"Understanding local computer vision models like YOLO" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
Coding agents in multi-service codebases routinely rebuild existing helpers, trust stale type definitions, and modify API contracts without knowing who consumes them. Carrick solves this by indexing your entire TypeScript ecosystem across service and repository boundaries. By integrating deeply with the TypeScript compiler, Carrick traces every route, type, and cross-service call while recording function behaviour so agents search by intent rather than name. Delivered via MCP for AI agents and LSP for IDEs, Carrick ensures models see existing endpoints and utilities before generating new code. The scanner is source-available and runs from your CLI or CI pipeline.
Security reviews, threat models over a repo or website, and remediation tracking, in your editor.
Guardian agent for AI coding: four frontier models review risky diffs and commits before they ship.
An MCP server that compiles ASN.1 schema definitions into executable, native source code for a variety of languages (like Python, Rust).
Your AI agent is smart enough to code all day. Local firewall & zero-loss runtime.
APK ZIP local-file count, bytes discarded
Find retiring AI models and outdated API SDKs in your code, with dates, replacements and guides.
Repository knowledge graph MCP server for codebase understanding and debugging.
Multi-model code review: a panel of models + detectors return a pass/fail verdict. Paid via x402.
The OpenZeppelin Stylus Contracts MCP server generates secure smart contracts for the Arbitrum Stylus environment using OpenZeppelin templates, including ERC-20, ERC-721, and ERC-1155 standards. It automatically validates generated code against OpenZeppelin's security and style rules, enforcing best practices for imports, modifiers, naming conventions, and security checks to prevent common vulnerabilities. The server integrates with AI development tools like Cursor, Claude, Gemini, Windsurf, and VS Code to enable AI-assisted, production-ready smart contract development.
Multi-LLM council: 25+ frontier models in parallel, consensus scoring, verdict-first code review.
Stop your AI agents from writing sloppy TypeScript. A toolkit that teaches coding agents like Claude Code, Codex, Cursor, Amp, and more to ship production-ready code in half the time, at half the cost. Docs are available at https://convention.sh/docs
IaC, CI and dependency security review for coding agents: local scan CLI plus hosted OAuth MCP.
Code review by AI models from different companies, usually two. Shows where they agree and disagree.
Review connected software projects, submit local findings and read reports with explicit approval.
Audits MCP tool definitions for patterns that make models call tools wrong or mis-fill args.
MCP server for understanding Javascript internals from ECMAScript specification.
AI-powered codebase analysis — call graphs, security, dead code, complexity. 150+ tools.