Home › Development › Tracekit MCP gateway
Tracekit MCP gateway
MCP gateway you deploy: a Tracekit signer decides and signs each call; agents send each run's token.
Connect
Review any command before running it. Package names and URLs come from the server's own registry entry.
Remote (streamable-http)
https://{tracekit_gateway}/mcp
Claude Code:
claude mcp add --transport http tracekit https://{tracekit_gateway}/mcp --header "X-Tracekit-Run: <YOUR_VALUE>" --header "Authorization: <YOUR_VALUE>"
Or add to your MCP client config:
{
"mcpServers": {
"tracekit": {
"url": "https://{tracekit_gateway}/mcp",
"headers": {
"X-Tracekit-Run": "<YOUR_VALUE>",
"Authorization": "<YOUR_VALUE>"
}
}
}
}
X-Tracekit-Runrequired secret — <run_id>.<run_token> of the agent's run (register_run): new for every run, so the agent framework sets it per run; one typed in once works for one runAuthorizationsecret — Bearer <token>: the agent's identity, when the gateway's http.authenticators accept a bearer or Kubernetes service account token (else a client certificate)
Related servers
storybook
Helps agents write and test Storybook stories for UI components.
chromedevtools/chrome-devtools-mcp
MCP server for Chrome DevTools
Codebase Memory
Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
PostHog MCP Server
Official PostHog MCP Server for product analytics, feature flags, experiments, and more.
code-review-graph
Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters,…
Serena MCP: the IDE for your agent
A powerful toolkit for coding, providing semantic retrieval and editing capabilities.
Data from the Official MCP Registry