Skip to main content
Glama
sentry-self-hosted-mcp

sentry-self-hosted-mcp

by vitalypanait

sentry-self-hosted-mcp

MCP (Model Context Protocol) server for integrating self-hosted Sentry with AI assistants — Cursor, Claude Desktop, and any other MCP-compatible clients.

Tools

Tool

Description

list_projects

List all projects in the organization

list_issues

List issues with filtering by project, status, and level

get_issue

Issue details by numeric ID or short ID (e.g. PAYOUT-A6Z)

get_issue_with_stacktrace

Issue metadata + latest event stacktrace in a single call

get_latest_event

Latest event for an issue

get_event

Specific event by project slug and event ID

get_stack_frames

Stack frames for an event, with an option to show only in-app frames

Related MCP server: Sentry MCP Server

Requirements

  • Node.js 18+

  • Self-hosted Sentry instance with API access

  • Auth token with org:read, project:read, event:read scopes

Installation

npm install
npm run build

Configuration

The server reads three environment variables:

Variable

Description

Example

SENTRY_HOST

Your Sentry URL

https://sentry.example.com

SENTRY_TOKEN

Auth token

sntrys_...

SENTRY_ORG_SLUG

Organization slug

my-org

Tokens are created in Settings → Auth Tokens in Sentry.

Connecting to Cursor

Add to ~/.cursor/mcp.json:

{
  "mcpServers": {
    "sentry-selfhosted": {
      "command": "npx",
      "args": ["@vitaliypanait/sentry-self-hosted-mcp"],
      "env": {
        "SENTRY_HOST": "https://sentry.example.com",
        "SENTRY_TOKEN": "sntrys_...",
        "SENTRY_ORG_SLUG": "my-org"
      }
    }
  }
}

Local development alternative (if running from a cloned repo):

{
  "mcpServers": {
    "sentry-selfhosted": {
      "command": "node",
      "args": ["/absolute/path/to/sentry-mcp/dist/index.js"],
      "env": {
        "SENTRY_HOST": "https://sentry.example.com",
        "SENTRY_TOKEN": "sntrys_...",
        "SENTRY_ORG_SLUG": "my-org"
      }
    }
  }
}

Connecting to Claude Desktop

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "sentry-selfhosted": {
      "command": "npx",
      "args": ["@vitaliypanait/sentry-self-hosted-mcp"],
      "env": {
        "SENTRY_HOST": "https://sentry.example.com",
        "SENTRY_TOKEN": "sntrys_...",
        "SENTRY_ORG_SLUG": "my-org"
      }
    }
  }
}

Cursor Rule

To make Cursor automatically fetch Sentry context when you mention an issue or ask about a bug, add a rule to your project.

Copy examples/cursor-rule.mdc into your project as .cursor/rules/sentry.mdc.

With alwaysApply: false the rule activates only when relevant (recommended). Change to alwaysApply: true to apply it to every request in the project.

Development

# Run the compiler in watch mode
npm run dev

# Type check
npx tsc --noEmit

Stack

  • MCP SDK — AI interaction protocol

  • Axios — HTTP client for the Sentry API

  • Zod — input validation for tools

Available Tools

7 tools
get_eventA

Get detailed information about a specific Sentry event by project slug and event ID. Returns exception details, stacktrace, tags, and context.

Inputs: event_id (required), project_slug (required).

get_issueB

Get information about a Sentry issue by its numeric ID or short ID (e.g. "PAYOUT-123"). Includes status, event count, first/last seen.

Inputs: issue_id (required).

get_issue_with_stacktraceB

Get issue metadata and latest event stacktrace in a single call.

Inputs: issue_id (required).

get_latest_eventB

Get the latest event for a Sentry issue.

Inputs: issue_id (required).

get_stack_framesA

Extract and format stack frames from a Sentry event. Useful for quickly seeing the call chain without full event details.

Inputs: event_id (required), project_slug (required), in_app_only.

list_issuesB

List Sentry issues with optional filters. Supports search queries like "is:unresolved", "level:error", etc.

Inputs: limit, query, project_slug.

list_projectsA

List all Sentry projects in the organization.

Inputs: no named parameters.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.7/5.0

    Scored across 7 tools

    Disambiguation4/5

    Most tools have distinct purposes: list vs. get, issue vs. event vs. stacktrace. Some minor overlap exists between get_event and get_stack_frames, as both return stacktrace data, but they are differentiated by level of detail and formatting.

    Naming Consistency5/5

    All tool names follow a consistent verb_noun pattern using snake_case. The 'get_' and 'list_' prefixes clearly indicate action type, and resource names are used uniformly across the set.

    Tool Count5/5

    With 7 tools, the server is well-scoped for a read-only Sentry debugging workflow. Each tool provides a meaningful view into issues and events without unnecessary bloat or redundancy.

    Completeness3/5

    The tool surface covers exploration and retrieval well, including issues, events, stacktraces, and projects. However, it lacks any mutating operations (e.g., updating issue status, resolving issues) and has no way to list all events for an issue, which could create dead ends in a complete debugging workflow.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      B
      quality
      D
      maintenance
      A Model Context Protocol server that retrieves and analyzes Sentry.io issues, allowing users to inspect error reports, stacktraces, and debugging information from their Sentry account.
      2
      23
      -
    • A
      license
      B
      quality
      F
      maintenance
      A Model Context Protocol server that enables AI assistants to interact with Sentry for error tracking and monitoring, allowing retrieval and analysis of error data, project management, and performance monitoring through the Sentry API.
      11
      21
      ISC
    • F
      license
      Not graded
      quality
      D
      maintenance
      An MCP server that connects to Sentry.io or self-hosted Sentry instances to retrieve and analyze error reports, stack traces, and debugging information.
      3
      -
    • A
      license
      B
      quality
      D
      maintenance
      A Model Context Protocol server that lets AI assistants interact with the Sentry API to retrieve and analyze error data, manage projects, and monitor application performance.
      11
      12
      ISC