SafetyChain MCP
Access food safety records, corrective actions, forms, suppliers and equipment from SafetyChain
Read-only access to SafetyChain food safety management data including compliance records, corrective and preventive actions (CAPAs), forms, locations, suppliers, items and equipment. Search and retrieve detailed records with field values and verification status.
Try asking Muse: "Show me all open corrective actions from the past month at our main facility"
See the most upvoted connectors
Source: Found in the official MCP Registry (io.usefulapi/safetychain) · First listed October 30, 2026
Last 24 hours
Each bar is one check, every 15 minutes. Green means it answered. Last checked 2 h ago.
Is it safe to connect?
What Muse can see: It does not ask you to sign in, so it cannot see your accounts. It only sees what Muse sends it from your request.
Before it acts: Read what Muse plans to do before you approve it, and remove the app from Muse when you stop using it.
musedirectory.ai is not part of Meta. More about how Muse handles your information
How to add it to Muse
Not in Muse's Connectors list yet, but Muse can still use it. Copy the request below and paste it into Muse. Muse asks before it shares anything with the app's site. Meta does not review apps used this way, so only use ones you trust. We tested this in the Muse app on September 24, 2026: Muse used an app's link directly this way and returned a live answer.
https://safetychain.usefulapi.io/mcpNot in Muse's Connectors list yet. Muse can still use it: its page gives you a request to paste into Muse.
Also use it in ChatGPT or Claude
SafetyChain MCP is a remote MCP server, so any assistant that can add a custom connector by link can use it. Same link, same tools.
Add it to ChatGPT
- 1
Open ChatGPT settings
In ChatGPT, open Settings, then Connectors (called Apps & Connectors on some accounts).
- 2
Turn on developer mode
Under Advanced settings, switch on Developer mode. That is what lets you add a connector by link.
- 3
Create the connector
Choose Create, give it a name, paste the link as the MCP server URL, and save. If it needs a sign-in, ChatGPT asks for it here.
- 4
Use it in a chat
Start a chat, open the tools menu, pick the connector, and ask. ChatGPT asks before it runs a tool the first time.
Custom connectors need a paid ChatGPT plan, and on Team, Enterprise and Edu accounts only an admin can add them. Our "Working" label means the server answered us; it cannot tell whether your plan lets you add it. All connectors that work in ChatGPT
Add it to Claude
- 1
Open Claude settings
In Claude, open Settings, then Connectors.
- 2
Add a custom connector
Choose Add custom connector, give it a name, and paste the link.
- 3
Connect and use it
If it needs a sign-in, Claude sends you to it. Then turn the connector on in a chat from the tools menu and ask.
Custom connectors are available on paid Claude plans; on Team and Enterprise accounts an admin may need to add them. Our "Working" label means the server answered us; it cannot tell whether your plan lets you add it. All connectors that work in Claude
https://safetychain.usefulapi.io/mcpWhat people ask Muse to do
Technical details: safety screening, tools, response time and recent checks
Response time at the last check: 220ms. Worked in n/a of checks over 30 days.
Screening · October 30, 2026
Screened, no issues found
Screening looks for known threats and hidden instructions at the time of the check, and runs again weekly and whenever the tool list changes. It cannot see the server's code, so only connect what you need and review what Muse asks to do. How screening works.
Tools · 29
safetychain_list_customersList customers of the SafetyChain tenant, with ids, names, enabled flags and created/modified dates. Filter by name. The API does not page: all matches come back (cut at limit). GET /clientapis/resourcemanagement/v1.0/customers.safetychain_get_customerGet one customer by id (an id from safetychain_list_customers). GET /clientapis/resourcemanagement/v1.0/customer/{id}.safetychain_list_locationsList locations (plants, sites, areas) of the SafetyChain tenant, with ids, names, enabled flags and created/modified dates. Filter by name. The API does not page: all matches come back (cut at limit). GET /clientapis/resourcemanagement/v1.0/locations.safetychain_get_locationGet one location by id (an id from safetychain_list_locations). GET /clientapis/resourcemanagement/v1.0/location/{id}.safetychain_list_suppliersList suppliers of the SafetyChain tenant, with ids, names, enabled flags and created/modified dates. Filter by name. The API does not page: all matches come back (cut at limit). GET /clientapis/resourcemanagement/v1.0/suppliers.safetychain_get_supplierGet one supplier by id (an id from safetychain_list_suppliers). GET /clientapis/resourcemanagement/v1.0/supplier/{id}.safetychain_list_itemsList items (products, ingredients, materials) of the SafetyChain tenant, with ids, names, enabled flags and created/modified dates. Filter by name. The API does not page: all matches come back (cut at limit). GET /clientapis/resourcemanagement/v1.0/items.safetychain_get_itemGet one item by id (an id from safetychain_list_items). GET /clientapis/resourcemanagement/v1.0/item/{id}.safetychain_list_equipmentList equipment of the SafetyChain tenant, with ids, names, enabled flags and created/modified dates. Filter by name. The API does not page: all matches come back (cut at limit). GET /clientapis/resourcemanagement/v1.0/equipment.safetychain_get_equipmentGet one equipment by id (an id from safetychain_list_equipment). GET /clientapis/resourcemanagement/v1.0/equipment/{id}.safetychain_list_resourcesList resources of every type (customers, equipment, items, suppliers, lists) of the SafetyChain tenant, with ids, names, enabled flags and created/modified dates. Filter by name. The API does not page: all matches come back (cut at limit). GET /clientapis/resourcemanagement/v1.0/safetychain_get_resourceGet one resource by id (an id from safetychain_list_resources). GET /clientapis/resourcemanagement/v1.0/resource/{id}.safetychain_list_formsList forms (the checklists and data-entry forms operators fill in) of the SafetyChain tenant, with ids, names, enabled flags and created/modified dates. Filter by name. The API does not page: all matches come back (cut at limit). GET /clientapis/resourcemanagement/v1.0/forms.safetychain_get_formGet one form by id (an id from safetychain_list_forms). GET /clientapis/resourcemanagement/v1.0/form/{id}.safetychain_list_categoriesList categories used to group resources of the SafetyChain tenant, with ids, names, enabled flags and created/modified dates. Filter by name. The API does not page: all matches come back (cut at limit). GET /clientapis/resourcemanagement/v1.0/categories.safetychain_get_categoryGet one category by id (an id from safetychain_list_categories). GET /clientapis/resourcemanagement/v1.0/category/{id}.safetychain_search_capasSearch corrective and preventive actions (CAPA, SCAR, CCAR). Filters combine with AND. Returns id, name, severity, owner workgroup, status, event and due dates, task counts, location and template type, 50 per page. Use the Id (a GUID) with safetychain_get_capa and the other CAPA safetychain_get_capaGet one CAPA's details: status, severity, event and due dates, summary, creator, resource, source, category, owner workgroup, template and steps. The id is the GUID `Id` from safetychain_search_capas. GET /clientapis/capamanagement/v1.0/capa/{id}.safetychain_get_capa_tasksList a CAPA's tasks (step, form, location, resource, workgroup, assignee, due date, status). The id is the GUID `Id` from safetychain_search_capas. GET /clientapis/capamanagement/v1.0/capa/{id}/tasks.safetychain_get_capa_attachmentsList a CAPA's attachments (name, extension, link, creator, date). The id is the GUID `Id` from safetychain_search_capas. GET /clientapis/capamanagement/v1.0/capa/{id}/attachments.safetychain_get_capa_historyList a CAPA's history entries. The id is the GUID `Id` from safetychain_search_capas. GET /clientapis/capamanagement/v1.0/capa/{id}/history.safetychain_get_capa_linked_recordsList a CAPA's linked records. The id is the GUID `Id` from safetychain_search_capas. GET /clientapis/capamanagement/v1.0/capa/{id}/linkedrecords.safetychain_get_capa_linked_capasList a CAPA's linked CAPAs. The id is the GUID `Id` from safetychain_search_capas. GET /clientapis/capamanagement/v1.0/capa/{id}/linkedcapas.safetychain_get_capa_activityList a CAPA's activity (comments and events). The id is the GUID `Id` from safetychain_search_capas. GET /clientapis/capamanagement/v1.0/capa/{id}/activity.safetychain_get_recordGet one submitted record in full by its record id (the GUID `recordId` from safetychain_search_records): form, who submitted it and when, location, resource, field values, verifications. GET /clientapis/recordmanagement/v1.0/record/{recordId}.safetychain_record_existsCheck whether a record exists for a record id (GUID). GET /clientapis/recordmanagement/v1.0/record/{recordId}/Exists.safetychain_search_recordsSearch submitted records (the headers: record number, compliance, submitted date, location, form and version, resource, who submitted, signed, verifications, ids). Filter by date range, form, location, resource, identifier and compliance. Always narrow by a date range or a name: safetychain_get_record_fieldsGet the field-level values of records (one entry per record with its fields: name, short name, type, value, unit, compliance, min, max, target, comments, section). Same filters as safetychain_search_records; narrow strongly (a record number or one form and a short date range), easafetychain_get_record_summaryFast summary of the records matching the filters: first and last date, and how many forms, resources, locations and users are involved. Use it to size a request before safetychain_search_records. POST /clientapis/v2.0/getRecordSummary (a read).Link
https://safetychain.usefulapi.io/mcpQuestions about SafetyChain MCP in Muse
How do I connect SafetyChain MCP to Muse?
Not in Muse's Connectors list yet, but Muse can still use it. Paste this into Muse: "Use SafetyChain MCP to help me. It is a free service with an MCP server at https://safetychain.usefulapi.io/mcp. It does not need an API key. Ask me before you share anything with it." Muse asks before it shares anything with the app's site. Meta does not review apps used this way, so only use ones you trust. We tested this in the Muse app on September 24, 2026: Muse used an app's link directly this way and returned a live answer.
Is SafetyChain MCP working right now?
At the last check (October 30, 2026, 00:51 UTC) the endpoint was working, answering in 220ms. It is checked every 15 minutes.
Is SafetyChain MCP safe to connect to Muse?
It was screened on October 30, 2026 with the result "screened, no issues found". Screening checks the domain against threat feeds and reads the tools for hidden instructions and requests for passwords or card numbers. It cannot see the server's code, so grant only the access you need.
What can SafetyChain MCP do in Muse?
It exposes 29 tools, including safetychain_list_customers, safetychain_get_customer, safetychain_list_locations, safetychain_get_location. For example, you could ask Muse: "Show me all open corrective actions from the past month at our main facility"
Follow SafetyChain MCP
Made this app? Claim it or get a status badge
Is this yours?
This listing was added from public sources (Found in the official MCP Registry (io.usefulapi/safetychain)). If you build SafetyChain MCP, claim it to correct the details and get your badge.
Paste this on your site or README. It always shows the latest check.
<a href="https://musedirectory.ai/connector/safetychain-mcp"><img src="https://musedirectory.ai/badge/safetychain-mcp.svg" alt="SafetyChain MCP on musedirectory.ai" width="236" height="40"></a>