MCP App StoreMCP App Store
from opendatalab
Run, validate, and parse OmniDocBench document parsing evaluations with Docker/conda workflows and result parsing.
python pdf_validation.py --config ... inside recommended Docker image ghcr.io/zeng-weijun/omnidocbench-eval:repro-ubuntu2204.\n- Parse and summarize *_metric_result.json, *_run_summary.json, *_stage_execution.json, and *_runtime_environment.json.\n- Troubleshooting: Docker access, CDM OOMs, ImageMagick policy issues, GT capitalization, and prediction folder nesting.\n\n## Recommended prompts / usage\n- "How do I run OmniDocBench end2end evaluation on my GT JSON and markdown predictions?"\n- "Help me parse an OmniDocBench result directory and extract overall/text/formula/table scores."\n- "I get CDM OOMs — how should I set cdm_workers on a 4CPU/8GB node?"\n\n## Installation / scripts\nThe skill bundles scripts: scripts/generate_end2end_config.py and scripts/parse_results.py for config generation and result parsing. Follow Docker workflow in the skill to avoid local dependency issues.\nA well-documented skill for running OmniDocBench document parsing evaluations via Docker or conda. The SKILL.md is thorough with input validation, Docker/SSH workflows, config guidance, and a detailed troubleshooting playbook. No bundled scripts to test. Security posture is strong: read-only mounts for inputs, no destructive commands, no credentials, non-interactive sudo only as fallback. The main limitation is narrow audience — only useful to researchers evaluating document parsing models on OmniDocBench.
No scripts to run. Security deductions: -3 for shell variable interpolation in heredoc/Docker commands (minor injection risk if user paths contain special characters, though paths are quoted in validation), -2 for sudo -n fallback pattern. Quality is high but no idempotent scripts to verify. Architecture is good — clear sections, progressive disclosure, result parsing guidance — but no scripts/ or references/ directories. Usefulness is niche: only researchers running OmniDocBench evaluations would use this.
Sync Production Database to Development
Run a safe, scripted workflow to download production database dumps and restore them into a development environment (download-only and restore options).
Cross-Project Analytics
Query local, privacy-safe cross-project analytics to report on agent, skill, hook, and team performance; replay sessions and estimate token costs.
Docker Compose Generator
Generate and validate Docker Compose files for multi-container apps with templates, best-practice guidance, and deployment/runbook outputs.
Code Audit
Perform professional code security audits across 9 languages with configurable quick/standard/deep modes and Docker-backed verification.
MetricFlow: Interactive Metric Definition
Interactively define MetricFlow metrics from natural-language business descriptions; proposes, validates, and dry-runs metric YAML for semantic modeling.
Harness Health Audit
Assess and score the overall health of a Claude Code harness across architecture, skills coverage, hooks, rules, MCP servers, eval pipelines, and team setup.
LLM Evaluation
Evaluation framework and tools for systematically measuring LLM performance using automated metrics, human judgment, and A/B testing.
OpenTelemetry Skill — Observability Engineering Assistant
Expert OpenTelemetry observability skill for designing collectors, pipelines, sampling, cardinality management, security, and production-ready deployment patter