Описание
AXI wrapper for the Sentry MCP server
README
Agent-friendly TypeScript CLI for the Sentry MCP server. It exposes Sentry investigation and operation workflows as predictable shell commands with compact structured output, repository defaults, OAuth support, and explicit binary destinations.
Requirements
- Node.js 24 or newer
- A Sentry account with access to the target organization and projects
Install
Install the standalone CLI globally so sentry-axi is available on PATH:
npm install --global @nikolauska/sentry-axi
sentry-axi auth login
Session hooks are an explicit, optional integration:
sentry-axi setup hooks
The command idempotently installs or repairs user-level session-start hooks for Claude Code, Codex, and OpenCode. Hooks resolve sentry-axi from PATH when it identifies the current executable and otherwise retain its absolute path.
As a lower-overhead alternative, install the static sentry-axi skill:
skills add nikolauska/sentry-axi --skill sentry-axi
Hooks provide ambient session context; the skill loads on demand. Install either integration or both after installing the standalone binary.
Quick start
# Inspect authentication and current repository context
sentry-axi
# Bind the current Git repository to a default Sentry project
sentry-axi init --organization acme --project web
# Investigate
sentry-axi issues search "unresolved errors"
sentry-axi issues view ISSUE_ID
sentry-axi traces view TRACE_ID
sentry-axi events search "count()" --fields count --dataset errors
# Download binary content only to an explicit path
sentry-axi attachments download EVENT_ID \
--organization acme --project web --attachment-id ATTACHMENT_ID \
--output artifact.bin
Run sentry-axi --help, sentry-axi <group> --help, or sentry-axi <group> <action> --help for focused usage. The CLI covers organizations, projects, teams, DSNs, issues, events, attachments, traces, replays, releases, dashboards, monitors, alerts, docs, profiles, resources, snapshots, conversations, and Sentry tool discovery.
Authentication and endpoint configuration
By default, sentry-axi connects to https://mcp.sentry.dev/mcp and uses MCP OAuth. Login credentials are saved with mode 0600 under $XDG_CONFIG_HOME/sentry-axi/oauth.json or ~/.config/sentry-axi/oauth.json.
sentry-axi auth login
sentry-axi auth login --manual
sentry-axi auth finish --code CODE
sentry-axi auth whoami
sentry-axi auth logout
Environment variables:
| Variable | Purpose |
|---|---|
SENTRY_AXI_MCP_URL |
Override the MCP endpoint |
SENTRY_AXI_MCP_TOKEN |
MCP OAuth access token, sent as Bearer |
SENTRY_ACCESS_TOKEN |
Sentry API token, sent as Sentry-Bearer |
SENTRY_AXI_AUTH_FILE |
Override the saved OAuth credential path |
The two token variables are mutually exclusive. Scoped endpoints such as /mcp/<organization>/<project> constrain commands and reject conflicting flags or repository bindings.
Repository context and output
sentry-axi init validates the organization and project before writing .sentry-project at the Git root. Commands use those values when their flags are omitted. Pass --all-projects only on commands where project scope is optional.
Results are structured for agent consumption. Long strings are previewed at 1,500 characters; add --full for complete content or --select id,title to project fields. Attachments and snapshot images require --output <path> and never emit binary bytes to stdout.
Create and update commands are direct mutations. Agents should confirm their target unless the user already requested that exact action, and inspect the target before retrying after an uncertain transport failure.
Development
mise installs Node 24 and exposes the local workflow:
mise install
mise run setup
mise run check
The same checks are available through npm:
npm ci
npm run format # Oxfmt
npm run lint # Oxlint
npm run typecheck
npm run build # Emit publishable JavaScript to dist/
npm test
npm run check
Development source runs directly as TypeScript. npm run build emits the JavaScript published from dist/. Update src/skill.ts or the command catalog, then run npm run build:skill and commit the generated skills/sentry-axi/SKILL.md. Run npm pack --dry-run to inspect the standalone package contents.
License
MIT
Установить Sentry Axi в Claude Desktop, Claude Code, Cursor
unyly install sentry-axiСтавит в Claude Desktop, Claude Code, Cursor и VS Code — сам разбирается с npx, uvx и сборкой из исходников.
Впервые? Поставь CLI: curl -fsSL https://unyly.org/install | sh
Или настроить вручную
Выполни в терминале:
claude mcp add sentry-axi -- npx -y @nikolauska/sentry-axiПошаговые гайды: как установить Sentry Axi
FAQ
Sentry Axi MCP бесплатный?
Да, Sentry Axi MCP бесплатный — установка в пару кликов через Unyly без оплаты.
Нужен ли API-ключ для Sentry Axi?
Нет, Sentry Axi работает без API-ключей и переменных окружения.
Sentry Axi — hosted или self-hosted?
Self-hosted: сервер запускается локально на твоей машине командой из раздела установки.
Как установить Sentry Axi в Claude Desktop, Claude Code или Cursor?
Открой Sentry Axi на unyly.org, выбери вкладку своего клиента (Claude Desktop, Claude Code, Cursor) и нажми Install — конфиг сгенерируется автоматически, без правки JSON.
Изменения
Версии и запрашиваемые доступы со временем.
- Новая версия опубликована
Похожие MCP
Fetch
Web content fetching and conversion for efficient LLM usage.
AWS KB Retrieval
Retrieval from AWS Knowledge Base using Bedrock Agent Runtime.
автор: modelcontextprotocolSpring AI MCP Server
Provides auto-configuration for setting up an MCP server in Spring Boot applications.
llm-analysis-assistant
A very streamlined mcp client that supports calling and monitoring stdio/sse/streamableHttp, and can also view request responses through the /logs page. It also
автор: xuzexin-hzMCP-Agent
A simple, composable framework to build agents using Model Context Protocol by [LastMile AI](https://www.lastmileai.dev)
автор: lastmile-aiSpring AI MCP Client
Provides auto-configuration for MCP client functionality in Spring Boot applications.
mcp.natoma.ai
A Hosted MCP Platform to discover, install, manage and deploy MCP servers by [Natoma Labs](https://www.natoma.ai)
MCPHub
Website to list high quality MCP servers and reviews by real users. Also provide online chatbot for popular LLM models with MCP server support.
MCP Servers Rating and User Reviews
Website to rate MCP servers, write authentic user reviews, and [search engine for agent & mcp](http://www.deepnlp.org/search/agent)
mkinf
An Open Source registry of hosted MCP Servers to accelerate AI agent workflows.
Compare Sentry Axi with
Не уверен что выбрать?
Найди свой стек за 60 секунд
Автор?
Embed-бейдж для README
Похожее
Все в категории ai
