CodeGraph
未认领CodeGraph builds a semantic graph of your codebase — functions, classes, imports, call chains — and exposes it through 42 MCP tools, 38 languages, a VS Code extension, and a persistent memory layer. AI agents get structured code understanding instead of grepping through files.
01 / 选择客户端
03 / 添加配置
claude mcp add --transport stdio 'codegraph' -- 'npx' '-y' '@vscode/vsce' 'package'04 / 在客户端中确认
打开客户端的 MCP 设置，确认服务器已连接并列出工具。复制配置不代表连接成功。
更多Databases服务器
浏览完整目录安全概况
已认领和已认证的服务器每周接受一次静态扫描，显示代码能触及的范围（外部服务、环境变量、shell 命令、代理配置目录）以及带有已知公告的依赖。认领此列表即可获得。 安全概况的工作原理
40 个工具中显示 40 个
文档中列出的工具 (40)
内容来自项目文档。服务器握手不会验证每个工具的说明或行为。
analyze_complexity
Cyclomatic complexity with breakdown (branches, loops, nesting, exceptions, early returns)
analyze_coupling
Module coupling metrics and instability scores
analyze_impact
Blast radius prediction — what breaks if you modify, delete, or rename
core
8 — search + symbol info + AI context
design_gaps
Find identifiers described in docs that don't exist in code yet — build TODO lists from specs
find_by_imports
Find files importing a module
find_by_signature
Search by param count, return type, modifiers
find_circular_deps
Detect circular import/dependency chains across files
find_dead_imports
Find unused imports — modules imported but never referenced
find_entry_points
Main functions, HTTP handlers, CLI commands, event handlers
find_hot_paths
Most-called functions ranked by transitive caller count
find_implementors
Find all functions registered as ops struct callbacks
find_related_tests
Tests that exercise a given function
generate_architecture_doc
Auto-generate a structured ARCHITECTURE.md from the live code graph (modules, hot paths, complexity, circular deps)
get_ai_context
Primary context tool. Intent-aware (explain/modify/debug/test) with token budgeting. Returns source, related symbols, imports, siblings, debug hints.
get_call_graph
Function call chains (callers and callees)
get_curated_context
Cross-codebase context for a natural language query ("how does auth work?")
get_dependency_graph
File/module import relationships with depth control
get_detailed_symbol
Full symbol info: source, callers, callees, complexity
get_edit_context
Everything needed before editing: source + callers + tests + memories + git history
get_module_summary
High-level summary of a directory: file count, functions, language breakdown, top complex functions
get_symbol_info
Quick metadata: signature, visibility, kind
graph
17 — callers/callees/deps/impact/traverse/PR context
index_directory
Add directory to graph alongside existing data
index_files
Add/update specific files without full reindex
index_markdown
Index a local .md file (ARCHITECTURE.md, APIDESIGN.md, etc.) into the persistent docs store. Heading-tree chunking with leaf-node embeddings.
list_doc_sources
List all indexed source files
memory
14 — codegraphmemory plus the docs tools
memory_context
Get memories relevant to a file/function
pr_context
One-call PR review. Runs git diff against base branch, finds changed functions in the graph, reports: blast radius (callers), test coverage + gaps, affected modules, diff-aware change classification (signature vs body), stale-doc warnings, complexity, commit-message hint, suggested reviewers from gi
reindex_workspace
Full or incremental workspace reindex
remove_doc_source
Remove all indexed chunks from a source file
scan_security
Security vulnerability scan: 40+ dangerous function patterns, source-to-sink taint tracing, auth coverage for HTTP endpoints (7 languages/frameworks), architectural layer violations, weak crypto, hardcoded secrets
search_by_error
Find functions that throw, catch, or handle specific error types
search_by_pattern
Regex search across function bodies, signatures, names, and docstrings
search_docs
Semantic search over indexed docs — returns matching sections with heading-path breadcrumbs
security
pro security tools only (empty on community)
symbol_search
Find symbols by name or natural language (hybrid BM25 + semantic search)
traverse_graph
Custom graph traversal with edge/node type filters
verify_design
Cross-reference doc claims vs code graph. direction=forward (doc→code), reverse (code→doc), or both