Provides tools to retrieve and analyze issues from Sentry.io or self-hosted Sentry instances, allowing inspection of error reports, stack traces, and debugging information. Supports fetching individual issues by ID or URL as well as listing issues for specific projects.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Sentry MCP Serverget issue details for error ID 1234567890"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
English 中文
Below is a revised and polished version of the README.md for the mcp-sentry-custom project, formatted properly for clarity, correctness, and professionalism. It adheres to standard Markdown conventions and organizes the content into logical sections.
mcp-sentry-custom: A Sentry MCP Server
Overview
mcp-sentry-custom is a Model Context Protocol (MCP) server designed to retrieve and analyze issues from Sentry.io or self-hosted Sentry instances. This server provides tools to inspect error reports, stack traces, and other debugging information directly from your Sentry account.
Related MCP server: Sentry MCP Server
Features
Tools
get_sentry_issueDescription: Retrieve and analyze a specific Sentry issue by its ID or URL.
Input:
issue_id_or_url(string): The Sentry issue ID or full URL to analyze.
Returns: Detailed issue information, including:
Title
Issue ID
Status
Level
First seen timestamp
Last seen timestamp
Event count
Full stack trace
get_list_issuesDescription: Retrieve and analyze a list of Sentry issues for a specific project.
Input:
project_slug(string): The Sentry project slug.organization_slug(string): The Sentry organization slug.
Returns: A list of issues with details, including:
Title
Issue ID
Status
Level
First seen timestamp
Last seen timestamp
Event count
Basic issue information
Prompts
sentry-issueDescription: Retrieve formatted issue details from Sentry for use in conversation context.
Input:
issue_id_or_url(string): The Sentry issue ID or URL.
Returns: Formatted issue details.
Installation
Installing via Smithery
To install mcp-sentry-custom for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @javaDer/mcp-sentry-custom --client claudeUsing uv (Recommended)
When using uv, no specific installation is required. You can run mcp-sentry-custom directly with uvx:
uvx mcp-sentry-custom --auth-token YOUR_SENTRY_TOKEN --project-slug YOUR_PROJECT_SLUG --organization-slug YOUR_ORGANIZATION_SLUG --sentry-url YOUR_SENTRY_URLUsing pip
Alternatively, install mcp-sentry-custom via pip:
pip install mcp-sentry-customOr, with uv:
uv pip install -e .After installation, run it as a script:
python -m mcp_sentryConfiguration
Usage with Claude Desktop
Add the following to your claude_desktop_config.json:
Using uvx
{
"mcpServers": {
"sentry": {
"command": "uvx",
"args": [
"mcp-sentry-custom",
"--auth-token", "YOUR_SENTRY_TOKEN",
"--project-slug", "YOUR_PROJECT_SLUG",
"--organization-slug", "YOUR_ORGANIZATION_SLUG",
"--sentry-url", "YOUR_SENTRY_URL"
]
}
}
}Using Docker
{
"mcpServers": {
"sentry": {
"command": "docker",
"args": [
"run", "-i", "--rm",
"mcp/sentry",
"--auth-token", "YOUR_SENTRY_TOKEN",
"--project-slug", "YOUR_PROJECT_SLUG",
"--organization-slug", "YOUR_ORGANIZATION_SLUG",
"--sentry-url", "YOUR_SENTRY_URL"
]
}
}
}Using pip Installation
{
"mcpServers": {
"sentry": {
"command": "python",
"args": [
"-m", "mcp_sentry",
"--auth-token", "YOUR_SENTRY_TOKEN",
"--project-slug", "YOUR_PROJECT_SLUG",
"--organization-slug", "YOUR_ORGANIZATION_SLUG",
"--sentry-url", "YOUR_SENTRY_URL"
]
}
}
}Usage with Zed
Add the following to your settings.json in Zed:
Using uvx
{
"context_servers": {
"mcp-sentry-custom": {
"command": {
"path": "uvx",
"args": [
"mcp-sentry-custom",
"--auth-token", "YOUR_SENTRY_TOKEN",
"--project-slug", "YOUR_PROJECT_SLUG",
"--organization-slug", "YOUR_ORGANIZATION_SLUG",
"--sentry-url", "YOUR_SENTRY_URL"
]
}
}
}
}Using pip Installation
{
"context_servers": {
"mcp-sentry-custom": {
"command": "python",
"args": [
"-m", "mcp_sentry",
"--auth-token", "YOUR_SENTRY_TOKEN",
"--project-slug", "YOUR_PROJECT_SLUG",
"--organization-slug", "YOUR_ORGANIZATION_SLUG",
"--sentry-url", "YOUR_SENTRY_URL"
]
}
}
}Using pip Installation with Custom Path
{
"context_servers": {
"mcp-sentry-custom": {
"command": "python",
"args": [
"-m", "mcp_sentry",
"--auth-token", "YOUR_SENTRY_TOKEN",
"--project-slug", "YOUR_PROJECT_SLUG",
"--organization-slug", "YOUR_ORGANIZATION_SLUG",
"--sentry-url", "YOUR_SENTRY_URL"
],
"env": {
"PYTHONPATH": "path/to/mcp-sentry-custom/src"
}
}
}
}Debugging
Use the MCP inspector to debug the server.
For uvx Installations
npx @modelcontextprotocol/inspector uvx mcp-sentry-custom --auth-token YOUR_SENTRY_TOKEN --project-slug YOUR_PROJECT_SLUG --organization-slug YOUR_ORGANIZATION_SLUG --sentry-url YOUR_SENTRY_URLFor Local Development
If you've installed the package in a specific directory or are developing it:
cd path/to/mcp-sentry-custom/src
npx @modelcontextprotocol/inspector uv run mcp-sentry-custom --auth-token YOUR_SENTRY_TOKEN --project-slug YOUR_PROJECT_SLUG --organization-slug YOUR_ORGANIZATION_SLUG --sentry-url YOUR_SENTRY_URLOr, with a custom directory:
npx @modelcontextprotocol/inspector uv --directory /path/to/mcp-sentry-custom/src run mcp_sentry --auth-token YOUR_SENTRY_TOKEN --project-slug YOUR_PROJECT_SLUG --organization-slug YOUR_ORGANIZATION_SLUG --sentry-url YOUR_SENTRY_URLForked From
This project is forked from:
https://github.com/modelcontextprotocol/servers/tree/main/src/sentry
License
This MCP server is licensed under the MIT License. You are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, see the LICENSE file in the project repository.
Notes on Changes
Formatting: Used proper Markdown headings, lists, and code blocks for readability.
Consistency: Standardized terminology (e.g.,
mcp_sentryvs.mcp-sentry-custom) and removed redundant<TEXT>and<JSON>tags.Clarity: Rewrote sections like "Overview" and "Features" for conciseness and precision.
Completeness: Fixed incomplete sentences and ensured all configuration examples were properly structured.
Professional Tone: Adjusted wording to sound more formal and polished.
Let me know if you'd like further refinements!