SafetyChain MCP by usefulapi
RemoteAbout SafetyChain MCP by usefulapi
SafetyChain MCP by usefulapi is a read-only MCP server for teams working with SafetyChain food safety data. It provides tools to retrieve records across CAPAs, forms, suppliers, items, locations, and equipment.
Key features
- 01Search and retrieve records
- 02Read CAPAs and related activity
- 03Access forms and categories
- 04Browse suppliers, items, and customers
- 05Retrieve locations and equipment
Use cases
- 01Review CAPA tasks and history
- 02Look up food safety records
- 03Check supplier and item details
MCP support
Exposes read-only SafetyChain data retrieval tools to MCP clients. It connects through a remote endpoint and uses OAuth sign-in for SafetyChain credentials.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://safetychain.usefulapi.io/mcpclaude mcp add --transport http io-usefulapi-safetychain https://safetychain.usefulapi.io/mcp{"mcpServers":{"io-usefulapi-safetychain":{"type":"http","url":"https://safetychain.usefulapi.io/mcp"}}}Open in Cursor{"servers":{"io-usefulapi-safetychain":{"type":"http","url":"https://safetychain.usefulapi.io/mcp"}}}Open in VS Code{"mcpServers":{"io-usefulapi-safetychain":{"type":"http","url":"https://safetychain.usefulapi.io/mcp"}}}{"mcpServers":{"io-usefulapi-safetychain":{"serverUrl":"https://safetychain.usefulapi.io/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
Details
From the project READMESafetyChain MCP by usefulapi
Live endpoint: https://safetychain.usefulapi.io/mcp
Connect
- Claude (claude.ai, Desktop): open Customize → Connectors, click + Add → Add custom connector, and paste
https://safetychain.usefulapi.io/mcp. - Claude Code:
claude mcp add --transport http safetychain https://safetychain.usefulapi.io/mcp, then run/mcpto log in. - VS Code: Add to VS Code.
- Cursor and other clients: add the URL as a remote MCP server:
{
"mcpServers": {
"safetychain": {
"url": "https://safetychain.usefulapi.io/mcp"
}
}
}
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, and the login page asks for your SafetyChain credentials.
Step-by-step setup, where to find your credentials, and FAQ: https://usefulapi.io/safetychain/
On first connect you will enter your SafetyChain tenant (the part before .safetychain.com), the username and password of a SafetyChain integration user, and the environment (Production or Train). They are validated, stored per-user, and scoped to you. No keys in config files. This server is read-only.
Tools
| Tool | Type | What it does |
|---|---|---|
safetychain_list_customers | read | List customers |
safetychain_get_customer | read | Get customer |
safetychain_list_locations | read | List locations |
safetychain_get_location | read | Get location |
safetychain_list_suppliers | read | List suppliers |
safetychain_get_supplier | read | Get supplier |
safetychain_list_items | read | List items |
safetychain_get_item | read | Get item |
safetychain_list_equipment | read | List equipment |
safetychain_get_equipment | read | Get equipment |
safetychain_list_resources | read | List resources |
safetychain_get_resource | read | Get resource |
safetychain_list_forms | read | List forms |
safetychain_get_form | read | Get form |
safetychain_list_categories | read | List categories |
safetychain_get_category | read | Get category |
safetychain_search_capas | read | Search CAPAs |
safetychain_get_capa | read | Get CAPA |
safetychain_get_capa_tasks | read | Get CAPA tasks |
safetychain_get_capa_attachments | read | Get CAPA attachments |
safetychain_get_capa_history | read | Get CAPA history |
safetychain_get_capa_linked_records | read | Get CAPA linked records |
safetychain_get_capa_linked_capas | read | Get CAPA linked capas |
safetychain_get_capa_activity | read | Get CAPA activity |
safetychain_get_record | read | Get record |
safetychain_record_exists | read | Check a record exists |
safetychain_search_records | read | Search records |
safetychain_get_record_fields | read | Get record field values |
safetychain_get_record_summary | read | Summarize records |
safetychain_usage_status | meta | Usage status (free-tier meter) |
safetychain_request_feature | meta | Request a missing feature |
safetychain_upgrade | meta | Upgrade to Pro (unlimited*) |
safetychain_cancel_subscription | meta | Cancel the Pro subscription |
read tools are read-only; write tools mutate data (clients should confirm them); meta tools report usage, manage your subscription or send a feature request.
Pricing
| Plan | Price | Limit |
|---|---|---|
| Free | $0 | 50 tool calls / month |
| Pro (per account) | $9/mo or $90/yr (2 months free) | Unlimited* |
*Pro has a fair use limit of 10,000 tool calls a month on this server. For more, write to [email protected].
Pro covers this server only. Subscribe with safetychain_upgrade (it returns a Stripe Checkout link). Cancel any time with safetychain_cancel_subscription: Pro continues to the end of the paid period, with no refund for the current period, and running safetychain_upgrade before then undoes the cancel. Or write to [email protected].
License
MIT
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.