What are the prerequisites?
You need Claude Desktop (a free account is sufficient).
@agardnerIT
基本信息
暂无概览
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"logreader": {
"command": "uv",
"args": [
"--directory",
"/full/path/claude-mcp-server-observability",
"run",
"logreader.py"
]
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
A demo MCP server that provides observability capabilities by reading application logs, enabling Claude Desktop to investigate errors and suggest remediation. It is intended for developers using Claude Desktop who want to experiment with log‑driven debugging.
Clone the repo, install dependencies with pip install -r requirements.txt, start the server with python logreader.py, then configure Claude Desktop by editing its config JSON to point to the logreader server. Launch Claude, start a new chat, and ask a question like “I noticed errors in the logs on the 22nd March. Help me investigate.” Claude will use the three server‑provided tools to answer, possibly after asking for permission.
You need Claude Desktop (a free account is sufficient).
Clone the repo, run `pip install -r requirements.txt`, then execute `python logreader.py`.
Go to `Claude > Settings > Developer`, click `Edit config`, and set the JSON content to the sample provided in the README, using the full path to your cloned repo.
For example, “I noticed errors in the logs on the 22nd March. Help me investigate.” Claude will use the tools to read logs and produce findings.
Claude may identify the responsible pipeline and release and suggest contacting a specific person (e.g., “Pipeline C and the release was most likely responsible; you should contact Susan”).

Build and edit landing pages and websites from your AI assistant, and pull how they are performing.
MCP-native LLM councils for debates, juries, blind panels, voting, refinement, and custom multi-model deliberation.
Open-source Node.js FHIR MCP server with SMART Backend Services, metadata-aware search/CRUD tools, compact responses, FHIRPath filtering, safe pagination, audit events, and terminology lookup.
FACTANKER serves 1.18B+ evidence-backed facts about US companies, banks, nonprofits and federal spending, sourced from SEC EDGAR, FFIEC call reports, IRS 990 filings and USAspending. Every value carries its evidence: fil
Detect and redact PII, PHI, PCI and secrets — SSNs, credit cards, passports, API keys and cloud credentials — in text and in local files, using the Strac DLP API. Five tools: redact_text, detect_sensitive_data, detect_fi
评论