Sentry

A Model Context Protocol server for retrieving and analyzing issues from Sentry.io

python

21

GitHub Stars

python

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "mcp-100-mcp-sentry": {
      "command": "uvx",
      "args": [
        "mcp-sentry",
        "--auth-token",
        "YOUR_SENTRY_TOKEN",
        "--project-slug",
        "YOUR_PROJECT_SLUG",
        "--organization-slug",
        "YOUR_ORGANIZATION_SLUG"
      ]
    }
  }
}

You can retrieve, inspect, and analyze Sentry issues directly through an MCP server dedicated to Sentry. This server lets you fetch individual issues, list issues by project, and receive formatted issue details to guide debugging and triage.

How to use

Use an MCP client to connect to the Sentry MCP server and run the available tools to query issues. You can retrieve a single issue by ID or URL, list issues for a specific project and organization, and get formatted issue details that include titles, IDs, status, severity, timestamps, event counts, and full stack traces.

How to install

Prerequisites: ensure you have a runtime to execute MCP servers. You can run the server via uvx, docker, or Python depending on your preference.

Configuration and start methods

[
  {
    "type": "stdio",
    "name": "sentry",
    "command": "uvx",
    "args": ["mcp-sentry", "--auth-token", "YOUR_SENTRY_TOKEN", "--project-slug", "YOUR_PROJECT_SLUG", "--organization-slug", "YOUR_ORGANIZATION_SLUG"]
  },
  {
    "type": "stdio",
    "name": "sentry_docker",
    "command": "docker",
    "args": ["run", "-i", "--rm", "mcp/sentry", "--auth-token", "YOUR_SENTRY_TOKEN", "--project-slug", "YOUR_PROJECT_SLUG", "--organization-slug", "YOUR_ORGANIZATION_SLUG"]
  },
  {
    "type": "stdio",
    "name": "sentry_py",
    "command": "python",
    "args": ["-m", "mcp_sentry", "--auth-token", "YOUR_SENTRY_TOKEN", "--project-slug", "YOUR_PROJECT_SLUG", "--organization-slug", "YOUR_ORGANIZATION_SLUG"]
  }
]

Using the MCP with Claude Desktop

If you are integrating with Claude Desktop, configure your MCP server entry to use the runtime you prefer (uvx, docker, or python) and provide your Sentry credentials and project details in the arguments.

Usage with Zed

For Zed, add a context server entry that points to the selected runtime and passes your Sentry details in the arguments. This allows you to access the MCP server from your Zed workflows.

Debugging

If you need to inspect or debug the MCP server during development, use the MCP inspector for your chosen runtime. Provide the same authentication and project details you use to run the server.

Notes

All commands assume placeholder values for tokens and project/organization slugs. Replace YOUR_SENTRY_TOKEN, YOUR_PROJECT_SLUG, and YOUR_ORGANIZATION_SLUG with your actual credentials and identifiers.

Available tools

get_sentry_issue

Retrieve and analyze a Sentry issue by ID or URL, returning details such as title, issue ID, status, level, first/last seen times, event count, and the full stacktrace.

get_list_issues

Retrieve and analyze Sentry issues by project slug and organization slug, returning a list of issues with titles, IDs, status, level, first/last seen times, event counts, and basic information.

sentry-issue

Fetch issue details from Sentry and return a formatted conversation context for integration into your chat flow.