Vectr runs on your own machine — the client starts it, so there is no endpoint to ping. 541 installs a week from pypi. Last commit 6 Sep 2026.
Semantic codebase search + persistent working memory for AI code editors. Local, no API key.
We read the source, 20 h ago · rules 3dff92dd89df
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
subprocess.Popen(
abs_path = os.path.normpath(os.path.join(root, path))
cp.spawn(launcher.command, [...launcher.args, 'start', '--path', workspaceRoot, '--port', String(preferredPort)], {
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add vectr -- uvx vectr
{
"mcpServers": {
"vectr": {
"args": [
"vectr"
],
"command": "uvx"
}
}
}
[mcp_servers.vectr]
command = "uvx"
args = ["vectr"]
{
"mcpServers": {
"vectr": {
"args": [
"vectr"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"vectr": {
"args": [
"vectr"
],
"command": "uvx"
}
}
}
This one needs environment variables set before it will start:
VECTR_PORT (Port the local vectr daemon serves MCP on. Start the daemon with `vectr start` before connecting.).
The author declared them in the registry entry; get the values from the project itself.
Persistent cross-project memory for Cursor and Claude Code using local semantic search.
Local semantic code search with Git history. Works offline, no API key needed.
Local file search for AI agents — semantic + keyword indexing over your codebase.
Persistent session memory for Claude Code. Local SQLite, no LLMs, no network.
Private persistent memory for Claude, ChatGPT & Gemini via MCP - semantic search, zero-code setup.
Persistent knowledge memory for AI agents. Hybrid search, code graph, pgvector.
MCP server for enterprise local codebase indexing, semantic search, and code dependency graphs.
Persistent memory for Claude Code — offline, single-file, hybrid search.
Answers built from our own checks of this server.