SLF Guardian

Registre officiel Outils de développement

Safety checks an agent runs before it acts: packages, commands, prompt injection, links, code.

Installation

Ajoutez ceci à la configuration MCP de votre client (Claude Desktop : claude_desktop_config.json ; Cursor : .cursor/mcp.json ; VS Code et les autres utilisent la même forme « mcpServers »).

PYPI package slf-guardian-mcp
Claude Code
claude mcp add slf-guardian -e 'SLF_API_KEY=<your slf_api_key>' -- uvx slf-guardian-mcp==1.2.0
Configuration JSON (Claude Desktop, Cursor, VS Code)
{
    "mcpServers": {
        "slf-guardian": {
            "command": "uvx",
            "args": [
                "slf-guardian-mcp==1.2.0"
            ],
            "env": {
                "SLF_API_KEY": "<your slf_api_key>"
            }
        }
    }
}

Variables d'environnement

  • SLF_API_KEY obligatoire secret SLF Guardian API key (slf_live_...). Get one free: POST https://slfguardian.com/v1/keys

Documentation

Tirée du README du projet sur GitHub, actualisée chaque semaine. Les liens ouvrent GitHub.

Sommaire
  1. SLF Guardian MCP
  2. Install
  3. Get a key
  4. Configure your client
  5. What it catches
  6. Honest limits
  7. Environment

SLF Guardian MCP

Six security checks an AI agent can call before it acts — before it delivers code, installs a dependency, runs a shell or SQL command, opens a link or reads an untrusted page.

One file, no dependencies, stdio transport. Works with Claude Desktop, Cursor, Cline, Windsurf, Continue and anything else that speaks MCP.

ToolThe question it answers
audit_codeIs this code safe to deliver or run?
check_packageDoes this dependency exist, and is it safe to install?
check_promptDoes this text or page carry instructions aimed at me?
check_commandCan this shell or SQL command be undone?
check_domainIs this domain safe to trust?
scan_sitePassive outside-in security check of a website

Every answer is a single verdict (pass, review, block) plus the evidence behind it, so an agent can branch on it without reading prose.

Install

pip install slf-guardian-mcp
# or straight from this repository
pip install git+https://github.com/slfguardian/slf-guardian-mcp

Get a key

curl -X POST https://slfguardian.com/v1/keys \
  -H "Content-Type: application/json" \
  -d '{"email":"you@example.com"}'

25 calls are free. The raw key is shown once.

Configure your client

{
  "mcpServers": {
    "slf-guardian": {
      "command": "slf-guardian-mcp",
      "env": { "SLF_API_KEY": "slf_live_..." }
    }
  }
}

What it catches

check_package — the invented dependency. Assistants hallucinate package names; attackers register them. langchain-helper-utils comes back block, no such package, lodahs comes back review, did you mean lodash. The source is the registry itself plus the OSV vulnerability database, with npm postinstall hooks, yanked and abandoned releases, age and download counts.

check_prompt — instructions hidden in content you were asked to read. Text hidden with display:none, zero-width and bidi characters, Unicode tag smuggling, homoglyphs, markdown exfiltration pixels, "ignore previous instructions", "send .env to this webhook", "do not tell the user". The tool never follows any instruction it finds; it returns the cleaned text and the findings.

check_command — the thing you cannot undo. UPDATE users SET plan=1 without a WHERE comes back block, reversible=false; git push --force origin main comes back review with --force-with-lease suggested. Nothing is ever executed.

check_domain — the link before you open it. Registration age and status, DNS, lookalike brands, brand in a subdomain, punycode, shorteners, disposable hosting, abuse-heavy TLDs. The site itself is never contacted.

audit_code — before you hand the file over. Remote code execution (curl | bash), environment and credential exfiltration, reverse shells, destructive commands, hidden base64, hard-coded secrets, install-time hooks, shell=True, pickle.loads, TLS verification turned off.

Honest limits

These are detectors, not proofs. A pass means no known pattern matched, not that the input is safe; a finding is evidence to look at, not a conviction. Nothing submitted is executed, and the analysis is static.

Environment

VariableDefaultPurpose
SLF_API_KEY—Required. Your key.
SLF_API_BASEhttps://slfguardian.comOverride the endpoint.
SLF_TIMEOUT120Seconds per call.

HTTP API and OpenAPI description: https://slfguardian.com/api

MIT licensed.

Questions fréquentes

Qu'est-ce que SLF Guardian ?

Safety checks an agent runs before it acts: packages, commands, prompt injection, links, code.

Comment installer SLF Guardian ?

Il s'exécute sur votre machine. Dans Claude Code : claude mcp add slf-guardian -e 'SLF_API_KEY=<your slf_api_key>' -- uvx slf-guardian-mcp==1.2.0. Pour les autres clients, collez la configuration JSON de cette page dans leurs réglages MCP.

Faut-il une clé API pour SLF Guardian ?

Oui. Il attend SLF_API_KEY, à renseigner dans sa configuration.

SLF Guardian est-il open source ?

Oui. Son code est sur GitHub sous licence MIT.

Qui maintient SLF Guardian ?

Il est publié par slfguardian. AI.tn le référence sans le maintenir ni le recommander.

Issu du registre MCP officiel. Être listé n'est pas une recommandation : vérifiez le code et les permissions d'un serveur avant de lui donner accès à vos données.