# Lovec (pypi · lovec-mcp)

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

- Trust score: 66/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-21

## Components

- pypi · `lovec-mcp`: 66/100 (this document), [markdown](https://verifymcp.io/servers/lovec-tech-lovec-mcp/lovec-mcp.md), [page](https://verifymcp.io/servers/lovec-tech-lovec-mcp/lovec-mcp)

## Channel facts

- Registry: `pypi`
- Package: `lovec-mcp`
- Version: `0.1.2`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-09-21.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs setuptools.build_meta at install time, a recognised native-build step with no shell scripting around it.
  - 1 of 32 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 32/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - License check failed: no license is declared.
  - Actively maintained (last published 3 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 80/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 201 tokens (~201/item across 1 items; 1 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 71/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 1 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 1 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### How do I install the Lovec MCP server?

Lovec runs locally as a PyPI package, launched with uvx lovec-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add lovec-tech-lovec-mcp -- uvx lovec-mcp
```

### Cursor

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

### VS Code

```json
{
  "servers": {
    "lovec-tech-lovec-mcp": {
      "command": "uvx",
      "args": [
        "lovec-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add lovec-tech-lovec-mcp -- uvx lovec-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "lovec-tech-lovec-mcp": {
      "type": "local",
      "command": [
        "uvx",
        "lovec-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add lovec-tech-lovec-mcp --command uvx --arg lovec-mcp
```

### Hermes

```yaml
mcp_servers:
  lovec-tech-lovec-mcp:
    command: "uvx"
    args: ["lovec-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "lovec-tech-lovec-mcp": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "lovec-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add lovec-tech-lovec-mcp -t stdio -c uvx -a lovec-mcp
```

### Other

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

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-09-21 (score 66, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-09-17 (score 51)

First indexed and scored.

## MCP tools (1)

### `check_prompt_injection` (~201 tokens)

Check a piece of untrusted text for prompt-injection risk.

Call this on any content that will be handed to another LLM but did not
come directly from the trusted user — a web page, a document, a tool
result, an email, a review. It does NOT enforce authorization/RBAC and
is not a jailbreak filter for the user's own messages.

The text is sent to the lovec.tech API for analysis — it is not kept
purely local. Each call spends one request against this key's balance.

Score is bimodal in practice (clusters near 0 or 1); treat mid-range scores
as low-confidence rather than as a precise probability. The detector is known
to false-positive on long, evaluative/opinionated text (reviews, argumentative
prose) more than on short factual text — factor that in before hard-blocking
on is_injection alone.

Input parameters:

- `text` (string, required)

Output parameters:

- `is_injection` (boolean)
- `lang_tag`
- `score` (number)
- `version`

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/lovec-tech-lovec-mcp/lovec-mcp#diagnostics

## Score history

- 2026-09-21: 66
- 2026-09-20: 51
- 2026-09-19: 51
- 2026-09-18: 51
- 2026-09-17: 51

## Common questions

### What is the Lovec MCP server?

Lovec is an MCP server listed in the public MCP registry as io.github.lovec-tech/lovec-mcp. Prompt-injection detector for untrusted text before it reaches an LLM (RU/EN). BYO lovec.tech key. This page covers its PyPI package (lovec-mcp).

### Is the Lovec MCP server safe to use?

Lovec scores 66 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 September 2026. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Lovec MCP server expose?

Lovec exposes 1 tool: check_prompt_injection. Their descriptions and schemas cost roughly 201 tokens of context every time the server is loaded.

### Is the Lovec MCP server still maintained?

Lovec is still listed as active in the MCP registry. We last reached this channel on 21 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- PyPI project: https://pypi.org/project/lovec-mcp/
- Socket report: https://socket.dev/pypi/package/lovec-mcp
- Repository: https://github.com/lovec-tech/lovec-mcp
- Website: https://lovec.tech/
- Changelog RSS feed: https://verifymcp.io/servers/lovec-tech-lovec-mcp/lovec-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/lovec-tech-lovec-mcp/lovec-mcp.json
- HTML version of this page: https://verifymcp.io/servers/lovec-tech-lovec-mcp/lovec-mcp