ndjson-local-log-triage-mcp
Streams NDJSON log triage without loading gigabyte files into context
🪵 ndjson-local-log-triage-mcp
Your service just crashed. The log file is 2GB. Your AI agent can't help.
MCP server that stream-parses NDJSON log files without loading them into memory — filter by pattern, detect error spikes via Z-score analysis, summarize severity timelines by time window.
🤔 The problem
A service crashes at 3am. The log file is app.log.ndjson and it's 2GB. You ask your agent to find what caused the spike in errors around 03:17. The agent can't read 2GB. It can't even try.
ndjson-local-log-triage-mcp streams the file line by line — never loading it into memory — and gives the agent exactly the slice it needs.
🛠️ Tools
query_log_pattern
Filter log entries by a field/value match. Returns up to N matching entries, streaming the file without loading it entirely.
Log Query Results
File: /var/log/app.log.ndjson
Filter: service contains "auth"
Lines read: 847,293
Matches: 50 (limit 50 reached)
{"timestamp":"2025-01-15T03:17:02Z","level":"error","service":"auth","msg":"token validation failed","userId":"u_abc123"}
...
detect_error_anomalies
Z-score frequency analysis. Buckets errors by time window, computes mean + stddev, flags windows where the error rate is anomalously high.
Error Anomaly Detection
File: /var/log/app.log.ndjson
Window: 5min
Z-score cutoff: 2.0
Baseline: mean=3.2 errors/window, stdDev=1.8
Anomalies found: 2
[z=4.71] 2025-01-15T03:15:00.000Z 23 errors
[z=2.33] 2025-01-15T03:20:00.000Z 9 errors
summarize_log_timeline
Chronological aggregation of errors, warnings, and info counts per time window. Quick visual of where the incident is.
Log Timeline Summary
File: /var/log/app.log.ndjson
Window: 5min
Buckets: 48
Time (UTC) Errors Warnings Info Other
─────────────────────────────────────────────────────────
2025-01-15 03:00:00Z 2 8 142 0
2025-01-15 03:05:00Z 1 5 138 0
2025-01-15 03:10:00Z 3 9 141 0
! 2025-01-15 03:15:00Z 23 14 119 0
2025-01-15 03:20:00Z 9 11 133 0
⚡ Setup
{
"mcpServers": {
"log-triage": {
"command": "npx",
"args": ["-y", "ndjson-local-log-triage-mcp"]
}
}
}
🚀 Usage
"Analyze /var/log/app.log.ndjson — summarize the error timeline in 5-minute windows, detect any anomalous spikes, and show me the error entries around the spike."
Works great alongside:
- release-readiness-triage-mcp — CI failure triage before release
- env-secret-exposure-analyzer-mcp — secret exposure scanning
📦 Links
- npm: npmjs.com/package/ndjson-local-log-triage-mcp
- GitHub: github.com/vola-trebla/ndjson-local-log-triage-mcp
License
MIT
相关服务器
Alpha Vantage MCP Server
赞助Access financial market data: realtime & historical stock, ETF, options, forex, crypto, commodities, fundamentals, technical indicators, & more
Databutton
An MCP server for initial app planning and creating a good starting point for an app.
Storybook MCP Server
Apify-hosted MCP server for Storybook. Browse components, inspect props, read stories, capture screenshots. Supports Storybook 6/7/8.
GPT Image 1
Generate high-quality AI images with OpenAI's GPT-Image-1 model and save them directly to your local machine.
click-to-mcp
Auto-wrap any Click/typer CLI as an MCP server. Introspects CLI commands at runtime and maps them to MCP tools.
MCP Servers
A collection of reference implementations for the Model Context Protocol (MCP), demonstrating how to give LLMs secure access to tools and data using Typescript and Python SDKs.
Code Context Provider MCP
Provides code context and analysis for AI assistants using WebAssembly Tree-sitter parsers.
Formo
Formo makes analytics and attribution easy for crypto apps, so you can focus on growth. Measure what matters and drive growth onchain with the data platform for onchain apps. Get the best of web, product, and onchain analytics on one versatile platform.
Keycloak MCP Server
An MCP server for Keycloak administration, offering over 30 tools to manage users, realms, clients, roles, and more from AI assistants.
Codacy
Access the Codacy API to analyze code quality, coverage, and security for your repositories.
better-code-review-graph
Knowledge graph for token-efficient code reviews with Tree-sitter parsing, dual-mode embedding (ONNX + LiteLLM), and blast-radius analysis via MCP tools.