Back to Home
wgawan icon

mcp-code-vector--search

Verified Safe

by wgawan

Overview

Builds a semantic index of a codebase for natural language search and code context retrieval, often used as a tool for AI coding agents.

Installation

Run Command
PROJECT_ROOT=$YOUR_PROJECT_PATH ./run-docker.sh

Environment Variables

  • PROJECT_ROOT
  • PERSIST_DIR
  • FORCE_REINDEX
  • DEBUG

Security Notes

The server design generally appears robust. It uses standard, reputable libraries (ChromaDB, Sentence Transformers). When run via Docker, it limits file system write access to only the index directory (`/vector-index`). Input validation for `query` and `filter_filepath` in `semantic_search` is handled by ChromaDB's query interface, reducing direct injection risks. No 'eval' or obvious hardcoded secrets are present. The communication for the MCP client interface occurs over standard I/O (`stdio_server`), which reduces the direct network attack surface. The primary risk would be if a malicious client (within a trusted environment) could craft highly inefficient queries leading to excessive resource consumption, but this is generally mitigated by running against your own codebase in a controlled environment.

Similar Servers

Stats

Interest Score0
Security Score8
Cost ClassMedium
Avg Tokens650
Stars0
Forks0
Last Update2025-12-14

Tags

Code IndexingSemantic SearchOpenVINOChromaDBMCP Server