Code

Through-the-upgrade dependency-migration briefs for LLM coding agents.

Tells AI agents which files to test first — churn, coverage, and test mapping as risk scores.

AST-based Python refactoring MCP server with safe automated refactorings and rollback

MCP as a Judge: a behavioral MCP that strengthens AI coding assistants via explicit LLM evaluations

Code context for AI dev tools: pack-scoped, cited code retrieval over MCP.

MCP server giving AI agents eyes and hands inside Android devices via ADB

Search, inspect, and install 400+ QA testing skills from qaskills.sh into any MCP client.

Local MCP for Chinese criminal dossier review; Word notes + Excel catalogs stay on-device.

Structural code-quality tools for AI coding agents.

Federated academic search, citation traversal, persistent PDF download, and temporary reading.

Semantic search over IMAGIN.studio API documentation — CDN, API, integration guides, and more.

Epistemic foraging for AI agents: source discovery, verified evidence, uncertainty-aware briefs

Gold-first AI-agent traceback diagnosis, exact fixes, verification, and reusable prescriptions.

Manage temporary or persistent Linux VMs (QEMU/KVM). Designed for AI agents and automation.

Generate QA datasets & evaluate RAG systems with failure diagnosis. Any LLM.

Delegate bulk code edits to a cheap worker model. Gated, atomic. PHP and Python.

Django ORM static analysis MCP. Models, relations, migrations, indexes, signals, N+1.

AI-powered log analysis - parse, search, extract errors across 9+ formats

A verified dependency-audit verdict any AI agent can call over MCP, not a raw scan.

Code review as an MCP server — structured reviews with OWASP security scanning.