semantic_code_search
Search by meaning, not exact text. Uses embeddings over file headers/symbols and returns matched symbol definition lines.
How to use it
semantic_code_search is exposed by the Contextplus MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), and the semantic_code_search tool becomes available to the model automatically. See the full listing for setup details and every tool this server provides.
Install Contextplus
npx -y contextplus init claudeOther tools in Contextplus (16)
Bulk-add nodes with auto-similarity linking (cosine ≥ 0.72 creates edges automatically).
Create typed edges between nodes (relatesto, dependson, implements, references, similarto, contains).
Trace every file and line where a symbol is imported or used. Prevents orphaned references.
Structural AST tree of a project with file headers and symbol ranges (line numbers for functions/classes/methods). Dynamic pruning shrinks output automatically.
Obsidian-style feature hub navigator. Hubs are .md files with [[wikilinks]] that map features to code files.
Function signatures, class methods, and type definitions with line ranges, without reading full bodies. Shows the API surface.
List all shadow restore points created by proposecommit. Each captures file state before AI changes.
The only way to write code. Validates against strict rules before saving. Creates a shadow restore point before writing.
Remove decayed edges (e^(-λt) below threshold) and orphan nodes with low access counts.
Start from a node and walk outward — returns all reachable neighbors scored by decay and depth.
Run native linters and compilers to find unused variables, dead code, and type errors. Supports TypeScript, Python, Rust, Go.
Semantic search with graph traversal — finds direct matches then walks 1st/2nd-degree neighbors.
Identifier-level semantic retrieval for functions/classes/variables with ranked call sites and line numbers.
Browse codebase by meaning using spectral clustering. Groups semantically related files into labeled clusters.
Restore files to their state before a specific AI change. Uses shadow restore points. Does not affect git.
Create or update a memory node (concept, file, symbol, note) with auto-generated embeddings.