Developer Tools MCP servers

Local retrieval for AI agents: index code, docs, PDFs, data in SQLite; 24 parsers, served via MCP.

AI testing harness with Jay: risk-based checks, bug investigation, and local evidence reports.

Curated MCP tools from OpenAPI, websites, apps, Postman, cURL or SQL; your agent designs them.

Turn any codebase into a queryable knowledge graph — offline-first, zero API keys.

Finds the files a coding task touches, so your AI agent reads less. Local CLI and MCP server.

Sandboxed coding workers, verified: tests rerun fresh and must fail with the change reverted.

Play with your app's design in the browser: load a build, turn the knobs, export the code.

Turn a research paper into working code and prove, claim by claim, how close it gets.

Fast local and federated OSS code search and repo discovery for AI agents

Code Intelligence Platform for AI Coding Agents

Disposable microVM sandboxes for AI agents: run code, read/write files, git, preview URLs.

Click an element in your running app or iOS Simulator, say what should change; your agent gets it.

Engineering decisions, change impact, documentation audits, and CI evidence for coding assistants.

Recommends MCP servers, plugins and skills for a repo, from what is actually in it.

Self-hosted gallery of your SwiftUI #Preview and Jetpack Compose @Preview screens.

Read-only source-linked AI API prices, comparisons, cost estimates, and price changes.

Discover Swagger/OpenAPI operations and call configured dev/UAT APIs through 10 fixed tools.

Runs Python in a local, hardware-isolated micro-VM that keeps its state between calls

Upload Android, iOS and HarmonyOS apps to PGYER and manage their apps and versions.

Local-first AI identity for MCP coding tools. Lessons, decisions, and context you control.

WCAG 2.1 AA accessibility scanner (Playwright + axe-core) with grounded, browser-verified fixes.

Visual website feedback, screenshots and team discussion for coding assistants. Self-hosted.

Run Android tests on real phones, or lease one: install, shell, screenshot, logcat.

LSP call graph for coding agents: a symbol's callers, callees, tests and live files in one call.

Delegate coding tasks to the OpenAI Codex CLI, installed separately, with explicit model and effort.

Tells coding agents which npm dependencies changed after their training cutoff, and what changed.

Serial terminal with a GUI that AI assistants drive over MCP: read device logs, send commands.

Inspect n8n, Dify, Trigger.dev and Activepieces automation exports before deployment.