-drift": {
"url": "https://api.usetusk.ai/api/drift-mcp",
"headers": {
"x-api-key": "YOUR_TUSK_API_KEY"
}
}
}
}For Claude Code:
Option A — CLI command:
claude mcp add --transport http tusk-drift https://api.usetusk.ai/api/drift-mcp \
--header "x-api-key: YOUR_TUSK_API_KEY"Option B — Add to .mcp.json in your project root:
{
"mcpServers": {
"tusk-drift": {
"type": "http",
"url": "https://api.usetusk.ai/api/drift-mcp",
"headers": {
"x-api-key": "YOUR_TUSK_API_KEY"
}
}
}
}For Claude Desktop:
{
"mcpServers": {
"tusk-drift": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://api.usetusk.ai/api/drift-mcp"],
"env": {
"MCP_HEADERS": "{\"x-api-key\": \"YOUR_TUSK_API_KEY\"}"
}
}
}
}Run the MCP server locally. This is useful if you need offline access or custom configuration.
For Claude Desktop / Cursor:
Add to your claude_desktop_config.json or Cursor MCP settings:
{
"mcpServers": {
"tusk-drift": {
"command": "npx",
"args": ["-y", "@use-tusk/drift-mcp"],
"env": {
"TUSK_API_KEY": "YOUR_TUSK_API_KEY"
}
}
}
}Variable | Required | Description |
| Yes | Your API token |
| No | Backend base URL (defaults to |
| No | Service ID (auto-discovered from |
| No | Comma-separated workspace roots to search for |
Related MCP server: Shepherd MCP
Tool | Description |
| Search API traffic with flexible filters |
| Get structure/schema of captured traffic |
| Discover available endpoints and field values |
| Calculate latency percentiles, error rates, counts |
| View distributed traces as hierarchical trees |
| Fetch specific spans with full payloads |
Need help? Open an issue or contact us at support@usetusk.ai.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
See, price, and control every tool call your AI agents make: policy checks, cost, and audit tools.
Runtime permission, approval, and audit layer for AI agent tool execution.
Read-only access to Auralogs production logs: search logs, inspect errors, review AI analyses.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Use-Tusk/drift-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server