sentry-mcp

Dependency freshness

Declared = lowest version the kit's dependency file (package.json, pyproject.toml or requirements.txt) allows. Latest = the npm "latest" tag or the newest PyPI release. TypeScript, the Stripe SDK, FastAPI and other 0.x packages are shown but not counted in the verdict.

What's in the stack

Framework

React Router, Astro, Vite

Database / ORM

SQLite

UI

Tailwind CSS, Radix UI

AI

Vercel AI SDK, Anthropic SDK

API layer

Hono

Testing

Vitest

Monitoring

Sentry, Vercel Analytics

Detected from declared dependencies. A listed package means it's installed, not necessarily fully wired up.

What the README says you get

• Admin
  Skill filteringYou can narrow the exposed tools with `?skills=inspect,triage` or `?disable-skills=seer`
• Admin
  Disable individual skillsYou can also disable any other skill to prevent unsupported tools from being exposed
• AI
  AI-powered search toolsThe AI-powered search tools (`search_errors`, `search_traces`, `search_logs`, `search_issues`, etc.) require an LLM provider
• AI
  Natural language query translationThese tools use natural language processing to translate queries into Sentry's query syntax
• AI
  Claude Code pluginInstall as a Claude Code plugin for automatic subagent delegation
• Auth
  Explicit Sentry token authRemote clients that support custom HTTP headers can pass an upstream Sentry API token directly
• Auth
  MCP OAuth access tokens`Bearer` is reserved for MCP OAuth access tokens
• Deploy
  Stdio transportwe also support a `stdio` transport
• Deploy
  Self-hosted Sentry supportNeed to connect to a self-hosted deployment? Add --host
• Deploy
  Plain HTTP supportFor isolated internal deployments that only expose plain HTTP, also add --insecure-http
• Testing
  MCP Inspector testingMCP includes an Inspector, to easily test the service
• Testing
  Unit testsThere are three test suites included: unit tests, evaluations, and manual testing
• Testing
  Evaluations**Evaluations** require a `.env` file in the project root with some config
• Testing
  Manual testing**Manual testing** (preferred for testing MCP changes)

Extracted from the kit's README by a local AI model (deepseek-flash) on Oct 12, 2026. Every item is checked against an exact README quote. A README claim is the maker's description, not something we tested.