Read SafetyChain food safety records, CAPAs, forms, suppliers, items, locations and equipment. Hosted by usefulapi: connect it to Claude, ChatGPT, Cursor or any MCP client.
Turn on the SafetyChain connector, then ask in plain words. The AI picks the tools.
For food and beverage manufacturers that run their food safety and quality programs in SafetyChain.
The AI searches the records submitted in a date range for non-compliant ones, filtered by form, location or resource, and reads the field values of a record with each field's compliance result.
The AI searches corrective and preventive actions by status, location or severity, and for one CAPA shows its details, due dates and tasks with their assignees.
The AI finds the records that carry an identifier such as a lot number and reads their field values: value, unit, target, minimum, maximum and compliance.
The AI summarizes the records of a date range: the first and last date, and how many forms, locations, resources and users are involved.
The AI lists the suppliers, items and forms of the tenant by name, with ids and enabled flags, and opens one for its details.
The AI reads a CAPA's history, its comments and events, and the records linked to it, to explain how the action developed.
The login page asks for your Tenant, Integration user's username, Integration user's password and Environment.
Create a dedicated user for this connection in SafetyChain: System Management → Roles (a role with the Access to Integration API Scope permission), then add a user with that role and tick Disable Password Expiration Policy. The tenant is the part before .safetychain.com in your address (acme.safetychain.com → acme). That permission lets the user read all records and resources, so every record the integration user can see is visible to your AI assistant. The password is used only to sign in to the SafetyChain API on your behalf (SafetyChain issues 5-minute access tokens) and is never shown to anyone. If you change the password you must reconnect, and SafetyChain locks an account after 10 failed sign-ins.
Team and Enterprise: an Owner adds the connector for the organization first.
No Add custom MCP server option? It depends on your account or workspace settings: see OpenAI's guide.
Run this command, then run /mcp in Claude Code to log in:
Add to Cursor or add this to ~/.cursor/mcp.json:
{
"mcpServers": {
"safetychain": {
"url": "https://safetychain.usefulapi.io/mcp"
}
}
} Add to VS Code or add this to .vscode/mcp.json:
{
"servers": {
"safetychain": {
"type": "http",
"url": "https://safetychain.usefulapi.io/mcp"
}
}
} Run these commands. The second one opens the login page:
Windsurf, Cline, Zed and other MCP clients: add this URL as a remote MCP server (Streamable HTTP). The client then opens the login page in your browser.
Add only the URL. Do not add an Authorization header or an API key to the client config. The server signs you in with OAuth: the login page asks for your Tenant, Integration user's username, Integration user's password and Environment. If the config has such a header, remove it: some clients then send that header instead of the login token, and every call fails with 401.
| Plan | Price | Limit |
|---|---|---|
| Free | $0 | 50 tool calls / month |
| Proper account | $9/mo · $90/yr | 10,000 tool calls / month |
| Pro+per account | $39/mo · $390/yr | 100,000 tool calls / month |
Each paid plan covers this SafetyChain server only. Ask your AI to run safetychain_upgrade and choose Pro or Pro+, billed monthly or yearly (it returns a Stripe Checkout link). If you already have Pro, ask to change it to Pro+. The change requires your confirmation, keeps your billing interval and charges the price difference for the rest of the period immediately. Cancel any time with safetychain_cancel_subscription: your paid plan continues to the end of the paid period, with no refund for the current period, and asking to resume the same plan with safetychain_upgrade before then undoes the cancel. Or write to [email protected].
safetychain_list_customerssafetychain_get_customersafetychain_list_locationssafetychain_get_locationsafetychain_list_supplierssafetychain_get_suppliersafetychain_list_itemssafetychain_get_itemsafetychain_list_equipmentsafetychain_get_equipmentsafetychain_list_resourcessafetychain_get_resourcesafetychain_list_formssafetychain_get_formsafetychain_list_categoriessafetychain_get_categorysafetychain_search_capassafetychain_get_capasafetychain_get_capa_taskssafetychain_get_capa_attachmentssafetychain_get_capa_historysafetychain_get_capa_linked_recordssafetychain_get_capa_linked_capassafetychain_get_capa_activitysafetychain_get_recordsafetychain_record_existssafetychain_search_recordssafetychain_get_record_fieldssafetychain_get_record_summarysafetychain_usage_statussafetychain_request_featuresafetychain_upgradesafetychain_cancel_subscriptionFind non-compliant records. Review open CAPAs and their tasks. Trace what operators entered for a lot. Size a period's record activity. Look up suppliers, items and forms. Follow a CAPA's history and linked records. See what you can do for the details.
No. usefulapi is an independent service. It is not affiliated with or endorsed by SafetyChain. The server calls the SafetyChain API with your own SafetyChain access, so it sees only the data that your account can see.
Yes. In Claude, add this server's URL as a custom connector. In ChatGPT, add it as a custom MCP server in Plugins. Then log in once. Cursor, VS Code, Claude Code and Codex work too. See the setup steps.
The login page asks for your Tenant, Integration user's username, Integration user's password and Environment. See Before you connect for where to find them.
No. Add only the URL. Do not add an Authorization header or an API key to the client config. The server signs you in with OAuth: the login page asks for your Tenant, Integration user's username, Integration user's password and Environment. If the config has such a header, remove it: some clients then send that header instead of the login token, and every call fails with 401.
The login stores them encrypted in the authorization grant of your connection. The server uses them to call the SafetyChain API for you and to derive a private account id for usage metering. usefulapi does not show them on any page or in any reply. To stop all access, remove the connector and change or delete these credentials in SafetyChain.
All 29 SafetyChain tools are marked read-only.
The Free plan gives 50 tool calls / month. Pro costs $9/mo or $90/yr, with 10,000 tool calls / month. Pro+ costs $39/mo or $390/yr, with 100,000 tool calls / month. Each subscription covers this SafetyChain server only. Cancel any time: your paid plan then runs to the end of the paid period. Run safetychain_usage_status to see how many calls you used.
Ask the AI to run safetychain_upgrade and choose Pro or Pro+, billed monthly or yearly: it returns a Stripe Checkout link. If you already have Pro, ask to change it to Pro+. After you confirm, your existing subscription changes in place, keeps its billing interval and charges the price difference for the rest of the period immediately. To cancel, run safetychain_cancel_subscription. Your paid plan continues to the end of the paid period.
Tell the AI what you wanted to do. It can send the request with safetychain_request_feature. We store the text with the server name, the type of AI client and the tool you tried, not with your account, and read every request when we plan new tools. You can send up to 5 requests per day.
Any client that supports remote MCP servers (Streamable HTTP) with OAuth login: Claude (web and desktop), Claude Code, ChatGPT, Codex, Cursor, VS Code, Windsurf and others.
This is a Model Context Protocol endpoint — meant to be connected from an AI client, not opened in a browser. An invalid_token response at the URL is the auth gate working as designed; clients authenticate automatically.
Need a tool this server does not have, or a connection to another system? We build custom integrations and MCP servers.