MCP 서버
공식 레지스트리, GitHub 및 npm의 121,886개 서버. 카테고리, 전송 방식 및 언어로 필터링하세요.
공식 레지스트리, GitHub 및 npm의 121,886개 서버. 카테고리, 전송 방식 및 언어로 필터링하세요.
Lets AI coding agents query a prebuilt index of a codebase's graph, git history, tests and decisions instead of grepping files.
$claude mcp add repowise -- uvx repowiseProvides a bi-temporal structural knowledge graph that allows AI coding agents to query codebase relationships, history, and impact analysis locally.
$claude mcp add memtrace-public -- npx -y memtraceProvides AST-based semantic code search for local repositories using incremental re-indexing and natural language queries.
$claude mcp add cocoindex-code -- uvx cocoindex-codeBuilds a structural knowledge graph of your codebase to enable semantic search and call-graph resolution for token-efficient code reviews.
$claude mcp add crg -- uvx n24q02m-crgEnables AI coding agents to navigate codebases by symbol, maintain persistent memory across sessions, and reduce token usage via Bash command rewriting.
$claude mcp add token-savior -- uvx token-savior-recallEnables AI coding agents to navigate codebases by symbol, maintain persistent memory across sessions, and reduce token usage through Bash command rewriting.
$claude mcp add token-savior-recall -- uvx token-savior-recallAnalyzes codebases for dead code, security vulnerabilities, secrets, and AI-generated mistakes across multiple programming languages.
$claude mcp add skylos -- uvx skylosLets a coding agent search a local repository's symbol graph, trace callers, and read source with file and line citations.
$claude mcp add codenib -- uvx codenibIndexes your codebase to provide AI clients with efficient, searchable code context while reducing token usage.
$claude mcp add code-context-engine -- uvx code-context-engineBuilds a structural graph of codebases to help LLMs navigate entities, relationships, and flows without reading entire repositories.
$claude mcp add repo-graph -- uvx mcp-repo-graphAnalyzes codebases using tree-sitter to generate AGENTS.md files that provide architectural context and conventions for AI coding agents.
$claude mcp add agents-md-generator -- uvx agents-md-generatorLets AI agents build a persistent knowledge graph of code, docs and policies, and gate decisions with signed verdicts.
$claude mcp add graqle -- uvx graqleLets AI assistants semantically search and read indexed codebases, inspect file trees, and trace code relationships via MCP.
$claude mcp add codealive-mcp -- docker run -i --rm ghcr.io/codealive-ai/codealive-mcp:3.0.3Provides an evidence layer for AI coding agents to test, find bugs, and optimize codebases using runtime traces and real execution data.
$claude mcp add vinvai -- npx -y vinv-mcpProvides persistent semantic memory, knowledge graphs, and AST indexing to reduce AI agent token usage and improve codebase context.
$claude mcp add cognirepo -- uvx cognirepoLets an AI client index a codebase and retrieve exact functions, classes, and methods by symbol instead of reading whole files.
$claude mcp add jcodemunch-mcp -- uvx jcodemunch-mcpTranslates Python source code between English keywords and natural languages with static validation and round-trip verification.
$claude mcp add legesher-mcp -- uvx legesher-mcpParses a multi-language codebase into a knowledge graph so an AI client can query, retrieve, and edit code in plain English.
$claude mcp add code-graph-rag -- uvx code-graph-ragExposes Django project information through MCP tools to enable AI assistants to understand and interact with Django codebases.
$claude mcp add django-telescope -- uvx django-telescopeCompresses code context using AST-based skeletons to reduce token usage by up to 95% for AI coding assistants.
$claude mcp add tzeroalgorithm -- npx -y tzero-mcp