Jobber · CRM
JOBBER_GRAPHQL
Run a Jobber GraphQL query or mutation using the connected Jobber account. Returns { data, errors, cost, versioning }.
- Provider
- Jobber
- Access
- Write
- Category
- CRM
- Version
- v1
Input schema
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Jobber GraphQL query or mutation."
},
"variables": {
"type": "object",
"description": "Optional GraphQL variables."
}
},
"required": [
"query"
],
"additionalProperties": false
}How to call it
Expose this tool to any MCP-capable agent (Claude, GPT, or your own) through CybrLink's MCP server. The agent calls jobber_graphql with arguments matching the schema above.
CybrLink validates the input, injects the connected Jobber credentials server-side, and runs a single scoped provider API call through the shared proxy — the same guarded path as the generic call_api tool. The raw secret never reaches the model, and the response is trimmed to just the fields the agent needs.
Write action — gate behind explicit user approval and write scope.
Frequently asked
- How do I let an AI agent jobber graphql?
- Connect Jobber to CybrLink, then expose the `jobber_graphql` tool to any MCP-capable agent (Claude, GPT, or a custom framework). The agent calls it with typed arguments; CybrLink injects the Jobber credential server-side and runs one scoped API call. Run a Jobber GraphQL query or mutation using the connected Jobber account. Returns { data, errors, cost, versioning }.
- Does the AI model see my Jobber credentials when using JOBBER_GRAPHQL?
- No. CybrLink stores the credential in a token vault and injects it on the server for each call, so the model can take this action in Jobber without the OAuth token or API key ever entering its context.