sentry-mcp-rs
A fast, lightweight MCP server for Sentry, written in Rust.
sentry-mcp
A fast, lightweight MCP server for Sentry, written in Rust.
Why sentry-mcp?
Compared to the official Node.js server:
- Memory: 10x less RAM usage
- Startup: instant cold start
- Disk: single binary, no runtime dependencies
- Tokens: fewer tools = smaller tool list in context
Features
This MCP server provides tools to interact with Sentry's API:
- get_issue_details - Retrieve detailed information about a Sentry issue including metadata, tags, stacktraces, and optionally a specific event
- get_trace_details - Retrieve trace details including span tree and timing information for distributed tracing analysis
- search_issue_events - Search events within an issue using Sentry's query syntax
Installation
From crates.io:
cargo install sentry-mcp
From GitHub:
cargo install --git https://github.com/utapyngo/sentry-mcp-rs.git
Or with mise:
mise use -g github:utapyngo/sentry-mcp-rs
The binary will be installed as sentry-mcp.
Configuration
Required environment variables:
SENTRY_AUTH_TOKEN- Your Sentry API authentication tokenSENTRY_HOST- Your Sentry instance hostname (e.g.,sentry.io)
Optional:
SOCKS_PROXY- SOCKS5 proxy URL (e.g.,socks5://127.0.0.1:1080)HTTPS_PROXY- HTTPS proxy URL
MCP Client Configuration
Add to your MCP client configuration:
{
"mcpServers": {
"sentry": {
"command": "sentry-mcp",
"env": {
"SENTRY_AUTH_TOKEN": "your_token_here",
"SENTRY_HOST": "sentry.io"
}
}
}
}
Or without installation using mise:
{
"mcpServers": {
"sentry": {
"command": "mise",
"args": ["x", "github:utapyngo/sentry-mcp-rs", "--", "sentry-mcp"],
"env": {
"SENTRY_AUTH_TOKEN": "your_token_here",
"SENTRY_HOST": "sentry.io"
}
}
}
}
Development
Clone the repository and create a .env file:
git clone https://github.com/utapyngo/sentry-mcp-rs.git
cd sentry-mcp-rs
cp .env.example .env
# Edit .env with your credentials
Build and test with MCP Inspector:
cargo build --release
npx @modelcontextprotocol/inspector ./run.sh
Or configure MCP client to use the script:
{
"mcpServers": {
"sentry": {
"command": "/path/to/sentry-mcp-rs/run.sh"
}
}
}
Tools
get_issue_details
Retrieve detailed information about a specific Sentry issue.
Parameters:
issue_url- Full Sentry issue URL (alternative to the parameters below)organization_slug- Organization slug (required ifissue_urlnot provided)issue_id- Issue ID likePROJECT-123or numeric ID (required ifissue_urlnot provided)event_id- Specific event ID to fetch instead of latest (optional)
get_trace_details
Retrieve trace details for distributed tracing analysis.
Parameters:
organization_slug- Organization slugtrace_id- 32-character hex trace ID
search_issue_events
Search events within an issue using Sentry's query syntax.
Parameters:
organization_slug- Organization slugissue_id- Issue ID (e.g.,PROJECT-123)query- Optional Sentry search querylimit- Maximum events to return (default: 10, max: 100)sort- Sort order:newest(default) oroldest
Похожие серверы
Maersk Vessel Deadlines
Access Maersk vessel schedules and shipment deadlines programmatically via the Maersk API.
Knowi
Query databases, build dashboards, and analyze documents in natural language from Claude or any MCP client. 28+ tools, 70+ data sources.
Authorize.Net by CData
A read-only MCP server by CData for querying live Authorize.Net data.
Pangea MCP proxy
Protect any MCP server from malicious entities and confidential PII using Pangea's AI Guard and Vault.
qURL
qURL is the portal to the invisible internet -- expiring, scope-limited URLs that let AI agents reach services no one else can see
Cloudflare Remote MCP Server (Authless)
An example for deploying a remote, authentication-free MCP server on Cloudflare Workers.
Prometheus
Interact with your Prometheus monitoring infrastructure using natural language.
CData Sage Cloud Accounting
A read-only MCP server for Sage Cloud Accounting, powered by the CData JDBC Driver.
Plesk
Manage your Plesk hosting server using AI assistants.
TagoIO
Interact with your TagoIO account to access devices, data, and platform resources for development and intelligent data analysis.