mcpField
I
Incident Library

Incident Library

Remote
benchlet.comSearch0Updated 2d ago

About Incident Library

Incident Library is a searchable collection of public post-incident reports, organized as structured cases that can be found by symptom and linked to their sources. Its cases, categories, and API answers use CC BY 4.0; this repository accepts case proposals and corrections.

Key features

  1. 01Search cases by symptom
  2. 02Structure public incident reports
  3. 03Link to original reports
  4. 04Accept case proposals and corrections
  5. 05Publish case text and API answers under CC BY 4.0

Use cases

  1. 01Find cases related to an incident symptom
  2. 02Trace a case to its source report
  3. 03Propose a public incident report for inclusion
  4. 04Report factual or category errors

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://incidentlib-mcp.benchlet.com/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

Incident Library: reports and corrections

Incident Library MCP connector – tool definition quality and endpoint health on Glama

This repository takes two kinds of issues for Incident Library, the searchable collection of public post-incident reports.

  • Propose a case. A public post-incident report (a postmortem page, an engineering blog post, a status page incident, a talk or a runbook entry) that the library should write up. Use the Case proposal issue form.
  • Report a mistake. A fact in a case that does not match its source, a broken link, or a wrong category. Use the Correction issue form.

The library's code and data are not in this repository. Cases are written up by hand from the report you point at, in English and Korean, and published with a link to the original. Every issue gets an answer here when the case is published or the correction is made.

The case texts, the category list and the API answers are available under CC BY 4.0; the original reports keep their own licences.


Incident Library: 제보와 정정

Incident Library 에 보내는 이슈 두 종류를 받는 저장소입니다. Incident Library 는 공개된 장애 보고서를 사례 하나하나로 구조화해 증상으로 찾는 검색 서비스입니다.

  • 사례 제안. 라이브러리에 넣을 만한 공개 장애 보고서(포스트모템 페이지, 기술 블로그 글, 상태 페이지의 사고 기록, 발표, 런북 항목)를 알려 주세요. Case proposal 이슈 양식을 씁니다.
  • 오류 신고. 사례의 내용이 출처와 다르거나, 링크가 깨졌거나, 분류가 틀렸을 때 알려 주세요. Correction 이슈 양식을 씁니다.

서비스의 코드와 데이터는 이 저장소에 없습니다. 사례는 알려 주신 보고서를 읽고 사람이 영어와 한국어로 써서 원문 링크와 함께 공개합니다. 사례가 공개되거나 정정이 반영되면 이슈에 답을 남깁니다.

사례 글, 분류 목록, API 응답은 CC BY 4.0 이고, 원문 보고서는 각자의 라이선스를 따릅니다.

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.