Lovec MCP Server

by lovec-tech Your server? Claim it

local only

Lovec runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 17 Sep 2026.

Prompt-injection detector for untrusted text before it reaches an LLM (RU/EN). BYO lovec.tech key.

—

Installs / week

pypi · lovec-mcp

Stars

0 open issues

17 Sep 2026

Last commit

no recent releases

Apache-2.0

License

Python

Nothing serious here today

Today is the operative word: we check Lovec every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

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.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add lovec-mcp -- uvx lovec-mcp

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "lovec-mcp": {
      "args": [
        "lovec-mcp"
      ],
      "command": "uvx"
    }
  }
}

~/.codex/config.toml

[mcp_servers.lovec-mcp]
command = "uvx"
args = ["lovec-mcp"]

.cursor/mcp.json

{
  "mcpServers": {
    "lovec-mcp": {
      "args": [
        "lovec-mcp"
      ],
      "command": "uvx"
    }
  }
}

.vscode/mcp.json

{
  "mcpServers": {
    "lovec-mcp": {
      "args": [
        "lovec-mcp"
      ],
      "command": "uvx"
    }
  }
}

This one needs environment variables set before it will start: LOVEC_KEY (API key issued at https://lovec.tech (format aig_...). Every check is billed to this key's balance.), LOVEC_BASE (Alternative API host), LOVEC_TIMEOUT (Hard cap for one API call, seconds). The author declared them in the registry entry; get the values from the project itself.

Alternatives to Lovec

same job, measured the same way

Safeprompt

by safeprompt

Detect prompt injection, jailbreaks, and code injection in untrusted text before it reaches an LLM.

37 installs/wk local only

Injectshield

by bch1212

Prompt-injection firewall for AI agents — scan untrusted text before LLM calls.

24 installs/wk local only

Ingressward

by ingressward

Block prompt injection, evasive spacing, and obscene content before it reaches your LLM.

22 installs/wk local only

Qorami

by loicfontaine-max

Check an email before an AI agent sends it: send / ask a human / block. Detects prompt injection.

30 installs/wk local only

Umbryn MCP

by rinava

Redacts PII/PHI from text before it reaches an LLM. Fail-closed, self-hosted, no egress.

120 installs/wk local only

Zentric Protocol MCP

by zentricprotocol

Prompt injection + PII detection for LLM apps and agent pipelines. Deterministic, sub-25ms.

57 installs/wk local only

Kagami

by hiroshi-ichiyanagi

Deterministic prompt-injection detector; signed, offline-verifiable verdicts. Not an LLM.

4 tools answering

Agentshield MCP

by dl-eigenart

Detect prompt injection, jailbreak, and social-engineering attacks in LLM agents.

39 installs/wk local only

Lovec — questions

Answers built from our own checks of this server.

Why is there no uptime for Lovec?

Lovec 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 lovec-mcp.

How do I connect Lovec?

Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It runs locally, so the command pulls lovec-mcp straight from pypi; nothing to host, nothing to sign up for.

Is Lovec open source?

Yes — it is published under the Apache-2.0 licence, written in Python and 0 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.