Spark
Sign In
MCP Connector

Integrate Sentry for Error Monitoring

An MCP server for retrieving and analyzing Sentry.io issues, returning full stacktraces and error details by issue ID or URL.

Get from source
Works with sentry
VibeBaza
Own this? Claim it
87
Spark score
out of 100
Updated May 2025
Fresher alternatives ↓
Source checked Sep 15, 2026
Version 1.0.0
Models
universal
Add to Favorites

Why it matters

Connect your AI to Sentry.io to automatically view, analyze, and debug application errors. Streamline your DevOps workflow by gaining immediate insights into issues and their root causes.

Outcomes

What it gets done

01

List and retrieve details of Sentry issues.

02

Analyze error stack traces and event breadcrumbs.

03

Resolve issues directly through AI commands.

04

Monitor application health and error patterns.

Source

Get it from source

Spark does not host a copy of it.

Open source

Reports

Agent outcome reports

No reports yet

Capabilities

Tools your agent gets

list_organizations

List all organizations you have access to.

list_projects

List projects in an organization.

list_issues

List issues for a project with optional query filtering.

get_issue

Get detailed information about a specific issue.

get_issue_events

Get events associated with an issue.

resolve_issue

Resolve an issue in Sentry.

Overview

Sentry MCP

An MCP server that retrieves and analyzes Sentry.io issues, returning title, status, timestamps, event count, and full stacktrace for a given issue ID or URL. Use it when Claude needs to pull a real Sentry issue's details into a debugging conversation; it is read-only and does not modify Sentry data.

What it does

This MCP server retrieves and analyzes issues from Sentry.io, giving an MCP client tools to inspect error reports, stacktraces, and other debugging information straight from a Sentry account. Its single tool, get_sentry_issue, takes an issue_id_or_url string (either the Sentry issue ID or its URL) and returns the issue's title, ID, status, level, first-seen and last-seen timestamps, event count, and full stacktrace. A matching prompt, sentry-issue, takes the same issue_id_or_url input and returns the formatted issue details as conversation context, so the details flow directly into the chat rather than requiring a separate tool call.

When to use - and when NOT to

Use it when you want to hand Claude (or another MCP client) a Sentry issue ID or link and have it pull the real error details and stacktrace into context for debugging or triage, instead of copy-pasting from the Sentry UI. It is a read/retrieval tool only - it inspects existing issues, it does not create, resolve, assign, or otherwise modify anything in Sentry.

Capabilities

The server can be debugged directly through the MCP inspector: npx @modelcontextprotocol/inspector uvx mcp-server-sentry --auth-token YOUR_SENTRY_TOKEN for a uvx install, or the same inspector run against a local checkout with uv run mcp-server-sentry --auth-token YOUR_SENTRY_TOKEN from the server's source directory. Configuration is supported across multiple clients - Claude Desktop, VS Code (with one-click install buttons plus manual settings.json or a shareable .vscode/mcp.json), and Zed - each accepting either a uvx, Docker, or pip-installed launch command with a Sentry auth token passed as --auth-token or the SENTRY_AUTH_TOKEN environment variable.

How to install

With uv/uvx, no separate installation step is needed - uvx mcp-server-sentry runs it directly. Alternatively, install via pip and run it as a module:

pip install mcp-server-sentry
python -m mcp_server_sentry

A Docker image is also available (mcp/sentry), runnable with docker run -i --rm mcp/sentry --auth-token YOUR_SENTRY_TOKEN. Whichever method you use, point your MCP client's config at the resulting command and pass your Sentry auth token as an argument or environment variable.

Who it's for

Developers and on-call engineers who want an MCP client to pull real Sentry error details and stacktraces into a debugging conversation by issue ID or URL, without leaving the chat to look them up manually. Because the returned prompt formats the issue as conversation context rather than raw JSON, it fits naturally into an incident-triage or bug-fixing session where the model needs the actual stacktrace, not just a summary of it. Licensed under the MIT License, so it can be freely used, modified, and redistributed subject to that license's terms.

Source README

mcp-server-sentry: A Sentry MCP server

Overview

A Model Context Protocol server for retrieving and analyzing issues from Sentry.io. This server provides tools to inspect error reports, stacktraces, and other debugging information from your Sentry account.

Tools

  1. get_sentry_issue
    • Retrieve and analyze a Sentry issue by ID or URL
    • Input:
      • issue_id_or_url (string): Sentry issue ID or URL to analyze
    • Returns: Issue details including:
      • Title
      • Issue ID
      • Status
      • Level
      • First seen timestamp
      • Last seen timestamp
      • Event count
      • Full stacktrace

Prompts

  1. sentry-issue
    • Retrieve issue details from Sentry
    • Input:
      • issue_id_or_url (string): Sentry issue ID or URL
    • Returns: Formatted issue details as conversation context

Installation

Using uv (recommended)

When using uv no specific installation is needed. We will
use uvx to directly run mcp-server-sentry.

Using PIP

Alternatively you can install mcp-server-sentry via pip:

pip install mcp-server-sentry

After installation, you can run it as a script using:

python -m mcp_server_sentry

Configuration

Usage with Claude Desktop

Add this to your claude_desktop_config.json:

Using uvx 
"mcpServers": {
  "sentry": {
    "command": "uvx",
    "args": ["mcp-server-sentry", "--auth-token", "YOUR_SENTRY_TOKEN"]
  }
}
Using docker 
"mcpServers": {
  "sentry": {
    "command": "docker",
    "args": ["run", "-i", "--rm", "mcp/sentry", "--auth-token", "YOUR_SENTRY_TOKEN"]
  }
}
Using pip installation 
"mcpServers": {
  "sentry": {
    "command": "python",
    "args": ["-m", "mcp_server_sentry", "--auth-token", "YOUR_SENTRY_TOKEN"]
  }
}

Usage with VS Code

For quick installation, use one of the one-click installation buttons below...

Install with UV in VS Code Install with UV in VS Code Insiders

Install with Docker in VS Code Install with Docker in VS Code Insiders

For manual installation, add the following JSON block to your User Settings (JSON) file in VS Code. You can do this by pressing Ctrl + Shift + P and typing Preferences: Open Settings (JSON).

Optionally, you can add it to a file called .vscode/mcp.json in your workspace. This will allow you to share the configuration with others.

Note that the mcp key is needed when using the mcp.json file.

Using uvx 
{
  "mcp": {
    "inputs": [
      {
        "type": "promptString",
        "id": "auth_token",
        "description": "Sentry Auth Token",
        "password": true
      }
    ],
    "servers": {
      "sentry": {
        "command": "uvx",
        "args": ["mcp-server-sentry"],
        "env": {
          "SENTRY_AUTH_TOKEN": "${input:auth_token}"
        }
      }
    }
  }
}
Using docker 
{
  "mcp": {
    "inputs": [
      {
        "type": "promptString",
        "id": "auth_token",
        "description": "Sentry Auth Token",
        "password": true
      }
    ],
    "servers": {
      "sentry": {
        "command": "docker",
        "args": ["run", "-i", "--rm", "mcp/sentry"],
        "env": {
          "SENTRY_AUTH_TOKEN": "${input:auth_token}"
        }
      }
    }
  }
}

Usage with Zed

Add to your Zed settings.json:

Using uvx 
"context_servers": [
  "mcp-server-sentry": {
    "command": {
      "path": "uvx",
      "args": ["mcp-server-sentry", "--auth-token", "YOUR_SENTRY_TOKEN"]
    }
  }
],
Using pip installation 
"context_servers": {
  "mcp-server-sentry": {
    "command": "python",
    "args": ["-m", "mcp_server_sentry", "--auth-token", "YOUR_SENTRY_TOKEN"]
  }
},

Debugging

You can use the MCP inspector to debug the server. For uvx installations:

npx @modelcontextprotocol/inspector uvx mcp-server-sentry --auth-token YOUR_SENTRY_TOKEN

Or if you've installed the package in a specific directory or are developing on it:

cd path/to/servers/src/sentry
npx @modelcontextprotocol/inspector uv run mcp-server-sentry --auth-token YOUR_SENTRY_TOKEN

FAQ

Common questions

Discussion

Questions & comments · 0

Sign In Sign in to leave a comment.