Skip to main content
Glama
bugfender-mcp

bugfender-mcp

Official
by bugfender

Bugfender MCP

Bugfender's hosted MCP service connects AI clients to Bugfender through remote Streamable HTTP and OAuth:

https://mcp.bugfender.com/mcp

The @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

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:read grants 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:write grants only update_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/mcp

Do 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 start

Local stdio configuration

  • BUGFENDER_API_TOKEN: required access token

  • BUGFENDER_REFRESH_TOKEN: recommended for automatic token refresh

  • BUGFENDER_API_URL: optional override, defaults to https://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/mcp

After 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: bugfender

  • Command to launch: npx

  • Argument 1: -y

  • Argument 2: @bugfender/mcp

  • BUGFENDER_API_TOKEN: YOUR_ACCESS_TOKEN

  • BUGFENDER_REFRESH_TOKEN: YOUR_REFRESH_TOKEN

  • BUGFENDER_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:http

It exposes:

  • POST /mcp: stateless MCP Streamable HTTP endpoint

  • GET /healthz: liveness check

  • GET /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 (default https://dashboard.bugfender.com/api)

  • BUGFENDER_MCP_HOST (default 0.0.0.0)

  • BUGFENDER_MCP_PORT (default 3002)

  • BUGFENDER_MCP_MAX_REQUEST_BYTES (default 1048576)

  • BUGFENDER_MCP_MAX_RESPONSE_BYTES (default 524288)

  • BUGFENDER_MCP_MAX_CONCURRENCY (default 100)

  • BUGFENDER_MCP_REQUEST_TIMEOUT_MS (default 35000)

  • BUGFENDER_MCP_SHUTDOWN_TIMEOUT_MS (default 10000)

  • 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-mcp

The 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_TOKEN or 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_status requires mcp:issues:write; investigation tools require mcp: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_URL to their backend.

Tools

  • who_am_i

  • list_teams

  • list_apps

  • get_app

  • list_app_versions

  • get_sdk_snippet

  • get_crashes

  • get_crash_stats

  • get_crash_device_stats

  • get_crash_details

  • search_logs

  • count_logs

  • count_devices_with_logs

  • get_network_aggregates

  • get_network_details

  • search_devices

  • count_devices

  • list_issues

  • get_issue

  • update_issue_status

  • get_issue_stats

  • get_issue_device_stats

  • get_issue_devices

  • get_feedback

  • get_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-setup

After 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 tools
count_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

    D1.7/5.0

    Scored across 25 tools

    Disambiguation2/5

    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.

    Naming Consistency4/5

    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.

    Tool Count3/5

    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).

    Completeness3/5

    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

    ActivityActive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      C
      maintenance
      MCP 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 PyPI
      Apache 2.0
    • A
      license
      Not graded
      quality
      D
      maintenance
      Hosted 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 npm
      MIT
    • A
      license
      B
      quality
      D
      maintenance
      An MCP server for authorized bug bounty work that enforces an evidence-driven workflow with session management, preflight checks, surface discovery, and verified scanning.
      12
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      A 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