"Coze" matching MCP servers:

Searches Claude Code documentation via BM25 indexing, returning ranked snippets with category filtering. Enables fast, local search over official docs without full-document scans.

MCP server for IFC4.3 specification reference — search and retrieve IFC entity definitions, attributes, inheritance hierarchies, and PropertySets

Facilitates searching and accessing programming resources across platforms like Stack Overflow, MDN, GitHub, npm, and PyPI, aiding LLMs in finding code examples and documentation.

Provides AI assistants with access to personal best practice skills and coding guidelines stored as markdown files in a GitHub repository, enabling retrieval and listing of custom development standards.

Intelligently detects package managers and provides unified access to documentation and information across 15+ package ecosystems including npm, PyPI, and others. Automatically routes requests to appropriate package-specific MCP servers for README retrieval, package information, and cross-ecosystem package search.

Provides deterministic, read-only access to engineering decisions, requirements, and designs stored as Markdown in a repository, enabling agents to retrieve and follow decided context without embeddings or external services.

An MCP server that provides static validation and documentation lookup for quantum computing libraries, currently supporting PennyLane. It allows users to verify quantum code syntax and method usage against official library documentation to ensure correct implementation.

An MCP server that performs code reviews by comparing local source code against design documents stored in Confluence. It integrates with Atlassian MCP servers to analyze documentation and provide suggestions for quality improvement based on design specifications.

Provides AI agents with a governed, three-layer project memory (guide, code facts, and knowledge) through namespaced MCP tools for code search, context compilation, impact analysis, and proposal-driven documentation updates.

Allows LLM tools like Claude Desktop and Cursor AI to access and summarize code files through a Model Context Protocol server, providing structured access to codebase content without manual copying.

Enables AI coding assistants to browse Unreal Python API documentation, search classes and functions, and execute Python code in Unreal Editor.

A Model Context Protocol server for querying and reading articles from a how-to documentation portal, with search and retrieval tools scoped to the token's user permissions.

High-performance code understanding toolkit that enables batch reading of multiple files with dependency context, structural outline extraction with Java annotation awareness, and precise location of classes/methods across large codebases.

Connects to vibe-code-best-practices.vercel.app to index 817 tools across 185 sections and 10 domains, routes the right tool/Skill for your project need, and can recommend a full stack.

Analyzes source code across multiple languages to extract structural elements like classes, functions, and parameters using tree-sitter. It provides LLM-optimized markdown output that includes nesting levels, line numbers, and signatures to facilitate codebase navigation.

Provides semantic search and intelligent access to SAP AI Core documentation for AI assistants like Claude. It enables users to search across categories, retrieve full document content, and access topic-specific information from the SAP artificial intelligence repository.

Automatically collects, summarizes, and documents code from vibe coding sessions, generating multiple document types (README, DESIGN, TUTORIAL, etc.) and publishing them to platforms like Notion, GitHub Wiki, and Obsidian.

Enables users to search and navigate over 22,500 indexed sections across 16 Canadian building codes and user guides. It supports keyword searches, hierarchy navigation, and optional full-text extraction from user-provided PDF documents.

Enables document-driven development by automatically detecting Markdown spec changes, generating implementation plans, and syncing code and tests through MCP tools.

A local, read-only MCP server that lets coding agents search the complete AAS skill catalog, compose and validate agent-chosen skill stacks, and generate reproducible, reviewable plans without uploading project code.