Vectr
Semantic codebase search + persistent working memory for AI code editors. Local, no API key.
Open the source (opens github.com) https://github.com/swapnanil/vectr
Before you use it
- Runs on your computer with your permissions. Read what it can do before connecting it to an agent.
What it is
MCP servers from io.github.swapnanil.
The problem it solves and who it suits haven't been reviewed by InnerVault. The description above is the source's own.
How to get it
pypi package (stdio)
vectr@1.12.0
From the server's entry in the official MCP Registry
pypi package (streamable-http)
vectr@1.12.0
From the server's entry in the official MCP Registry
Settings it asks for
VECTR_PORT· Port the local vectr daemon serves MCP on. Start the daemon with `vectr start` before connecting.
Related
-
Vectreal
MCP serversUpload, publish and embed 3D models on any website from your agent.
@vctrl/cli@3.1.0 -
Vectree
MCP serversSearch and read ~95,000 interactive concept diagrams that explain how things work — visually.
-
mcp-server
MCP serversTyped record store + hybrid search over MCP: deterministic lookups + semantic memory, per-customer.
@vectros-ai/mcp-server@0.19.0 -
GitHub MCP server
MCP serversGitHub's official MCP server. It lets an agent read and work with repositories, issues and pull requests.
https://api.githubcopilot.com/mcp/ -
Apify MCP server
MCP serversLets an agent run Apify's ready-made scrapers to pull data from websites, search engines, maps and social platforms.
-
Official MCP Registry
MCP serversThe MCP project's own registry of public MCP servers, so you can look for a connector before building one.