/init
**Experimental:** `sentry init` is experimental and may modify your source files. Always review changes before committing.
> /plugin marketplace add getsentry/toolkit > /plugin install sentry-mcp@sentry-mcp
How it fires
How this command gets triggered: by you, by Claude, or both.
- Fires itselfClaude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/init
Context preview
What this command does when you run it.
**Experimental:** `sentry init` is experimental and may modify your source files. Always review changes before committing.
Command definition
init.md> **Experimental:** `sentry init` is experimental and may modify your source files. Always review changes before committing.
**Authentication:** Interactive runs start the OAuth login flow automatically when credentials are missing or the stored session has expired. Non-interactive and CI runs must authenticate before running `sentry init`.
Examples
# Interactive setup
sentry init
# Non-interactive agent/CI setup
sentry init --yes --features errors,tracing,replay
# Dry run to preview changes
sentry init --dry-run
# Target a subdirectory
sentry init ./my-app
# Use a specific org (auto-detect project)
sentry init acme/
# Use a specific org and project
sentry init acme/my-app
# Assign a team when creating a new project
sentry init acme/ --team backend
# Enable specific features
sentry init --features profiling,replay
Target Syntax
| Syntax | Meaning | |--------|---------| | _(omitted)_ | Auto-detect org and project | | `acme/` | Use org `acme`, auto-detect or create project | | `acme/my-app` | Use org `acme` and project `my-app` | | `my-app` | Search for project `my-app` across all accessible orgs |
Path-like arguments (starting with `.`, `/`, or `~`) are always treated as the directory. The order of target and directory can be swapped — the CLI will auto-correct with a warning.
Available Features
| Feature | Description | |---------|-------------| | `errors` | Error monitoring | | `tracing` | Performance tracing | | `logs` | Log integration | | `replay` | Session replay | | `profiling` | Profiling | | `crons` | Cron job monitoring | | `agent-tracing` | Agent tracing for AI/LLM apps | | `mcp-observability` | MCP (Model Context Protocol) observability |
What the Wizard Does
1. **Detects your framework** — scans your project files to identify the platform and framework 2. **Installs the SDK** — adds the appropriate Sentry SDK package to your project 3. **Instruments your code** — configures error monitoring, tracing, and any selected features
Supported Platforms
- **JavaScript / TypeScript** — Next.js, Express, SvelteKit, React
- **Python** — Flask, FastAPI
More platforms and frameworks are coming soon.
Read more
> **Experimental:** `sentry init` is experimental and may modify your source files. Always review changes before committing.
**Authentication:** Interactive runs start the OAuth login flow automatically when credentials are missing or the stored session has expired. Non-interactive and CI runs must authenticate before running `sentry init`.
Examples
# Interactive setup sentry init # Non-interactive agent/CI setup sentry init --yes --features errors,tracing,replay # Dry run to preview changes sentry init --dry-run # Target a subdirectory sentry init ./my-app # Use a specific org (auto-detect project) sentry init acme/ # Use a specific org and project sentry init acme/my-app # Assign a team when creating a new project sentry init acme/ --team backend # Enable specific features sentry init --features profiling,replay
Target Syntax
| Syntax | Meaning | |--------|---------| | _(omitted)_ | Auto-detect org and project | | `acme/` | Use org `acme`, auto-detect or create project | | `acme/my-app` | Use org `acme` and project `my-app` | | `my-app` | Search for project `my-app` across all accessible orgs |
Path-like arguments (starting with `.`, `/`, or `~`) are always treated as the directory. The order of target and directory can be swapped — the CLI will auto-correct with a warning.
Available Features
| Feature | Description | |---------|-------------| | `errors` | Error monitoring | | `tracing` | Performance tracing | | `logs` | Log integration | | `replay` | Session replay | | `profiling` | Profiling | | `crons` | Cron job monitoring | | `agent-tracing` | Agent tracing for AI/LLM apps | | `mcp-observability` | MCP (Model Context Protocol) observability |
What the Wizard Does
1. **Detects your framework** — scans your project files to identify the platform and framework 2. **Installs the SDK** — adds the appropriate Sentry SDK package to your project 3. **Instruments your code** — configures error monitoring, tracing, and any selected features
Supported Platforms
- **JavaScript / TypeScript** — Next.js, Express, SvelteKit, React
- **Python** — Flask, FastAPI
More platforms and frameworks are coming soon.
Sentry's MCP service is primarily designed for human-in-the-loop coding agents. Our tool selection and priorities are focused on developer workflows and debugging use cases, rather than providing a general-purpose MCP server for all Sentry functionality.
Repo: getsentry/sentry-mcp
Other commands on toolkit.
explore
Enter explore mode - think through ideas, investigate problems, clarify requirements
propose
Propose a new change - create it and generate all artifacts in one step

