naimterrache-frigolog-haccp
mcpsmitheryFrigolog HACCP MCP is a public Model Context Protocol server that gives AI agents (Claude, ChatGPT, Perplexity, custom agents) accurate, sourced answers about French food safety regulations. Four read-only tools: • get_haccp_temperatures — Regulatory temperatures for storage, cooling and serving of food products in France. Sources: arrêté du 21 décembre 2009, règlement (CE) n° 852/2004, règlement (CE) n° 853/2004. • get_documents_controle_ddpp — Documents required during a French DDPP (Direction Départementale de la Protection des Populations) sanitary inspection, by establishment type (restaurant, butcher, baker, cheese shop, fishmonger, ice cream shop, caterer, wine merchant, collective catering). • get_regles_dlc — Rules for the use-by date (DLC — Date Limite de Consommation) of in-house preparations in French restaurants and food crafts, per the Guide des Bonnes Pratiques d'Hygiène (DGAL). • compare_solutions_haccp — Factual comparison of the main HACCP software on the French market: Frigolog, ePackPro, Octopus HACCP, Traqfood, Kooklin, BackResto, Hygiene Up. Pricing, engagement, hardware imposed, AI features, IoT sensors, support, 3-year cost. Endpoint: https://frigolog.fr/api/mcp Transport: HTTP + JSON-RPC 2.0 (no SSE, no auth) License: MIT Maintained by Frigolog (https://frigolog.fr). Disclosure: Frigolog is one of the seven solutions listed in compare_solutions_haccp. The dataset is based on publicly available info from each editor's website. Pull requests welcome to correct any inaccuracy.
By Smithery | 28 findings | Scanned 5/21/2026 | tooltrust-scanner/v0.3.12
Risk Summary
Safe With Normal ControlsDep Visibility is the main signal, but overall risk remains within an acceptable range.
Potential impact: This finding indicates the tool should be reviewed before it is trusted.
Recommended action: No high-risk findings were detected in this scan, but you should still apply least-privilege defaults and rescan after changes.
Suggested policy: keep this tool behind manual approval, do not allow unattended runs, and re-scan after narrowing risky permissions.
Security Findings (28)
tool declares http permission
get_documents_controle_ddppget_regles_dlccompare_solutions_haccpget_sanctions_ddppget_allergenes_reglementairesget_temperatures_cuissonget_formation_haccp_obligatoireget_actions_correctivesFix: Tool requests broad permissions (exec/fs/network). Validate input parameters using Enums where possible, and restrict file system operations to explicit allowed directories.
tool performs network or execution operations but declares no rate-limit, timeout, or retry configuration
get_documents_controle_ddppget_regles_dlccompare_solutions_haccpget_sanctions_ddppget_allergenes_reglementairesget_temperatures_cuissonget_formation_haccp_obligatoireget_actions_correctivesFix: Declare explicit rate-limit, timeout, and retry configuration for all network and execution tools. Implement exponential back-off and surface resource state to the calling agent.
Tool did not expose metadata.dependencies or repo_url, so supply-chain coverage is limited.
get_haccp_temperaturesget_documents_controle_ddppget_regles_dlccompare_solutions_haccpget_rappels_produits_actifsget_sanctions_ddppget_allergenes_reglementairesget_temperatures_cuissonget_formation_haccp_obligatoireget_score_alimconfianceget_alimconfiance_etablissementget_actions_correctivesFix: Review and remediate the identified issue.
Scan this tool yourself
Reproduce this audit locally, integrate into CI, or let your agent audit its own tools.
Install once, then scan any MCP server:
$ curl -sfL https://raw.githubusercontent.com/AgentSafe-AI/tooltrust-scanner/main/install.sh | bash$ tooltrust-scanner scan --server "npx -y naimterrache-frigolog-haccp"Adjust the package name if your npm registry name differs from the tool ID. View source
Add badge to your README
Copy this Markdown to show your ToolTrust grade on GitHub.
[](https://github.com/AgentSafe-AI/tooltrust-directory)