MCP servers that give coding agents real developer tooling: linters, package registries, test runners, language docs and local build commands. 이 카테고리에 13,985 servers가 있습니다.
Provides local code search using AST chunking and dependency graphs to reduce AI agent token usage.
Converts Excel, ODS, CSV, JSON, SQLite, Parquet, Arrow, and MTSV files into plain text for AI agents to read and process.
Provides semantic code intelligence for AI coding agents via a command-line tool.
Provides a machine-generated public record of Model Context Protocol server conduct and measurement verdicts.
Provides an AI client with durable engineering context across repositories by managing components, repos, tasks, and governance as markdown files.
Enables AI agents to perform precise offline unit conversions, dimensional analysis, and SI base unit reduction using the GNU units database.
Compiles websites into typed SDKs and MCP servers to allow AI agents to perform semantic actions without parsing raw HTML.
Provides coding agents with a suite of engineering tools including verification gates, repository maps, LSP, code graphs, and RAG.
Allows an AI client to inspect schemas and execute read-only SQL queries against a ClickHouse database.
Scaffolds production-ready FastMCP servers with built-in authentication, CI/CD pipelines, Docker support, and automated release workflows.
Provides an example application architecture to compare REST and MCP-based travel booking workflows and authentication methods.
Scans AI-generated GitHub repositories for security vulnerabilities like leaked keys, environment files, and SQL injection.
$claude mcp add --transport http vibescan https://vibescan.bigfloppy.net/mcp
Optimizes websites for AI agents by generating machine-readable assets like llms.txt, Markdown versions, API catalogs, and MCP server cards.
Converts existing source code into executable Functions, MCP tools, workflow Skills, and offline tests for AI coding agents.
Provides coding agents with a live knowledge graph of codebases to retrieve intent, co-change context, and architectural relationships.
Provides runnable modules for building AI agents, implementing RAG, managing memory, and deploying MLOps pipelines.
Generates Sphinx documentation for MCP tools, prompts, resources, and resource templates.
Enables coding agents to build, test, and evaluate reliable multi-step LLM workflows using typed files and local experiments.
Provides AI editors with code rationale by synthesizing git history, pull requests, and call-graph context.
An open-source, bilingual course providing hands-on labs for building reliable RAG systems, AI agents, and production-ready LLM applications.
