What does MCP Sentry Server (Node.js) do?
It exposes Sentry error issue data (title, status, severity, stacktrace) as MCP prompts and tools, allowing LLMs or other MCP clients to fetch and analyze error reports.
@weekitmo
基本情報
MCP Sentry Server
Retrieve and analyze a Sentry issue by ID or URL
Retrieve and analyze a list of Sentry issues from a URL
MCP Sentry Server (Node.js) is a Node.js and TypeScript implementation of the Model Context Protocol (MCP) that integrates with the Sentry API to retrieve error reports and stacktraces through the MCP interface.
Install dependencies with pnpm install, build with pnpm build, then run with pnpm start or pnpm start:sse for SSE support. Configure a Sentry authentication token via a .env file or command-line arguments. For MCP client integration, add the provided JSON configuration to your MCP settings.
It exposes Sentry error issue data (title, status, severity, stacktrace) as MCP prompts and tools, allowing LLMs or other MCP clients to fetch and analyze error reports.
Node.js >= 20.0.0 and pnpm >= 10.5.2 are required.
Provide a Sentry authentication token via the `SENTRY_TOKEN` environment variable in a `.env` file, or pass it as a command-line argument with `--auth-token`.
Standard MCP over stdin/stdout and SSE (Server-Sent Events) over HTTP on port 3579 (configurable).
Use the JSON configuration with the `command` and `args` set to `npx -y @weekit/mcp-sentry@1.0.9` and environment variables for the token and API base URL.

SSH MCP server for AI agents: remote commands, file transfer, log search and server audits through OpenSSH.

Turn Perfex CRM into an AI-ready workspace. This MCP server exposes your full REST API to Claude, ChatGPT and any AI agent, so leads, invoices and tasks are one prompt away.

Give an agent a place to put large output. Instead of returning 40k characters of a build log into the conversation, it posts the file to DocBin and hands back one short URL. Docs render with syntax highlighting and mark

Local-first credential broker for MCP. AI coding agents (Claude Code, Cursor, Codex…) call APIs, SSH and databases through scoped presets; secrets stay in your OS keychain and never enter the agent's context.
Modelglass turns "which model should I use?" into a lookup instead of a guess. Seven tools give your agent live pricing across image, language, video, and audio models. Sourced and versioned, not scraped once and forgott
コメント