Developer Tools MCP servers

PoC Q5b: run a differently-named console script via a positional runtimeArgument.

SOLID/OOP/DRY, the 23 GoF patterns, pattern scaffolding, and heuristic code-smell detection.

UAE Design System (AEGOV DLS) for AI assistants: components, tokens, validation. Not TDRA-official.

Architecture governance for AI agents: query the live model, get target patterns, check files.

Read-only MCP server for the official ACTA verifiable credentials documentation.

Cited 'why was this decided?' answers for your repo and for React, Kubernetes, and Rust.

Persistent code knowledge graph + 9 composite MCP tools for AI coding agents.

Local tools for planning and validating focused browser-game prototypes.

Drive devices and APIs from their W3C Thing Description. You gate every operation.

Capture dev context on interrupt; replay it as a 30-second resume card. Git stash for your head.

Zero-config SQL flight recorder for slow Python/SQLAlchemy jobs: exact call site, count, and fix.

AI agents read TraceBug bug reports (console, network, replay, repro timeline) from local disk.

Agent-native API client: execute/test REST/GraphQL/WS/SSE with assertions, extraction, collections

Tunnels and webhooks for AI agents: capture, await, verify, replay, and send signed test events.

Verify docs against code, detect drift, and generate verified specs (MCP server).

Local-first MCP server that reconstructs architecture, workflows and business rules from your code.

Recorded browser sessions, backend spans, and database row diffs as one ranked fix bundle.

Practice library for coding agents: skill search/invoke, seed patches, scout, reflect, ADR writer

Mines your Claude Code and Cursor sessions into evidence-based CLAUDE.md / AGENTS.md rules.

AI agents create, run, and save API requests as Gud API collections in your project.

Search 276,000+ open source icons and insert them as SVG or React components while you code.

Deploy and monetize agent-built apps: login, database, usage billing, and end-user-pays.

Visual regression & snapshot testing for AI agents — list runs, read semantic diffs, review.

Dependency-graph MCP server. Tells Claude/Cursor what breaks if you change X. Provenance guards.

Audit any MCP server's security & quality — OWASP MCP Top 10 + explainable 0-100 MCP Score

Two-way Figma MCP: extract + verify design-to-code, or generate on-brand Figma pages from a prompt.

Query pudge-ui — 93 skeuomorphic 2000s-era UI component specs — for coding-agent context.

Independent before/after accessibility-overlay (accessiBe/UserWay) witness for any public URL.