About sentry-selfhosted-mcp
sentry-selfhosted-mcp connects MCP clients to self-hosted Sentry instances. It supports issue and event lookups, project listing, status changes, and issue comments.
Key features
- 01Retrieve issue details by ID or URL
- 02List organization projects
- 03Filter issues by project, query, or status
- 04Retrieve event details
- 05Change issue status and add comments
Use cases
- 01Inspect an issue in a self-hosted Sentry instance
- 02Review project issues by status or query
- 03Resolve or ignore an issue and add a comment
MCP support
Exposes tools for querying projects, issues, and events and for updating issue status or comments. It reads the Sentry URL, authentication token, and organization slug from environment variables.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEsentry-selfhosted-mcp
A Model Context Protocol (MCP) server designed specifically for interacting with self-hosted Sentry instances.
Overview
This server provides tools to retrieve information and perform actions on issues within a self-hosted Sentry setup. It reads the Sentry instance URL, authentication token, and organization slug from environment variables.
Available Tools
The following tools are available:
-
get_sentry_issue- Description: Retrieve details for a specific Sentry issue by ID or URL.
- Input:
{ "issue_id_or_url": "string" }(e.g., "12345" or "https://sentry.example.com/organizations/org/issues/12345/")
-
list_sentry_projects- Description: List all projects within the configured Sentry organization.
- Input:
{}(No arguments needed)
-
list_sentry_issues- Description: List issues for a specific project, optionally filtering by query or status.
- Input:
{ "project_slug": "string", "query": "string" (optional), "status": "resolved" | "unresolved" | "ignored" (optional) }
-
get_sentry_event_details- Description: Retrieve details for a specific event ID within a project.
- Input:
{ "project_slug": "string", "event_id": "string" }
-
update_sentry_issue_status- Description: Update the status of a Sentry issue.
- Input:
{ "issue_id": "string", "status": "resolved" | "ignored" | "unresolved" }
-
create_sentry_issue_comment- Description: Add a comment to a Sentry issue.
- Input:
{ "issue_id": "string", "comment_text": "string" }
Installation & Setup
- Clone/Place Project: Clone this repository or place the project files in your desired location.
- Install Dependencies: Navigate into the project directory (
sentry-selfhosted-mcp) and run:cd <path/to/sentry-selfhosted-mcp> npm install - Build Server: Compile the TypeScript code from the project directory:
This creates the executable JavaScript file in thenpm run buildbuild/directory.
Configuration
This server requires the following environment variables to be set:
SENTRY_URL: The base URL of your self-hosted Sentry instance (e.g.,https://sentry.beoflow.app).SENTRY_AUTH_TOKEN: Your Sentry API authentication token (ensure it has necessary scopes likeissue:read,project:read,event:read,issue:write,comment:write).SENTRY_ORG_SLUG: The slug of your Sentry organization (e.g.,beoflow).
Example MCP Client Configuration:
Add the following entry to your MCP client's configuration file (e.g., cline_mcp_settings.json for the VS Code extension, claude_desktop_config.json for Claude.app):
"sentry-selfhosted-mcp": {
"command": "node",
"args": [
"<full/path/to/sentry-selfhosted-mcp/build/index.js>"
],
"env": {
"SENTRY_URL": "YOUR_SENTRY_URL",
"SENTRY_AUTH_TOKEN": "YOUR_SENTRY_AUTH_TOKEN",
"SENTRY_ORG_SLUG": "YOUR_SENTRY_ORG_SLUG"
},
"disabled": false,
"autoApprove": [],
"transportType": "stdio"
}
Replace YOUR_SENTRY_URL, YOUR_SENTRY_AUTH_TOKEN, and YOUR_SENTRY_ORG_SLUG with your actual values.
After updating the settings file, the MCP client should automatically connect to the server.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.