bugfender-mcp
OfficialUse Bugfender through MCP to inspect app observability data and make limited issue-status updates.
Identify the signed-in user and list teams/apps.
Fetch app metadata, versions, SDK snippets, and app summaries.
Search/count logs with filters for tags, level, app version, device, and date range.
Inspect devices, device counts, and device activity.
Analyze crashes with groups, stats, device stats, and details.
List/get issue groups and filter by type, status, version, or text.
View issue stats, affected devices, and device-level stats.
Update issue status when authorized with
mcp:issues:write.Retrieve feedback entries.
Inspect network request aggregates and details.
Use resource templates for SDK snippets, logs, and issue groups.
Provides tools to set up Bugfender SDK for Android applications, including retrieving platform-specific SDK snippets for onboarding.
Provides tools to set up Bugfender SDK for Angular applications, including retrieving platform-specific SDK snippets for onboarding.
Provides tools to set up Bugfender SDK for Flutter applications, including retrieving platform-specific SDK snippets for onboarding.
Provides tools to set up Bugfender SDK for Ionic applications, including retrieving platform-specific SDK snippets for onboarding.
Provides tools to set up Bugfender SDK for iOS applications, including retrieving platform-specific SDK snippets for onboarding.
Provides tools to set up Bugfender SDK for JavaScript applications, including retrieving platform-specific SDK snippets for onboarding.
Provides tools to set up Bugfender SDK for jQuery applications, including retrieving platform-specific SDK snippets for onboarding.
Provides tools to set up Bugfender SDK for .NET applications (including .NET MAUI), including retrieving platform-specific SDK snippets for onboarding.
Provides tools to set up Bugfender SDK for React applications, including retrieving platform-specific SDK snippets for onboarding.
Provides tools to set up Bugfender SDK for Unity applications, including retrieving platform-specific SDK snippets for onboarding.
Click on "Deploy 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., "@bugfender-mcp list my apps"
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.
Bugfender MCP
Bugfender's hosted MCP service connects AI clients to Bugfender through remote Streamable HTTP and OAuth:
https://mcp.bugfender.com/mcpThe @bugfender/mcp npm package remains available as a deprecated local stdio
fallback for existing and self-hosted installations.
What It Provides
user-scoped Bugfender read access through MCP
automatic access-token refresh when a refresh token is configured
logs, devices, app metadata, crash aggregation, and issue aggregation tools
SDK snippet retrieval for app onboarding
resource templates for snippets, logs, and issue groups
companion Bugfender skills distributed from
bugfender/bugfender-skills
Related MCP server: bugsink-mcp
Maintainers
development workflow: DEVELOPMENT.md
release and publish flow: RELEASING.md
Recommended: hosted OAuth
In ChatGPT or Codex, install the public Bugfender plugin and connect the included
Bugfender app. In any compatible remote MCP client, add
https://mcp.bugfender.com/mcp and choose OAuth authentication.
The client discovers the protected resource and Bugfender authorization server, opens the Bugfender sign-in and consent UI, and manages short-lived access and refresh tokens. Hosted users must not manually copy an API token into the connection.
OAuth scopes
mcp:readgrants read-only access to identity, teams, apps, SDK metadata, logs, devices, crashes, issues, feedback, network data, and summaries the signed-in user can already access.mcp:issues:writegrants onlyupdate_issue_status. It does not grant general Bugfender administration or other write operations.
Disconnect and revoke
Use the client's Bugfender Disconnect action to revoke the hosted grant and its access and refresh tokens. If a client lists the plugin and connection separately, disconnect the connection before uninstalling the plugin. A future tool call must start a new OAuth flow.
Privacy
The hosted MCP forwards the request bearer token to the Bugfender API and returns data the signed-in user is authorized to access. It does not persist user credentials or expose them in tool results. The MCP client and AI provider may separately process tool inputs and return Bugfender data under their own privacy and retention terms. See Bugfender's Privacy Policy and Terms of Service.
Deprecated: local stdio package
Existing installations and clients without remote OAuth can continue to run:
npx -y @bugfender/mcpDo not use this setup for a new public-cloud connection. Prefer the hosted URL or public plugin instead.
After adding or updating the MCP server in your IDE or agent, restart that client so it reloads the new MCP configuration cleanly.
If you are running from inside this repository checkout, do not use npx @bugfender/mcp or npx -p @bugfender/mcp bugfender-mcp. npm can resolve the current package instead of the published tarball and fail with bugfender-mcp: not found.
For local development, build and run the generated entrypoint directly:
pnpm build
pnpm startLocal stdio configuration
BUGFENDER_API_TOKEN: required access tokenBUGFENDER_REFRESH_TOKEN: recommended for automatic token refreshBUGFENDER_API_URL: optional override, defaults tohttps://dashboard.bugfender.com/api~/.bugfender/mcp.json: optional config file and local token store for rotated credentials
{
"default": {
"apiToken": "YOUR_ACCESS_TOKEN",
"refreshToken": "YOUR_REFRESH_TOKEN",
"apiUrl": "https://dashboard.bugfender.com/api"
}
}When a refresh token is provided, the MCP stores rotated credentials in ~/.bugfender/mcp.json so automatic refresh survives restarts. Updating the IDE config with a newly generated refresh token resets that local state.
These credentials and the local token store apply only to the stdio executable.
The hosted HTTP executable reads a bearer token from each request and never
reads or writes ~/.bugfender/mcp.json.
If you are using local or self-hosted Bugfender credentials, BUGFENDER_API_URL must point to the matching backend. For example, local credentials generated from https://dashboard:3000 will not work against https://dashboard.bugfender.com/api.
Legacy Cursor / Claude Code configuration
{
"mcpServers": {
"bugfender": {
"command": "npx",
"args": ["-y", "@bugfender/mcp"],
"env": {
"BUGFENDER_API_TOKEN": "YOUR_ACCESS_TOKEN",
"BUGFENDER_REFRESH_TOKEN": "YOUR_REFRESH_TOKEN",
"BUGFENDER_API_URL": "https://dashboard.bugfender.com/api"
}
}
}
}Legacy Codex CLI configuration
codex mcp add bugfender \
--env BUGFENDER_API_TOKEN='YOUR_ACCESS_TOKEN' \
--env BUGFENDER_REFRESH_TOKEN='YOUR_REFRESH_TOKEN' \
--env BUGFENDER_API_URL='https://dashboard.bugfender.com/api' \
-- npx -y @bugfender/mcpAfter running codex mcp add, restart the Codex session before testing who_am_i or list_apps.
Legacy Gemini CLI configuration
gemini mcp add bugfender npx -y @bugfender/mcp \
--env BUGFENDER_API_TOKEN='YOUR_ACCESS_TOKEN' \
--env BUGFENDER_REFRESH_TOKEN='YOUR_REFRESH_TOKEN' \
--env BUGFENDER_API_URL='https://dashboard.bugfender.com/api'After running gemini mcp add, start a new Gemini CLI session or reload MCP servers before testing who_am_i or list_apps.
Legacy Codex App configuration
In the custom MCP server form:
Name:bugfenderCommand to launch:npxArgument 1:-yArgument 2:@bugfender/mcpBUGFENDER_API_TOKEN:YOUR_ACCESS_TOKENBUGFENDER_REFRESH_TOKEN:YOUR_REFRESH_TOKENBUGFENDER_API_URL:https://dashboard.bugfender.com/api
Add the arguments as separate rows, not as one combined string.
After saving the server, restart the app before testing who_am_i or list_apps.
Hosted Streamable HTTP deployment
Build and start the HTTP entry point with:
pnpm build
pnpm start:httpIt exposes:
POST /mcp: stateless MCP Streamable HTTP endpointGET /healthz: liveness checkGET /readyz: readiness check
TLS is terminated by the production ingress. Every /mcp request must include
Authorization: Bearer <token>. The process creates an isolated MCP server and
Bugfender API client for that request; the token is neither shared nor persisted.
Hosted configuration:
BUGFENDER_API_URL(defaulthttps://dashboard.bugfender.com/api)BUGFENDER_MCP_HOST(default0.0.0.0)BUGFENDER_MCP_PORT(default3002)BUGFENDER_MCP_MAX_REQUEST_BYTES(default1048576)BUGFENDER_MCP_MAX_RESPONSE_BYTES(default524288)BUGFENDER_MCP_MAX_CONCURRENCY(default100)BUGFENDER_MCP_REQUEST_TIMEOUT_MS(default35000)BUGFENDER_MCP_SHUTDOWN_TIMEOUT_MS(default10000)BUGFENDER_OPENAI_APPS_CHALLENGE_TOKEN(optional; serves the exact plain-text OpenAI domain-verification token at/.well-known/openai-apps-challenge)
The hosted entry point uses JSON response mode within the Streamable HTTP
protocol. It is intentionally stateless, so GET and DELETE on /mcp return
405 Method Not Allowed.
The production container can be built and exercised locally with:
docker build -t bugfender-mcp .
docker run --rm --read-only --tmpfs /tmp:rw,noexec,nosuid,size=16m \
-p 3002:3002 bugfender-mcpThe image runs as UID/GID 10001, writes structured JSON logs to stderr, and
exposes Prometheus metrics on GET /metrics for cluster-internal scraping.
Hosted mode publishes OAuth protected-resource metadata at
GET /.well-known/oauth-protected-resource. Authentication challenges point
clients to that document. Production defaults to resource
https://mcp.bugfender.com/mcp, issuer https://dashboard.bugfender.com, and API
https://dashboard.bugfender.com/api;
staging deployments must override BUGFENDER_MCP_RESOURCE_URL and
BUGFENDER_OAUTH_ISSUER and BUGFENDER_API_URL with their staging values.
Documentation, privacy, and terms links can be overridden with BUGFENDER_MCP_DOCUMENTATION_URL,
BUGFENDER_MCP_PRIVACY_POLICY_URL, and BUGFENDER_MCP_TERMS_URL.
Hosted authentication troubleshooting
Use the exact endpoint and OAuth resource
https://mcp.bugfender.com/mcp.Do not configure
BUGFENDER_API_TOKENor paste a bearer token into a remote-hosted connection.Disconnect and reconnect to recover from expired or revoked grants or to request different scopes.
update_issue_statusrequiresmcp:issues:write; investigation tools requiremcp:read.A client must support remote Streamable HTTP, OAuth discovery, Authorization Code with PKCE, and resource indicators. Otherwise, use the deprecated local stdio fallback.
Hosted OAuth currently supports Bugfender's public cloud. Self-hosted deployments must use local stdio and set
BUGFENDER_API_URLto their backend.
Tools
who_am_ilist_teamslist_appsget_applist_app_versionsget_sdk_snippetget_crashesget_crash_statsget_crash_device_statsget_crash_detailssearch_logscount_logscount_devices_with_logsget_network_aggregatesget_network_detailssearch_devicescount_deviceslist_issuesget_issueupdate_issue_statusget_issue_statsget_issue_device_statsget_issue_devicesget_feedbackget_app_summary
Resources
bugfender://snippet/{app_id}/{platform}bugfender://app/{app_id}/logs?...bugfender://issue/{issue_id}?app_id={app_id}
Companion Skills
The companion skills now live in the separate bugfender/bugfender-skills repository. They encode opinionated workflows on top of the MCP tools:
use aggregation before logs
narrow time ranges early
size impact before deep-diving
end with a short triage summary
The MCP package gives the agent raw Bugfender capabilities. The skill adds an opinionated investigation workflow on top of those capabilities.
Use the skill when you want Cursor, Codex, or Claude Code to do things like:
help set up the Bugfender SDK in an app with the minimum required steps
fetch the SDK snippet for a platform and explain exactly where it goes
investigate the top crashes in an app
summarize issue or feedback trends over a time range
compare impact before and after an app version
identify likely cause, scope, and next checks
The investigation skill source lives in:
https://github.com/bugfender/bugfender-skills/tree/main/skills/bugfender
SDK Setup Skill
The dedicated onboarding skill also lives in bugfender/bugfender-skills.
Use it when you want Cursor, Codex, or Claude Code to:
detect the project platform automatically
fetch the correct Bugfender SDK snippet
map the setup to the real repository files
ask one short feature question when optional capabilities like crash reporting or Android logcat matter
apply the minimum integration changes
reduce the developer’s work to one final verification step
It also includes platform-specific references for:
iOS
Android
Flutter
Unity
.NET MAUI
Cordova
Ionic
Angular
React
Vue
JavaScript
jQuery
Titanium
Web
React Native
The skill source lives in:
https://github.com/bugfender/bugfender-skills/tree/main/skills/bugfender-sdk-setup
Install Skills In Cursor, Codex, Or Claude Code
Cursor, Codex, and Claude Code can install the skills directly from GitHub without cloning the repo manually.
In the agent chat inside your IDE, run this prompt with the built-in installer skill:
Use $skill-installer to install these skills from https://github.com/bugfender/bugfender-skills:
- skills/bugfender
- skills/bugfender-sdk-setupAfter installation, restart the client and use:
Use $bugfender-sdk-setup to set up Bugfender in this app with the minimum required changes.Available Tools
25 toolscount_devicesD
Inputs: app_id (required), name, model, enabled, +4 more.
count_devices_with_logsD
Inputs: text (required), app_id (required), date_range_end, date_range_start.
count_logsD
Inputs: app_id (required), tags, text, level, +4 more.
get_appD
Inputs: app_id (required).
get_app_summaryD
Inputs: app_id (required), date_range_start.
get_crash_detailsD
Inputs: hash (required), app_id (required).
get_crash_device_statsD
Inputs: app_id (required), date_range_start (required), hash, title, +1 more.
get_crashesA
Returns a list of crash groups for an app, optionally filtered by date range. Does not support filtering by status — use list_issues with type=crash and issue_status if you need open/resolved/closed crashes only.
Inputs: app_id (required), limit, date_range_end, date_range_start.
get_crash_statsD
Inputs: app_id (required), date_range_start (required), hash, title, +1 more.
get_feedbackD
Inputs: app_id (required), page, page_size, date_range_end, +1 more.
get_issueD
Inputs: app_id (required), issue_id (required), date_range_end, date_range_start.
get_issue_devicesD
Inputs: hash (required), app_id (required), page, order, +8 more.
get_issue_device_statsD
Inputs: app_id (required), date_range_end (required), date_range_start (required), hash, +5 more.
get_issue_statsD
Inputs: app_id (required), date_range_end (required), date_range_start (required), hash, +5 more.
get_network_aggregatesD
Inputs: app_id (required), os, os_version, app_version, +4 more.
get_network_detailsD
Inputs: app_id (required), domain (required), os, endpoint, +7 more.
get_sdk_snippetD
Inputs: app_id (required), platform (required).
list_appsD
Inputs: no named parameters.
list_app_versionsD
Inputs: app_id (required).
list_issuesA
Lists issue groups for an app. Supports filtering by type (issue, crash, feedback) and status (open, resolved, closed). Use this instead of get_crashes or get_feedback when you need status filtering or combined results.
Inputs: app_id (required), page, type, query, +6 more.
list_teamsD
Inputs: no named parameters.
search_devicesD
Inputs: app_id (required), name, model, order, +10 more.
search_logsD
Inputs: app_id (required), tags, text, level, +6 more.
update_issue_statusA
Updates the status of an issue group (issues aggregation). Use this to mark issues as resolved, closed, in progress, etc.
Inputs: app_id (required), status (required), issue_id (required).
who_am_iD
Inputs: no named parameters.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 25 tools
Many tools have similar names (e.g., get_crashes, get_crash_details, get_crash_stats) and most lack descriptions, making it hard to distinguish their exact purposes. An agent would likely misselect between crash-related tools.
The naming generally follows a verb_noun snake_case pattern (e.g., list_apps, get_crashes, search_logs). However, 'who_am_i' is an outlier that breaks the pattern, and the mix of 'list', 'get', 'search', 'count' is acceptable but slightly inconsistent.
With 25 tools, the server is on the heavy side for a monitoring/tracking API. While each tool may serve a specific need, the count is borderline and could be reduced by combining related tools (e.g., crash stats into one tool with parameters).
The tool surface covers reading and listing for most resources (crashes, issues, feedback, logs, devices, network). However, it lacks create, update (except for issue status), and delete operations, which limits the agent's ability to manage resources fully.
Maintenance
Related MCP Connectors
Official BugHerd MCP server. Sign in with OAuth, no API key needed.
MCP server for Appcircle mobile CI/CD platform.
MCP server for AI access to SmartBear tools, including BugSnag, Reflect, Swagger, PactFlow, QTM4J.
MCP server for Sentry - error monitoring, issue tracking, and debugging for AI assistants
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceMCP server for the air-Q Cloud API, enabling remote retrieval of air quality sensor data and historical analysis through read-only tools like listing devices, fetching readings, and exporting charts or data.50 PyPIApache 2.0
- AlicenseNot gradedqualityDmaintenanceHosted MCP server that exposes your self-hosted Bugsink error tracker as tools for LLMs, enabling issue management, release tracking, and stacktrace retrieval via chat prompts.112 npmMIT
- AlicenseBqualityDmaintenanceAn MCP server for authorized bug bounty work that enforces an evidence-driven workflow with session management, preflight checks, surface discovery, and verified scanning.12MIT

Auralogs MCP Serverofficial
AlicenseNot gradedqualityDmaintenanceA read-only MCP server for the Auralogs logging platform, enabling AI agents to query production logs, search errors, and retrieve AI analyses without write access. It allows you to ask your coding assistant 'what's broken in production right now?' by connecting to your logs via a simple bearer auth key.MIT