Permettez aux agents IA d'inspecter les rapports d'erreurs d'exécution, le contexte d'incidents, les bundles de débogage, les analyses produit et les tests de santé des endpoints.
Aussi connu sous debugbundle/debugbundle, mcp, @debugbundle/mcp
- Étoiles
- 7
- Outils
- —
- Téléchargements, 30 jours
- 4 598
- Dernière version
- 1.25.0
- Dernier commit
- 12 nov. 2026
- Licence
- Apache-2.0
Qu'est-ce que DebugBundle MCP ?
DebugBundle est un serveur MCP. Permettez aux agents IA d'inspecter les rapports d'erreurs d'exécution, le contexte d'incidents, les bundles de débogage, les analyses produit et les tests de santé des endpoints.
Résumé généré à partir du README du projet
À propos du MCP server DebugBundle
DebugBundle fournit une infrastructure de débogage en production qui permet aux agents IA d'inspecter les rapports d'erreurs d'exécution, les données de crash et le contexte d'incidents. Il s'adresse aux développeurs qui doivent enquêter sur des problèmes rencontrés par les clients, analyser des bundles de débogage déterministes et consulter des analyses produit via une interface de gestion unifiée. Le serveur peut être exécuté localement via stdio en utilisant npx ou installé globalement, et il prend en charge divers clients, notamment Claude Desktop, Cursor et Claude Code.
Les utilisateurs peuvent se connecter en utilisant l'état d'authentification CLI existant, un DEBUGBUNDLE_MEMBER_TOKEN pour les environnements headless, ou un bearerToken explicite pour des appels d'outils spécifiques. Le serveur inclut des outils spécialisés pour vérifier la santé du système, tels que des diagnostics de type doctor et smoke, ainsi que pour gérer les flux d'analyse. Contrairement aux plateformes d'observabilité générales, cet outil se concentre sur l'inspection approfondie des bundles de débogage, des artefacts de reproduction et des preuves spécifiques d'utilisation du produit pour faciliter une réponse rapide aux incidents.
Ce que vous pouvez faire avec
- 1Enquêter sur les incidents d'exécutionUn agent peut récupérer le contexte complet et les détails des incidents actifs pour aider à diagnostiquer les erreurs.
- 2Analyser les modèles d'utilisation du produitLes développeurs peuvent interroger des métriques agrégées telles que la répartition par appareil, les métriques de route et l'analyse de tunnel (funnel analysis).
- 3Récupérer des artefacts de reproductionUne IA peut extraire des bundles de débogage déterministes et des chemins de reproduction pour recréer les bugs signalés.
Extrait du README du projet. Chaque cas d'utilisation est vérifié par rapport à une citation du document.
Comment installer DebugBundle MCP
Formats vérifiés le 10 nov. 2026Installer DebugBundle MCP dans Claude Code
$ claude mcp add --env DEBUGBUNDLE_MEMBER_TOKEN=<YOUR_DEBUGBUNDLE_MEMBER_TOKEN> mcp -- npx -y @debugbundle/mcpInstaller DebugBundle MCP dans Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"mcp": {
"command": "npx",
"args": [
"-y",
"@debugbundle/mcp"
],
"env": {
"DEBUGBUNDLE_MEMBER_TOKEN": "<YOUR_DEBUGBUNDLE_MEMBER_TOKEN>"
}
}
}
}Installer DebugBundle MCP dans VS Code
.vscode/mcp.json
{
"servers": {
"mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@debugbundle/mcp"
],
"env": {
"DEBUGBUNDLE_MEMBER_TOKEN": "<YOUR_DEBUGBUNDLE_MEMBER_TOKEN>"
}
}
}
}Installer DebugBundle MCP dans Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"mcp": {
"command": "npx",
"args": [
"-y",
"@debugbundle/mcp"
],
"env": {
"DEBUGBUNDLE_MEMBER_TOKEN": "<YOUR_DEBUGBUNDLE_MEMBER_TOKEN>"
}
}
}
}Installer DebugBundle MCP dans Codex
~/.codex/config.toml
[mcp_servers.mcp] command = "npx" args = ["-y", "@debugbundle/mcp"] [mcp_servers.mcp.env] DEBUGBUNDLE_MEMBER_TOKEN = "<YOUR_DEBUGBUNDLE_MEMBER_TOKEN>"
Installer DebugBundle MCP dans Gemini CLI
~/.gemini/settings.json
{
"mcpServers": {
"mcp": {
"command": "npx",
"args": [
"-y",
"@debugbundle/mcp"
],
"env": {
"DEBUGBUNDLE_MEMBER_TOKEN": "<YOUR_DEBUGBUNDLE_MEMBER_TOKEN>"
}
}
}
}Configuration
DEBUGBUNDLE_MEMBER_TOKENSecretOptional DebugBundle access token used by hosted API and MCP management tools when CLI auth state is unavailable.
DEBUGBUNDLE_API_URLOptional DebugBundle API base URL for self-hosted, staging, or other non-default API environments.
| Nom | Description | Type |
|---|---|---|
| DEBUGBUNDLE_MEMBER_TOKEN | Optional DebugBundle access token used by hosted API and MCP management tools when CLI auth state is unavailable. | Secret |
| DEBUGBUNDLE_API_URL | Optional DebugBundle API base URL for self-hosted, staging, or other non-default API environments. |
Vérifications automatisées
Exécuté le 13 nov. 2026Rapport complet →A passé nos vérifications automatisées. Il ne s'agit pas d'un audit de sécurité : lisez le code et donnez au serveur l'accès le plus restreint dont il a besoin. Fonctionnement des vérifications
- Dépôt source lié et accessibleRéussi
- Licence open source (OSI)Réussi
- Commit ou version publiée au cours de l'année écouléeRéussi
- Nom du package non proche d'un package populaireRéussi
- L'endpoint distant utilise HTTPSNon vérifié
- Les outils destructifs sont étiquetésNon vérifié
- Aucune instruction cachée destinée au modèleRéussi
- Aucun avis critique dans le paquet ni ses dépendancesRéussi
README
Voir sur GitHub@debugbundle/mcp
Local artifact safety in 1.19.4
Retained bundle and reproduction paths must stay in their canonical local artifact
directories. Unsafe metadata returns invalid_local_artifact_path without reading,
rewriting or deleting unrelated files. Symlinked files/directories fail closed.
Normal local stores and their existing size allowance are preserved; local state
and processing writes use guarded atomic replacement. This supersedes earlier clients.
Cloud cache safety in 1.19.4
Upgrade to 1.19.4 for incident-ID validation before cloud requests and cache writes.
Unsafe IDs return invalid_incident_id; UUIDs and existing opaque IDs remain supported.
Cloud cache reads, writes and retention reject symbolic links; writes use guarded
atomic replacement. This corrects a path traversal present in earlier clients.
Installation guidance in 1.19.4
Prefer one project per system across service repositories, reuse existing connections, and keep separate projects for different access or privacy policies. Inspect existing projects before first-time connect; name matching does not infer system membership.
Local correlation safety in 1.19.1
Trace correlation crosses services only within the same project and environment.
If an older cache contains mixed retained source events, reads and incremental
processing fail with local_incident_scope_mismatch. Preserve the local store,
then explicitly rebuild from its retained event files using
debugbundle process --preset <minimal|balanced|investigative> with the desired
capture preset. This rebuild regenerates local incident/artifact state; it does
not change cloud records or the retained event files.
Project/service consolidation 1.19.1
Add logical service context and checked project-merge preview, apply, status, verification, resume and cancellation. Existing identities, credentials and restricted scopes remain compatible. Merge apply requires a qualified compatible core 1.21.0 runtime and remains disabled by default.
Connected doctor diagnostics check API health and saved access-token authentication with a one-incident probe restricted to cloud_project_id. Missing or blank connected project scope fails before any request. Incident contents are discarded and are not included in the report. Local-only diagnostics make no cloud request.
Connected-workspace incident lists use the saved connection's cloud_project_id
unless projectId is explicitly supplied. This also applies to source: "cloud"
and every cloud page. An unusable connected project fails with
invalid_local_connection_config before the list request; specify the intended
project or repair the connection. Local evidence and unconnected account-wide
member reads retain their existing behaviour.
MCP server for runtime error reporting, crash reporting, incident response, endpoint health checks, debug bundles, and product analytics. DebugBundle lets agents inspect customer-facing incidents, deterministic bundles, product-usage evidence, reproductions, probes, alerts, webhooks, projects, and setup state through the same management surface as the API and CLI. It is production debugging infrastructure, not a generic infrastructure-monitoring or observability platform.
Corrective update 1.18.3
Connected incident lists now retain their selected cloud project across all pages, including explicit cloud reads. Invalid connected scope fails before the list request. Tool names, schemas, access-token authentication and local evidence selection remain compatible. The coordinated OpenClaw plugin repairs native ESM loading and adds installed-host/runtime checks; marketplace security acceptance stays separate.
Install
Ordinary authenticated MCP includes account/project notification preferences, channel-specific pause/resume, and daily email scheduling with local time and IANA timezone. These tools use the same permissions and policies as the API and CLI; the hosted read-only and restricted catalogs remain unchanged. See the tool reference.
Run the stdio server directly with npm:
npx @debugbundle/mcp
Or install globally:
npm install -g @debugbundle/mcp
debugbundle-mcp
Supported Node.js versions: 22.x through 26.x.
MCP Client Config
{
"mcpServers": {
"debugbundle": {
"command": "npx",
"args": ["@debugbundle/mcp"]
}
}
}
Use npx -y @debugbundle/mcp in clients that require noninteractive package execution.
Install Matrix
| Environment | Recommended path | Notes |
|---|---|---|
| Generic local MCP client | npx @debugbundle/mcp |
stdio transport |
| Claude Desktop local MCP | local MCP server config | uses local machine auth/config |
| Claude Code plugin | /plugin marketplace add debugbundle/debugbundle |
installs bundled MCP config and DebugBundle skill |
| Codex developer plugin | codex plugin add debugbundle-codex@debugbundle |
repository marketplace; local MCP and workflow skill |
| Codex direct MCP | codex mcp add debugbundle -- npx -y @debugbundle/mcp@1.23.0 --local-auth |
app, CLI, and IDE on the same host |
| Cursor | MCP config with npx @debugbundle/mcp |
stdio transport |
| VS Code / GitHub MCP Registry | com.debugbundle/mcp |
official registry metadata |
| OpenClaw / ClawHub | DebugBundle skill plus MCP config | use the published skill for workflow guidance |
| CI/headless agents | DEBUGBUNDLE_MEMBER_TOKEN |
never use a project token |
| Self-hosted DebugBundle | DEBUGBUNDLE_API_URL plus access-token authentication |
points the server at your API base URL |
This package is the supported public local stdio path. The separate OpenAI Plugin
uses an OAuth-protected read-only remote endpoint at
https://mcp.debugbundle.com/mcp. Its review/publication process is independent and
does not alter this package's catalog or authentication.
Local authentication profile
MCP 1.9.0 adds npx @debugbundle/mcp --local-auth. This opt-in profile removes bearerToken from tool schemas, rejects per-call credentials and unknown fields, and uses only the server's startup CLI/environment access-token authentication. Hosted tools that require an access token fail with mcp_tool_error:auth_state_missing before an API request when auth is absent; run debugbundle login on that host or configure the server environment and restart the connection. Local-only retrieval remains available without a token. The default invocation preserves the legacy schemas and explicit per-tool token precedence.
Codex
Codex can use the existing stdio server independently of the hosted OpenAI plugin. See the Codex developer package and Codex setup guide for the repository marketplace, direct configuration, authentication, verification, and removal. The repository plugin must be released on the default branch before GitHub installation works; local checkout installation is available for candidate validation.
Claude Desktop
In Claude Desktop, open Settings > Developer, edit the local MCP config, and add:
{
"mcpServers": {
"debugbundle": {
"command": "npx",
"args": ["-y", "@debugbundle/mcp"]
}
}
}
Run debugbundle login first to reuse local CLI auth state, or add DEBUGBUNDLE_MEMBER_TOKEN to the server environment for managed/headless use. Set DEBUGBUNDLE_API_URL only for self-hosted or non-default API hosts.
Claude Code Plugin
Claude Code users can add DebugBundle's first-party marketplace from this repository:
/plugin marketplace add debugbundle/debugbundle
/plugin install debugbundle@debugbundle
The plugin package lives at apps/mcp/claude-code/debugbundle and bundles a Claude Code skill. See the Claude Code setup guide for the plugin's pinned MCP version, direct MCP configuration, authentication, verification, updates, and removal. It is also structured for Claude community marketplace review; do not describe it as listed in claude-community until Anthropic accepts and publishes it.
Authentication
| Mode | Use | Notes |
|---|---|---|
| CLI auth state | Local developer machines | Reuses ~/.debugbundle/auth.json when available. |
DEBUGBUNDLE_MEMBER_TOKEN |
Headless or marketplace-managed clients | Access tokens are for CLI/API/MCP read and management operations. |
Per-tool bearerToken |
Explicit advanced automation | Overrides default auth for that call only. |
| Project token | SDK ingestion only | Do not use project tokens for MCP retrieval or management. |
What Agents Can Do
-
Read public project acquisition/activation definitions and aggregate reports with
list_analytics_flowsandget_analytics_flow_report; owners/admins can manage them withsave_analytics_flowandarchive_analytics_flow. These developer tools use the same project authorization and flow services as API, CLI and web. The separate hosted OpenAI catalog is unchanged. -
List active incidents and fetch full incident context.
-
Fetch deterministic debug bundles and reproduction artifacts.
-
Discover observed filter choices with
get_analytics_filter_optionsfor an authorised project, period, granularity and service/environment. Bounded sets exposevaluesandtruncated, with approved custom keys and no generation quota. Empty/unavailable choices must not be replaced with invented defaults. This tool is ordinary MCP only; restricted agent/OpenAI catalogues stay unchanged. -
Query aggregate usage, routes, device/browser/OS/language segments, referrers, actions, funnels, and journey patterns without waiting for an analysis artifact through
get_usage_summary,get_route_metrics,get_device_breakdown,get_action_metrics,get_funnel_analysis, and related reads. -
Inspect retained redacted journey samples, analytics opportunities, and generated AnalyticsBundles; request a bounded analysis artifact when aggregate metrics alone are insufficient.
-
Read analytics settings before proposing privacy, retention, consent, capture, or approved custom-dimension changes; update them only with explicit owner/admin intent.
-
List saved analytics funnels and, with owner/admin access, create, update, or archive reusable funnel definitions through
list_saved_analytics_funnels,create_saved_analytics_funnel,update_saved_analytics_funnel, andarchive_saved_analytics_funnel. -
Inspect hosted health checks, probes, alerts, webhooks, projects, members, billing, capture policy, and GitHub automation state.
-
Run local and hosted verification through tools such as
verify_local,verify_cloud,doctor,smoke, andanalyze.
verify_app_event provides real SDK-driven app proof, matching the CLI's
verify cloud --expect-app-event. Pass projectId and at least one of service,
traceId, or requestId; environment, maxAgeMinutes, and authFilePath are
optional. It reads existing incidents/bundles and never sends synthetic events.
The existing verify_cloud schema and description remain unchanged. The new tool
is available through ordinary and local-auth stdio MCP and its OpenClaw projection;
hosted read-only and restricted agent catalogs remain unchanged.
- Resolve or reopen incidents after verification.
For analytics questions, use direct aggregate tools first and generate an AnalyticsBundle only when a bounded analysis needs a durable artifact. The product does not create one bundle per visit.
Troubleshooting
| Symptom | Check |
|---|---|
| Node.js launch failure | Use Node.js 22.x through 26.x. Configure the client to use a supported node or npx runtime. |
| Missing local auth | Run debugbundle login, or set DEBUGBUNDLE_MEMBER_TOKEN for headless and managed clients. |
| Invalid token | Use a dbundle_mem_ access token. Project tokens are SDK ingestion-only credentials. |
| Wrong API host | Leave DEBUGBUNDLE_API_URL unset for DebugBundle Cloud; set it only for self-hosted or non-default API hosts. |
| Local repo not initialized | Run debugbundle setup before local-only diagnostics, local bundle analysis, or generated project-skill workflows. |
Links
- Docs: https://debugbundle.com/docs/mcp
- Agent workflows: https://debugbundle.com/docs/agent-workflows
- LLM index: https://debugbundle.com/llms.txt
- MCP tool schema: https://debugbundle.com/schemas/mcp-tools.json
- OpenAI Plugin candidate: https://debugbundle.com/docs/mcp/openai-plugin
- Official MCP Registry metadata: https://github.com/debugbundle/debugbundle/blob/main/apps/mcp/server.json
Security And Trust
- Official MCP Registry name:
com.debugbundle/mcp. - Official npm package:
@debugbundle/mcp. - Source repository: https://github.com/debugbundle/debugbundle/tree/main/apps/mcp
- License: Apache-2.0.
- The server uses stdio transport and local process credentials. It does not include hidden hosted management auth.
- Public examples must use placeholders only; never paste real access tokens, project tokens, webhook secrets, or customer configuration into marketplace listings.
License
Apache-2.0.
disconnect_github_installation calls the existing organization-wide disconnect
route. It requires the active organization's owner and removes repository assignments
for all its projects, including cleanup after downgrade. It does not uninstall the
App on GitHub. Install/reconnect uses the dashboard browser flow to retain the signed
state cookie. The ordinary/local-auth catalog now contains 134 tools;
the hosted 23-tool and restricted five-tool profiles remain unchanged.
test_webhook_event accepts all eight supported webhook events through the existing
scoped test service. The legacy test_webhook schema remains verification-only.
Both queue a signed synthetic envelope without creating real incidents or bundles.
Public status pages
get_public_status_page, list_public_status_page_options,
save_public_status_page and preview_public_status_page manage owner-controlled
publication through the same API as Project Health. Read the options, select checks
explicitly and save {title, enabled, projects:[{project_id, check_ids}]}. A save with
enabled: false unpublishes without changing the URL. Publish only on the owner's
instruction: selected project/check names and aggregate availability become public;
URLs and diagnostics stay private. New checks remain private. The hosted read-only
and restricted-agent profiles do not expose publication tools. See the
status-page guide.
Questions sur DebugBundle MCP
Comment ajouter DebugBundle MCP à Claude Code ?
Exécutez claude mcp add --env DEBUGBUNDLE_MEMBER_TOKEN=<YOUR_DEBUGBUNDLE_MEMBER_TOKEN> mcp -- npx -y @debugbundle/mcp dans votre terminal. Ajoutez --scope user pour le rendre disponible dans tous les projets.
Comment ajouter DebugBundle MCP à Cursor ?
Ouvrez ~/.cursor/mcp.json et ajoutez le serveur sous mcpServers, avec la configuration Cursor indiquée dans la section d'installation ci-dessus.
Quel est l'objectif principal de DebugBundle ?
Il s'agit d'une infrastructure de débogage en production conçue pour le reporting d'erreurs d'exécution, les rapports de crash, la réponse aux incidents, les tests de santé des endpoints et les analyses produit.
Comment puis-je m'authentifier dans un environnement headless ou CI ?
Pour les clients headless ou gérés par le marketplace, vous devez utiliser la variable d'environnement DEBUGBUNDLE_MEMBER_TOKEN.
Les agents peuvent-ils gérer les flux d'analyse ?
Oui, les propriétaires et les administrateurs peuvent gérer les définitions publiques d'acquisition/activation de projet et les rapports agrégés à l'aide d'outils spécifiques.
S'agit-il d'une plateforme d'observabilité générale ?
Non, il s'agit spécifiquement d'une infrastructure de débogage en production plutôt que d'une plateforme générique d'observabilité ou de monitoring.