DOCS BLOG ABOUT TRY THE GATEWAY

// MCP TOOL REFERENCE

CODEGRAPH TOOLS

38 tools from the Codegraph MCP Server, categorised by risk level.

View the Codegraph policy → Token cost: 7,958 tokens →

// ALL 38 CODEGRAPH TOOLS

READ 33 tools

Read codegraph_analyze_complexity Measures code complexity metrics for refactoring decisions. USE WHEN: identifying functions that need simpl... Read codegraph_analyze_coupling Measures module coupling for architectural analysis. USE WHEN: evaluating module boundaries, planning decou... Read codegraph_analyze_impact Predicts blast radius of code changes before making them. USE WHEN: planning refactoring, renaming symbols,... Read codegraph_cluster_symbols Groups functions into semantic clusters based on what they do (e.g., all database access functions, all err... Read codegraph_compare_symbols Compares two functions semantically and structurally. USE WHEN: reviewing duplicates from find_duplicates, ... Read codegraph_cross_project_search Search for symbols across ALL other indexed projects in the shared graph database. USE WHEN: finding cross-... Read codegraph_find_by_imports Finds all files importing a specific module or package. USE WHEN: planning library migrations, finding all ... Read codegraph_find_by_signature Finds functions matching signature patterns. USE WHEN: searching by structural characteristics rather than ... Read codegraph_find_duplicates Detects duplicate and near-duplicate functions across the codebase using semantic code embeddings. USE WHEN... Read codegraph_find_entry_points Discovers application entry points and execution starting points. USE WHEN: understanding app architecture,... Read codegraph_find_implementors Find all functions registered as implementations of an ops struct field (e.g., who implements ndo_open in n... Read codegraph_find_related_tests Discovers test files and functions that exercise specific code. USE WHEN: modifying code to know which test... Read codegraph_find_similar Finds functions most similar to a given function using semantic code embeddings. USE WHEN: checking if simi... Read codegraph_find_unused_code Detects dead code that can be safely removed. USE WHEN: cleaning up codebase, reducing bundle size, or find... Read codegraph_get_ai_context Gathers comprehensive code context optimized for AI understanding. USE WHEN: explaining code, planning modi... Read codegraph_get_call_graph Maps function call relationships showing callers and callees. USE WHEN: tracing execution flow, understandi... Read codegraph_get_callees Finds all functions called by a target function (forward call graph). USE WHEN: understanding function depe... Read codegraph_get_callers Finds all functions that call a target function (reverse call graph). USE WHEN: understanding function usag... Read codegraph_get_curated_context Discovers and assembles context across the entire codebase for a natural language query. USE WHEN: you need... Read codegraph_get_dependency_graph Analyzes file import/dependency relationships. USE WHEN: understanding module architecture, finding circula... Read codegraph_get_detailed_symbol Gets comprehensive symbol details including source code and relationships. USE WHEN: you need full context ... Read codegraph_get_edit_context Assembles everything needed to edit code at a specific location in a single call. USE WHEN: you are about t... Read codegraph_get_symbol_info Gets quick metadata about any symbol (function, class, variable, type). USE WHEN: you need to quickly under... Read codegraph_memory_context Finds memories relevant to current code location. USE WHEN: starting work on a file/function to see past co... Read codegraph_memory_get Retrieves full memory details by ID. USE WHEN: you have a memory ID from search results and need complete c... Read codegraph_memory_invalidate Marks memory as outdated without deleting. USE WHEN: knowledge is superseded, bugs are fixed, decisions are... Read codegraph_memory_list Lists memories with filtering and pagination. USE WHEN: browsing available memories or auditing stored know... Read codegraph_memory_search Searches memories with hybrid BM25 + semantic + graph proximity. USE WHEN: recalling past knowledge — previ... Read codegraph_memory_stats Get statistics about stored memories - counts by kind, total storage, etc. Read codegraph_memory_store Persists knowledge for future sessions. USE WHEN: discovering important context worth remembering — debuggi... Read codegraph_reindex_workspace Reindex the workspace to refresh the code graph. USE WHEN: the graph data is stale or parsers have been upd... Read codegraph_search_git_history Searches git commit history using both semantic matching and keyword search. USE WHEN: you need to understa... Read codegraph_symbol_search Searches codebase for symbols by name or pattern. USE WHEN: finding function/class implementations, explori...

WRITE 3 tools

Write codegraph_index_files Add or update specific files in the code graph without full reindex. USE WHEN: new files were created, exis... Write codegraph_mine_git_history Mines git history to create memories from commit messages and patterns. USE WHEN: setting up a new project ... Write codegraph_mine_git_history_for_file Mines git history for a specific file to create memories. USE WHEN: wanting to understand the history and e...

DESTRUCTIVE 1 tools

Destructive codegraph_index_directory Add an entire directory to the code graph without clearing existing data. USE WHEN: you need to explore a n...

EXECUTE 1 tools

Execute codegraph_traverse_graph Advanced graph traversal for complex code exploration. USE WHEN: specialized analysis requiring custom trav...

// FAQ

How many tools does the Codegraph MCP server have? +

The Codegraph MCP server exposes 38 tools across 4 categories: Read, Write, Destructive, Execute.

How do I enforce policies on Codegraph tools? +

Route the Codegraph server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard — they are enforced on every call before it reaches the server.

What risk categories do Codegraph tools fall into? +

Codegraph tools are categorised as Read (33), Write (3), Destructive (1), Execute (1). Each category has a recommended default policy.

Let agents act without letting them run wild.

Route your MCP servers through PolicyLayer and every tool call is checked against your policy before it runs — allow, deny, or require approval. Per-identity grants. Full audit log. Live in minutes.

SECURE YOUR MCP →

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.