About Turbovec MCP
Turbovec MCP is an MCP server published by Gabrielsandbox in the RAG category: high-performance RAG for Claude Code — semantic file search powered by Google TurboQuant (TurboVec). MCP server + CLI.
The repository has 2 stars and 0 forks, with the last commit 4 months ago. Recent commit activity is the strongest signal that reported issues will get attention.
Install
git clone https://github.com/Gabrielsandbox/turbovec-mcpThis server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.
Tools (11)
tv_create_dbCreate a new database and choose its embedding provider/model
Parameters not published.
tv_deployDeploy to local copy, `.tar.gz` archive, S3, GCS, or Azure
Parameters not published.
tv_http_server_infoShow how to start the HTTP server for a database
Parameters not published.
tv_importImport from a local archive or cloud URI
Parameters not published.
tv_indexIndex a file or directory (`.md` `.py` `.ts` `.json` `.sql` and 20+ more)
Parameters not published.
tv_list_dbsList all databases with their embedding provider and model
Parameters not published.
tv_list_providersList all available providers and models
Parameters not published.
tv_remove_fileRemove a file's chunks from the index
Parameters not published.
tv_searchSemantic search → chunks with file path, line range, similarity score
Parameters not published.
tv_statsShow index stats including the active embedding provider
Parameters not published.
tv_use_dbSwitch to a different database (provider auto-restored)
Parameters not published.
Ask AI
Ask AI about Turbovec MCP
Powered by Claude · Grounded in docs
Security checks
6 checks have not been run yet.