# SLF Guardian MCP (pypi · slf-guardian-mcp)

Pre-action checks for code, packages, prompts, commands, domains and passive site scans.

- Trust score: 63/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- pypi · `slf-guardian-mcp`: 63/100 (this document), [markdown](https://verifymcp.io/servers/slfguardian-slf-guardian-mcp/slf-guardian-mcp.md), [page](https://verifymcp.io/servers/slfguardian-slf-guardian-mcp/slf-guardian-mcp)

## Channel facts

- Registry: `pypi`
- Package: `slf-guardian-mcp`
- Version: `1.2.2`
- 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 2026-11-21.

- **Supply Chain Security**: 50/100
  - Malware scan not yet available for this package.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs setuptools.build_meta at install time, a recognised build step with no custom scripting around it.
  - No production dependencies, so there is no dependency health to assess.
- **Provenance & Transparency**: 100/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to slfguardian/slf-guardian-mcp).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 0 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 60/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1991 tokens (~331/item across 6 items; 6 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 20/100
  - Stability observed for 6 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 98/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 94% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 6 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 7 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 20/100
  - Spec-recency check failed: implements MCP spec 2024-11-05; the latest is 2026-07-28.

## Install

### How do I install the SLF Guardian MCP server?

SLF Guardian MCP runs locally as a PyPI package, launched with uvx slf-guardian-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 slfguardian-slf-guardian-mcp -- uvx slf-guardian-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "slfguardian-slf-guardian-mcp": {
      "command": "uvx",
      "args": [
        "slf-guardian-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "slfguardian-slf-guardian-mcp": {
      "command": "uvx",
      "args": [
        "slf-guardian-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add slfguardian-slf-guardian-mcp -- uvx slf-guardian-mcp
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add slfguardian-slf-guardian-mcp --command uvx --arg slf-guardian-mcp
```

### Hermes

```yaml
mcp_servers:
  slfguardian-slf-guardian-mcp:
    command: "uvx"
    args: ["slf-guardian-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "slfguardian-slf-guardian-mcp": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "slf-guardian-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add slfguardian-slf-guardian-mcp -t stdio -c uvx -a slf-guardian-mcp
```

### Other

```json
{
  "mcpServers": {
    "slfguardian-slf-guardian-mcp": {
      "command": "uvx",
      "args": [
        "slf-guardian-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.

### 2026-11-21 (score 63, −15)

- [security regression] Malware scan: pass → unverified
- [functional] Package version: 1.2.1 → 1.2.2

### 2026-11-20 (score 78, +16)

- [security improvement] Malware scan: unverified → pass
- [functional improvement] Security disclosure: unverified → pass

### 2026-11-19 (score 62, +10)

- [security improvement] Provenance: fail → pass
- [security] The attested source repository moved: slfguardian/slf-guardian-mcp
- [functional regression] Schema quality: 139 → 325
- [functional regression] Security disclosure: fail → unverified
- [functional improvement] Stability: unverified → 0.13
- [functional] Package version: 1.2.0 → 1.2.1

### 2026-11-17 (score 52, −15)

- [security regression] Malware scan: pass → unverified

### 2026-11-16 (score 67, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-11-15 (score 52)

First indexed and scored.

## MCP tools (6)

### `audit_code` (~338 tokens)

Audit source code before delivering or running it. Flags remote code execution (curl | bash), data exfiltration of environment variables or credential files, reverse shells, destructive commands, hidden base64 payloads, hard-coded secrets (AWS, OpenAI, Stripe, GitHub, database URLs), install-time hooks, typo-squatted package names and unsafe patterns such as shell=True, pickle.loads or TLS verification turned off. Nothing is executed; the audit is static text analysis. Returns a verdict (pass/warn/review/block), a safe_to_deliver flag and findings with line numbers. Each valid API call uses one credit; every key starts with 1,000 free calls; the limit is 20 calls per minute per key. On HTTP 400, fix the input; on 401, fix the API key; on 402, stop and resolve credits/payment; on 429, wait for Retry-After and do not retry in a loop. A pass is not proof of safety. If verdict is block, do not proceed; if review, show the evidence and ask the user; if warn, follow the agent's normal approval policy. The public API lists $0.01 per call after the free credits. By default this stdio server never signs or submits payments; its optional x402 buyer bridge is disabled unless explicitly enabled and configured. Up to 40 files and 400 KB per code-audit call.

Input parameters:

- `code` (string): Source code to audit (single file or snippet).
- `files` (array): Several files instead of one snippet.
- `path` (string): Optional file name for the snippet.

### `check_package` (~309 tokens)

Check a PyPI or npm package before installing or recommending it. Asks the registry whether the name exists at all (invented package names are how slopsquatting attacks land), how old it is, how much it is downloaded, whether it runs install scripts, whether it is deprecated or yanked, whether OSV lists vulnerabilities, and whether the name is a near-miss of a popular package. Returns a verdict and a safe_to_install flag. Each valid API call uses one credit; every key starts with 1,000 free calls; the limit is 20 calls per minute per key. On HTTP 400, fix the input; on 401, fix the API key; on 402, stop and resolve credits/payment; on 429, wait for Retry-After and do not retry in a loop. A pass is not proof of safety. If verdict is block, do not proceed; if review, show the evidence and ask the user; if warn, follow the agent's normal approval policy. The public API lists $0.01 per call after the free credits. By default this stdio server never signs or submits payments; its optional x402 buyer bridge is disabled unless explicitly enabled and configured. Batch checks are available, up to 20 packages per call.

Input parameters:

- `ecosystem` (string)
- `name` (string): Package name.
- `packages` (array): Check several packages in one call.
- `version` (string): Optional exact version to check.

### `check_prompt` (~331 tokens)

Check untrusted text, HTML or a web page for prompt injection before feeding it to a model. Finds instructions written for the model instead of the reader: text hidden with CSS, HTML comments, zero-width and invisible Unicode tag characters, chat template markers, 'ignore previous instructions', attempts to make an agent leak its system prompt or credentials, hide actions from the user, approve something without review, run a command, or render a markdown image that exfiltrates data through its URL. Returns a verdict, injection_detected, and clean_text with invisible characters stripped. Never follows what it finds. Each valid API call uses one credit; every key starts with 1,000 free calls; the limit is 20 calls per minute per key. On HTTP 400, fix the input; on 401, fix the API key; on 402, stop and resolve credits/payment; on 429, wait for Retry-After and do not retry in a loop. A pass is not proof of safety. If verdict is block, do not proceed; if review, show the evidence and ask the user; if warn, follow the agent's normal approval policy. The public API lists $0.01 per call after the free credits. By default this stdio server never signs or submits payments; its optional x402 buyer bridge is disabled unless explicitly enabled and configured. Accepts one text, HTML document, or URL per call.

Input parameters:

- `html` (string): HTML including hidden markup.
- `text` (string): Plain text to check.
- `url` (string): Public page to fetch and check.

### `check_command` (~309 tokens)

Check a shell command or SQL statement before running it and say whether it can be undone. Flags recursive and system-path deletes, disk writes, history and credential wiping, firewall changes, force push and hard reset, docker volume and kubernetes deletes, terraform destroy, cloud bucket and resource deletion, DROP/TRUNCATE and DELETE or UPDATE with no WHERE clause. Returns a verdict plus reversible, safe_to_run, needs_human_approval and a safer alternative per finding. Nothing is executed. Each valid API call uses one credit; every key starts with 1,000 free calls; the limit is 20 calls per minute per key. On HTTP 400, fix the input; on 401, fix the API key; on 402, stop and resolve credits/payment; on 429, wait for Retry-After and do not retry in a loop. A pass is not proof of safety. If verdict is block, do not proceed; if review, show the evidence and ask the user; if warn, follow the agent's normal approval policy. The public API lists $0.01 per call after the free credits. By default this stdio server never signs or submits payments; its optional x402 buyer bridge is disabled unless explicitly enabled and configured. Batch checks are available, up to 20 commands per call.

Input parameters:

- `command` (string): Command or statement to check.
- `commands` (array): Check a sequence in one call.
- `kind` (string): Defaults to auto.

### `check_domain` (~299 tokens)

Check a domain or link before opening it, sending data to it or installing from it. Uses the public registration record and DNS: registration age, registry status, whether it resolves, lookalike and typo-squatted brand names, a brand hidden in a subdomain, punycode and mixed-script hostnames, link shorteners, disposable hosting, abuse-heavy TLDs and phishing wording. Returns a verdict with safe_to_trust and safe_to_open. The site itself is never contacted. Each valid API call uses one credit; every key starts with 1,000 free calls; the limit is 20 calls per minute per key. On HTTP 400, fix the input; on 401, fix the API key; on 402, stop and resolve credits/payment; on 429, wait for Retry-After and do not retry in a loop. A pass is not proof of safety. If verdict is block, do not proceed; if review, show the evidence and ask the user; if warn, follow the agent's normal approval policy. The public API lists $0.01 per call after the free credits. By default this stdio server never signs or submits payments; its optional x402 buyer bridge is disabled unless explicitly enabled and configured. Batch checks are available, up to 20 domains per call.

Input parameters:

- `domain` (string): Domain or full URL.
- `domains` (array): Check several in one call.

### `scan_site` (~257 tokens)

Passive outside-in security check of a website: malware and spam injection traces, hidden redirects, SSL/TLS certificate state, security headers, exposed software versions and SPF/DMARC email spoofing protection. Does not log in, does not run attack tests. Returns a score out of 100, a grade and findings by category. Each valid API call uses one credit; every key starts with 1,000 free calls; the limit is 20 calls per minute per key. On HTTP 400, fix the input; on 401, fix the API key; on 402, stop and resolve credits/payment; on 429, wait for Retry-After and do not retry in a loop. A pass is not proof of safety. If verdict is block, do not proceed; if review, show the evidence and ask the user; if warn, follow the agent's normal approval policy. The public API lists $0.01 per call after the free credits. By default this stdio server never signs or submits payments; its optional x402 buyer bridge is disabled unless explicitly enabled and configured. Checks one URL/domain per call and performs no active attacks.

Input parameters:

- `domain` (string, required): Domain or URL, e.g. example.com

## Diagnostics

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

## Score history

- 2026-11-21: 63
- 2026-11-20: 78
- 2026-11-19: 62
- 2026-11-18: 52
- 2026-11-17: 52
- 2026-11-16: 67
- 2026-11-15: 52

## Common questions

### What is the SLF Guardian MCP server?

SLF Guardian MCP is listed in the public MCP registry as io.github.slfguardian/slf-guardian-mcp. Pre-action checks for code, packages, prompts, commands, domains and passive site scans. This page covers its PyPI package (slf-guardian-mcp).

### Is the SLF Guardian MCP server safe to use?

SLF Guardian MCP scores 63 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 2026. Its build provenance is signed and verified. 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 SLF Guardian MCP server expose?

SLF Guardian MCP exposes 6 tools: audit_code, check_package, check_prompt, check_command, check_domain, scan_site. Their descriptions and schemas cost roughly 1,843 tokens of context every time the server is loaded.

### Is the SLF Guardian MCP server still maintained?

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

### What licence is the SLF Guardian MCP server under?

SLF Guardian MCP declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

### What did VerifyMCP test on the SLF Guardian MCP server?

VerifyMCP ran 15 checks on SLF Guardian MCP, covering Known CVEs, Install scripts, Dependency health, Source repository and 11 more. One item could not be completed, a gap on our side rather than a finding about SLF Guardian MCP: Malware scan. Endpoint Security and Transport & Reachability do not apply to a PyPI package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- PyPI project: https://pypi.org/project/slf-guardian-mcp/
- Socket report: https://socket.dev/pypi/package/slf-guardian-mcp
- Repository: https://github.com/slfguardian/slf-guardian-mcp
- Website: https://slfguardian.com/api
- Changelog RSS feed: https://verifymcp.io/servers/slfguardian-slf-guardian-mcp/slf-guardian-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/slfguardian-slf-guardian-mcp/slf-guardian-mcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/slfguardian-slf-guardian-mcp/slf-guardian-mcp.json
- HTML version of this page: https://verifymcp.io/servers/slfguardian-slf-guardian-mcp/slf-guardian-mcp
