sentry-mcp-rs
About
A fast, lightweight MCP server for Sentry, written in Rust.
Details
- Author
- utapyngo
- Categories
- Cloud Service, Infrastructure
Jump to
Setup
Install sentry-mcp-rs in your MCP client (Claude Desktop, Cursor, Windsurf, and others).
Repository: https://github.com/utapyngo/sentry-mcp-rs
Follow the installation instructions in the repository README, then restart your MCP client.
A fast, lightweightMCPserver for Sentry, written in Rust.
Compared to theofficial 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
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
cargo install --git https://github.com/utapyngo/sentry-mcp-rs.git
mise use -g github:utapyngo/sentry-mcp-rs
The binary will be installed assentry-mcp.
- SENTRY_AUTH_TOKEN- Your Sentry API authentication token
- SENTRY_HOST- Your Sentry instance hostname (e.g.,sentry.io)
- SOCKS_PROXY- SOCKS5 proxy URL (e.g.,socks5://127.0.0.1:1080)
- HTTPS_PROXY- HTTPS proxy URL
{ "mcpServers": { "sentry": { "command": "sentry-mcp", "env": { "SENTRY_AUTH_TOKEN": "your_token_here", "SENTRY_HOST": "sentry.io" } } } }
{ "mcpServers": { "sentry": { "command": "mise", "args": ["x", "github:utapyngo/sentry-mcp-rs", "--", "sentry-mcp"], "env": { "SENTRY_AUTH_TOKEN": "your_token_here", "SENTRY_HOST": "sentry.io" } } } }
Clone the repository and create a.envfile:
git clone https://github.com/utapyngo/sentry-mcp-rs.git cd sentry-mcp-rs cp .env.example .env # Edit .env with your credentials
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" } } }
Retrieve detailed information about a specific Sentry issue.
- 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)
Retrieve trace details for distributed tracing analysis.
- organization_slug- Organization slug
- trace_id- 32-character hex trace ID
Search events within an issue using Sentry's query syntax.
- organization_slug- Organization slug
- issue_id- Issue ID (e.g.,PROJECT-123)
- query- Optional Sentry search query
- limit- Maximum events to return (default: 10, max: 100)
- sort- Sort order:newest(default) oroldest
Navigate your Aiven projects and interact with the PostgreSQL®, Apache Kafka®, ClickHouse® and OpenSearch® services
Yunxiao MCP Server provides AI assistants with the ability to interact with the Yunxiao platform.
Get prescriptive CDK advice, explain CDK Nag rules, check suppressions, generate Bedrock Agent schemas, and discover AWS Solutions Constructs patterns.
This AWS Labs Model Context Protocol (MCP) server for CloudTrail enables your AI agents to query AWS account activity for security investigations, compliance auditing, and operational troubleshooting.
Core AWS MCP server providing prompt understanding and server management capabilities.
Analyze CDK projects to identify AWS services used and get pricing information from AWS pricing webpages and API.
Query and analyze your Axiom logs, traces, and all other event data in natural language
Manage and interact with Microsoft Azure services.
Bastion: External Attack Surface Monitoring
Ask your AI assistant about your attack surface: run scans, catch expiring certificates and domains, triage findings, and generate reports.
Agent-ready global image CDN that AI agents can install and operate through MCP.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.

