mcpField
S
sentry-issues-mcp

sentry-issues-mcp

Local
github.com/Leee62Developer Tools5Updated 74w ago

About sentry-issues-mcp

sentry-issues-mcp provides tools for querying Sentry events, for developers who want an LLM to analyze event details or project event lists. Results can be returned in compact or full mode.

Key features

  1. 01Get event details by URL or ID
  2. 02List events by project
  3. 03Choose compact or full data

Use cases

  1. 01Analyze an individual Sentry event
  2. 02Find recent project events
  3. 03Inspect event stack information

MCP support

This MCP server exposes get_single_event and get_project_events for MCP clients to query Sentry event details and lists. The README notes that issue retrieval has been deprecated since version 1.0.5.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"sentry-issues": {
"command": "npx",
"args": [
"-y",
"sentry-issues-mcp"
],
"env": {
"SENTRY_HOST": "<SENTRY_HOST>",
"SENTRY_ORG": "<SENTRY_ORG>",
"SENTRY_PROJ": "<SENTRY_PROJ>",
"SENTRY_USER_TOKEN": "<SENTRY_USER_TOKEN>"
}
}
}
}
Run commandnpx -y sentry-issues-mcp
Environment variables to set
SENTRY_HOST
SENTRY_ORG
SENTRY_PROJ
SENTRY_USER_TOKENSecret

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmsentry-issues-mcp

Tools

2

Saved tool list · updated 3w ago

ParameterTypeRequiredDescription
url_or_idstringYessentry issue event url or sentry issue event id
organization_id_or_slugstringNosentry organization id or slug, it can be undefined
project_id_or_slugstringNosentry project name or slug, it can be undefined
modeenumNomode for output, it can be undefined, it used to control LLM token usagetiny | huge

Details

From the project README

sentry-issue-mcp

中文文档 English smithery badge

Description

⚠️ Getting issues is deprecated as of version 1.0.5. The response structure is so similar to the event API that it's considered redundant.

This is a mcp for sentry issue.
It supports 2 tools to get a issue or list of issues.
U can let LLM analysis the Res, or u want to do.

Feature

  • EZ size
  • EZ understand
  • EZ tiny

Tools

  • get_single_event
    • get a event detail infos, tiny mode return stack info, huge mode return all info
    • inputs:
      • url_or_id: sentry event url or sentry event id
      • organization_id_or_slug: sentry organization id or slug, it can be undefined
      • project_id_or_slug: sentry project id or slug, it can be undefined
      • mode: tiny or huge, it can be undefined
  • get_project_events
    • get list of events, tiny mode return id and title, huge mode return all info
    • inputs:
      • project_id_or_slug: sentry project id or slug
      • organization_id_or_slug: sentry organization id or slug, it can be undefined
      • mode: tiny or huge, it can be undefined

QuickStart

this is MCP Server Config

  "mcpServers": {
    "sentry-issue-mcp": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "sentry-issues-mcp@latest"
      ],
      "env": {
        "SENTRY_HOST": "<your_sentry_host>",
        "SENTRY_ORG": "<your_sentry_org>",
        "SENTRY_PROJ": "<your_sentry_proj>",
        "SENTRY_USER_TOKEN": "<your_sentry_user_token>"
      }
    }
  }

Case

  • Ask LLM to analysis one issue by url or id
    1. input "analysis the issue, and give me the reason of it, and tell me how to fix it, {sentry_issue_url}"
    2. if ur LLM is SMART🧠, it will call tools
    3. u will get result
  • Ask LLM to find Today most dangerous issue (PS: default val of sentry time period is "24h")
    1. input "find today most dangerous issue, and give me the reason of it, and tell me how to fix it"
    2. if ur LLM is SMART🧠, it will call tools
    3. u will get result

License

MIT

Comments

Markdown supported

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.