mcpbeat Sign in

Vectr MCP Server

by swapnanil Your server? Claim it
local only

Vectr runs on your own machine — the client starts it, so there is no endpoint to ping. 156 installs a week from pypi. Last commit 6 Sep 2026.

Semantic codebase search + persistent working memory for AI code editors. Local, no API key.

Installs per day peak 103 · avg 32 · -52% w/w
a month agotoday
156
Installs / week
pypi · vectr
2
Stars
0 open issues
6 Sep 2026
Last commit
from GitHub
MIT
License
Python

What the code does

We read the source, 2 d ago · rules 995398eba69f

Capabilities

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.

    abs_path = os.path.normpath(os.path.join(root, path))
Runs an external command vscode-extension/src/extension.ts:102
    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.

This code can reach further than it looks

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.

Three servers free · no card

Connect this server

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.

run in your terminal
claude mcp add vectr -- uvx vectr
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "vectr": {
      "command": "uvx",
      "args": [
        "vectr"
      ]
    }
  }
}
~/.codex/config.toml
[mcp_servers.vectr]
command = "uvx"
args = ["vectr"]
.cursor/mcp.json
{
  "mcpServers": {
    "vectr": {
      "command": "uvx",
      "args": [
        "vectr"
      ]
    }
  }
}
.vscode/mcp.json
{
  "servers": {
    "vectr": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "vectr"
      ]
    }
  }
}

Optional settings from the registry entry, left out of the block above: VECTR_PORT (Port the local vectr daemon serves MCP on. Start the daemon with `vectr start` before connecting).

Alternatives to Vectr

same job, measured the same way
Longmem
by marerem

Persistent cross-project memory for Cursor and Claude Code using local semantic search.

38 installs/wk local only
Code Memory
by kapillamba4

Local semantic code search with Git history. Works offline, no API key needed.

216 installs/wk local only
Filesift
by roshunsunder

Local file search for AI agents — semantic + keyword indexing over your codebase.

44 installs/wk local only
Memex
by pragneshbagary

Persistent session memory for Claude Code. Local SQLite, no LLMs, no network.

103 installs/wk local only
CogZ
by balaianu

Local-first engineering cognition for AI coding agents — persistent memory over your codebase.

local only
Lybrary
by vibhu-dixit

Local codebase memory and repository code search for Codex, Claude Code, and MCP coding agents.

68 installs/wk local only
RemembrallMCP
by cdnsteve

Persistent knowledge memory for AI agents. Hybrid search, code graph, pgvector.

44 installs/wk local only
Socraticode
by giancarloerra

MCP server for enterprise local codebase indexing, semantic search, and code dependency graphs.

2 582 installs/wk local only

Vectr — questions

Answers built from our own checks of this server.

Why is there no uptime for Vectr?
Vectr runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the pypi package vectr was installed 156 times last week.
How do I connect Vectr?
Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It runs locally, so the command pulls vectr straight from pypi; nothing to host, nothing to sign up for.
How many people use Vectr?
The pypi package vectr was installed 156 times in the last week. Week over week that is -52%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.
Is Vectr open source?
Yes — it is published under the MIT licence, written in Python and 2 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.