Lightweight browser automation for AI agents: navigate, screenshot, extract, PDF. One small binary.
Loading MCP servers…
Lightweight browser automation for AI agents: navigate, screenshot, extract, PDF. One small binary.
Showing 337–384 of 3,099
Encoding-aware, indentation-smart file tools for AI coding agents with SSH, SFTP, and 20+ tools.
The shell around your coding agent: a neuro-symbolic code graph with calibrated trust, via MCP.
Local, deterministic review of Git changes: weakened tests and CI gates, risky flows, blast radius.
Temporal knowledge graph for codebases with constraint enforcement at the edit boundary.
MCP server bridging AI assistants to OpenAI Codex CLI for code analysis and review
Proxy MCP for Playwright, Figma, DevTools, Shopify Dev, Context7 — fewer tokens, caching
Roslyn-powered MCP server for C#/VB.NET. Query symbols, call graphs, and facts. 90%+ token savings.
Agent-first MCP server for WeChat Mini Program debugging & automation via WeChat DevTools.
Keep the state. Change the model. Shared context and a multi-model panel across coding assistants.
Hand browser work off to a server-side agent: read the page as a table, act, then verify.
Cross-repository semantic code intelligence for AI coding agents, from a local code graph.
MCP server for Apple's App Store Connect API. Manage apps, TestFlight, and more.
Git and forge ops: local git via gitoxide, plus GitHub, GitLab, Gitea and Forgejo
Compiler-backed read-only Verilog and SystemVerilog project analysis.
Catch spec drift before it catches you. Detect overlap, stale docs, and code drift.
GoReleaser MCP server
MCP server for Cucumber Studio - test scenarios, action words, and execution data
Build, simulate and calibrate JAX block-diagram models of hybrid dynamical systems.
Multi-language code analysis for complexity, debt, hotspots, ownership, and defect prediction
Playwright-style automation of .NET desktop apps (WPF, WinForms, WinUI) for AI agents.
Inspect waveforms and navigate RTL in live Synopsys Verdi. Requires a licensed Verdi installation.
Chrome over CDP for AI agents. Blind benchmark vs agent-browser: -33% tokens, -33% cost, -32% time
Development tooling MCP server with process management, proxy, and frontend diagnostics
One shared, durable memory for your AI coding agents — local-first, zero-dependency.
Give Claude live access to SAP ABAP via ADT: read, search, check, test, and edit objects.
Deterministic local-first context and impact maps for coding agents from tasks, issues, and diffs.
MCP server for AI agents to interact with terminal applications. Think Playwright for terminals.
Indexes your codebase's public API and serves it via compact MCP tool responses.
Reversibly compress tool outputs to recoverable handles; expand to exact original bytes on demand.
Inspect and drive WPF apps: trees, bindings, screenshots, mouse dragging and touch gestures.
Full-featured ADB MCP server — 209 tools across 49 modules, from UI to baseband.
Zuul CI — build failure analysis, log search, pipeline status, and job configuration
Graph-powered code intelligence with semantic search and knowledge graph for AI assistants
Spec-Driven Development workflow: specs, plans, gates, status and logbook tools. Bilingual EN/ES.
Build native Linux packages (.deb/.rpm/.apk/.pkg.tar.zst) from a single PKGBUILD via MCP.
Annotates any web page with hover labels for AI assistants — zero extensions, any browser
Authenticated local evidence paths for JavaScript and TypeScript coding agents.
Android engineering MCP server with verified documentation grounding and AI validation tools.
Generate IDs, QR codes, and hashes, encode values, geolocate IPs, plus gated host diagnostics.
Manage Meta apps: creation, configuration, webhooks, permissions, compliance, and App Review.
WinDbg/DbgEng over MCP: crash dumps, live user & kernel, driver IOCTLs, and TTD.
MCP server for building, inspecting, and exporting PhysiCell and PhysiBoSS configuration files
Transcribe videos from 1000+ platforms or local files offline, and search across every transcript
Find test gaps, generate grounded tests, and dynamically prove behavior with mutation testing.
Agent-safe structured edits: JSON/YAML/TOML/md/AST, dry-run, batch/tx. Not a filesystem MCP.
Lets AI agents read the real source of any Maven dependency, decompiled from ~/.m2 or Central.
Python wrapper that makes Xcode's MCP bridge compatible with strict MCP clients like Cursor