DebugBundle
DebugBundle MCP: runtime error reporting, incident response, health checks, and product analytics.
At a glance
Not tested yet- GitHub stars
- 7
- Weekly downloads
- 1,307
- Last commit
- 2026-11-19
- Licence
- Apache-2.0
- Transport
- stdio
- Auth
- api-key
npx -y @debugbundle/mcp
What it does
DebugBundle is a production debugging service for AI agents and the people who run them. It captures runtime errors, groups them into incidents, and publishes versioned debug bundles that hold errors, requests, responses, logs, frontend context, deploy metadata and reproduction hints. It also covers crash reporting, incident response, endpoint health checks and product analytics. It is aimed at teams that want an agent to work from packaged incident facts instead of scraping dashboards, logs and chat threads.
Key features
- Deterministic failure and improvement bundles with errors, requests, responses, logs, frontend context, deploy metadata, runtime details and reproduction hints.
- Interface parity across API, CLI and MCP for incident, bundle, probe, webhook, alert, project and automation workflows.
- Local-first setup that writes events to
.debugbundle/local/events/without a cloud account, with a later path to DebugBundle Cloud. - SDKs that swallow their own failures, redact sensitive fields before transport and suppress duplicate storms locally.
- A self-hostable core with a Compose-based stack for the web app, API, worker, Postgres, Redis and S3-compatible object storage.
- Monitoring scope is customer-facing runtime behavior and endpoint health, not generic infrastructure metrics.
Quick start
npm install -g @debugbundle/cli debugbundle setup debugbundle login debugbundle connect
Then add the smallest SDK or ingestion path that matches your app, deploy it with the token configured, and verify ingestion:
debugbundle verify cloud --project-id proj_01HXYZ... --trigger-5xx debugbundle incidents --source cloud debugbundle inspect inc_01HXYZ...
For local-only mode:
npm install -g @debugbundle/cli debugbundle setup --project-mode local-only debugbundle process debugbundle incidents --source local debugbundle inspect inc_local_...
Add this to .mcp.json in your project root (Claude Code) or .cursor/mcp.json (Cursor):
{
"mcpServers": {
"debugbundle-mcp": {
"command": "npx",
"args": [
"-y",
"@debugbundle/mcp"
],
"env": {
"DEBUGBUNDLE_MEMBER_TOKEN": "YOUR_DEBUGBUNDLE_MEMBER_TOKEN",
"DEBUGBUNDLE_API_URL": "YOUR_DEBUGBUNDLE_API_URL"
}
}
}
}Replace each YOUR_ value with your own, and delete the variables you do not use.
Environment variables
DEBUGBUNDLE_MEMBER_TOKEN: declared by the server. The README does not explain it.DEBUGBUNDLE_API_URL: declared by the server. The README does not explain it.
Example prompts
- List the open incidents from the cloud source and summarize each one.
- Inspect incident
inc_01HXYZ...and tell me what the bundle says about the failing request. - Run a health probe against my endpoint and report the result.
- Show me the debug bundle for the most recent local incident.
What to watch out for
- Cloud mode requires an account and a project token.
debugbundle connectcreates a write-only project token that you put in your hosted environment. - The browser SDK needs a matching backend relay route configured first. The relative endpoint URL does not create a server endpoint, and the backend project token must stay on the server.
- SDK client constructors, framework configuration and plugin activation are runtime-specific, so setup differs per language.
- The sources state no costs.
Not tested by tools4agents yet. Read the source repository before you install it.
Similar tools
Memory
A knowledge graph that persists facts across sessions, so an agent can recall context after the conversation ends.
DBHub
Token-efficient MCP server for PostgreSQL, MySQL, MariaDB, SQL Server, Oracle, ClickHouse, SQLite
PostgreSQL
Read only SQL access with schema introspection, so an agent can answer questions about your data without guessing column names.
Supabase MCP Server
Connects AI assistants directly to Supabase projects to manage database tables, query data, run migrations, and control edge functions.