Skip to main content

Overview

The Model Context Protocol (MCP) is a standardized protocol designed to facilitate communication and context sharing between AI agents and external services. It is especially useful for code assistants and chat-based AI tools that benefit from accessing a shared understanding of user intent, session state, and operational context.

Bugsee MCP server​

The Bugsee MCP server gives any MCP-aware AI agent secure, scoped access to your Bugsee data — issues (crashes, errors, and user-submitted bug reports), builds (app/install size, dependency changes, build-timing regressions, and dependency vulnerabilities), and debug symbols — without the developer leaving the agent's chat or editor. Combined with a code assistant that has access to your local source tree, this enables an end-to-end workflow: the agent fetches the issue or build, reads the stack trace or regression, locates the relevant files, and proposes a fix in the same conversation.

What you can do with it​

  • Triage: ask the agent which crashes are spiking, blocking the most users, or newly appearing in a specific app version.
  • Root-cause analysis: pull a single issue with its stack trace and surrounding log entries, and have the agent map it to source files and explain the failure — including memory/thread-leak analysis (leaking class, retained size, GC-root reference chain) for leak issues.
  • Regression hunting: diff issues across releases to spot what's new in the next build.
  • Bug-report to PR: turn a user-submitted bug report into a proposed code change without leaving the IDE.
  • Build health: check a build's app/install size, see what a release added or removed, and catch size, dependency, or build-timing regressions against the baseline.
  • Dependency vulnerabilities: read a build's vulnerability-scan summary and the diff versus the previous scan, or queue a fresh scan.
  • Symbolication diagnostics: when a crash still shows raw addresses, look up the module UUID to see whether its debug symbols were never uploaded, are still processing, or came through broken.
  • App onboarding: create a new application and get its app token to drop straight into the SDK initialization — for clients granted the mcp:write scope.

See Usage for concrete example prompts.

Supported clients​

The Bugsee MCP server works with any MCP client that supports HTTP transport. Tested clients include:

  • Claude Desktop (via Connectors)
  • Cursor
  • Windsurf
  • Visual Studio Code (GitHub Copilot Chat)
  • Cline
  • Zencoder
  • Antigravity

Configuration has per-client setup instructions.

Authentication​

Bugsee supports two ways for an MCP client to authenticate:

  • OAuth 2.1 with PKCE (recommended). Most modern MCP clients support this — they prompt the user to sign in to Bugsee in the browser, the user approves access, and the client receives a scoped, rotated access token. No long-lived secret lives on the user's machine. See Security for details.
  • Personal access token. For clients that don't yet support OAuth, you can generate a long-lived personal token from the Bugsee dashboard and paste it into the client config. Treat it as a password.

Both modes resolve to the same set of tools and the same data your account already has access to. Most tools are read-only. The two mutating tools are trigger_build_vuln_scan, which requires modify permission on the target application, and create_application, which requires the mcp:write scope plus organization admin or app_create permission. See Security.

Availability​

The Bugsee MCP server is generally available to all Bugsee users at no additional cost.

Found an issue, typo, or wrong statement on this page? Report it now →