MCP servers
121,703 servers from the official registry, GitHub and npm. Filter by category, transport and language.
121,703 servers from the official registry, GitHub and npm. Filter by category, transport and language.
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 repowiseLets an AI client query an indexed codebase for callers, change risk, health scores, tests, ownership, and cited answers.
$claude mcp add --transport http repowise-hosted https://api.repowise.dev/mcpLets AI clients semantically search a codebase, find definitions and usages, and trace symbol and file dependencies.
$claude mcp add octocode -- npx -y @muvon/octocodeLets AI assistants run CodeScene Code Health reviews on a local codebase to find maintainability issues and technical debt.
$claude mcp add codescene-mcp-server -- npx -y @codescene/codehealth-mcpLets AI agents search code semantically, research behavior with citations, and dig through git history and web docs to ground answers in your codebase.
Provides a local knowledge graph that connects source code, documentation, and infrastructure to give AI agents structural context.
$claude mcp add codebase-memory-mcp -- npx -y codebase-memory-mcpAllows AI clients to explore the Claude Code source code by browsing tools, commands, and searching the codebase.
$claude mcp add codemaster -- npx -y @divyesh2000/codemasterLets AI agents perform compiler-accurate semantic analysis, navigation, search, refactoring, and metrics on Java codebases via Eclipse JDT.
$claude mcp add javalens-mcp -- npx -y javalens-mcpSearches the web, academic papers, and codebases to build a local knowledge graph with automated ontology and data lineage.
$claude mcp add google-surf-mcp -- npx -y google-surf-mcpBuilds a semantic graph of TypeScript codebases so an AI client can search code and analyze dependency impact.
$claude mcp add code-graph-context -- npx -y code-graph-contextLets 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 codenibBuilds 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-graphLets AI agents read and write a codebase ontology stored as Markdown files to maintain a map of system logic, dependencies, and documentation.
$https://github.com/wlsdks/ontology-atlas/releases/download/v1.2.0/ontology-atlas-mcp-0.13.0.mcpbLets 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:3.0.3Gives AI coding agents deterministic, local codebase memory and pre-commit guardrails over MCP, without an LLM in the hot path.
$claude mcp add openlore -- npx -y openloreGives AI clients filesystem access to read, write, search, and modify project files, plus run custom commands and generate context documents.
Indexes your codebase so AI assistants can search code, docs, and notes with far less context than grep.
$claude mcp add aidex -- npx -y aidex-mcpLets 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-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-rag