CallRail MCP integration for AI agents.
Connect AI agents to CallRail through 6 structured actions, including get call, get form submission, and list accounts. Review authentication, inputs, workfl…
- ACTION CONTRACTS
- 6
- AUTHENTICATION
- API key
- SOURCE STATUS
- Provider-backed
CATALOG SOURCE REVIEWED AUGUST 23, 2026 / ACTION NAMES AND SCHEMAS DERIVED FROM WORKING MACHINES PROVIDER SOURCE
CAPABILITY PROFILE
What the CallRail integration exposes
The CallRail Agent App exposes 6 provider-backed actions for marketing and data work. Its current contract lets an authorized agent retrieve one callrail call by account id and call id, retrieve one callrail form submission by account id and form submission id, and list callrail accounts visible to the api key. These operations are called through Working Machines as typed capabilities rather than through browser navigation or copied UI steps.
A connection uses API key. Before execution, the agent can inspect the selected action, its required fields, declared scopes, and expected output contract. Provider credentials remain inside the Working Machines runtime; the calling agent receives the capability and its structured result, not the underlying secret.
For reliable operation, start with the narrowest action that satisfies the task, resolve stable provider identifiers before changing state, and validate the returned object or status after execution. Availability still depends on the connected CallRail account, granted provider permissions, workspace policy, region, plan, and upstream API behavior.
VERIFIED ACTION SAMPLE
Real CallRail capabilities.
Showing 6 of 6 actions. Risk labels are conservative signals based on operation names, not substitutes for provider documentation or runtime policy.
get_callREADRetrieve one CallRail call by account ID and call ID.
INPUTS: accountId / callId / fields
get_form_submissionREADRetrieve one CallRail form submission by account ID and form submission ID.
INPUTS: accountId / formSubmissionId
list_accountsREADList CallRail accounts visible to the API key.
INPUTS: page / perPage / hipaaAccount
list_callsREADList CallRail calls for one account with optional company, tracker, date, and field filters.
INPUTS: accountId / companyId / trackerId / startDate / endDate
list_companiesREADList CallRail companies for one account.
INPUTS: accountId / page / perPage
list_form_submissionsREADList CallRail form submissions for one account with optional company, date, and field filters.
INPUTS: accountId / companyId / startDate / endDate / fields
INPUT CONTRACTS
Know what the action needs before it runs.
get_call
accountIdREQUIRED- The CallRail account ID.
callIdREQUIRED- The CallRail call ID.
fieldsOPTIONAL- Additional field names to request from CallRail, such as milestones or keywords_spotted.
get_form_submission
accountIdOPTIONAL- The CallRail account ID.
formSubmissionIdOPTIONAL- The CallRail form submission ID.
list_accounts
pageOPTIONAL- The page number to return.
perPageOPTIONAL- The number of records to return per page.
hipaaAccountOPTIONAL- Filter accounts by HIPAA account status.
list_calls
accountIdREQUIRED- The CallRail account ID.
companyIdOPTIONAL- The CallRail company ID.
trackerIdOPTIONAL- Only return calls for this CallRail tracker ID.
startDateOPTIONAL- Only return calls on or after this date.
endDateOPTIONAL- Only return calls on or before this date.
PROVIDER-SPECIFIC WORKFLOWS
Jobs this Agent App can support
Inspect Get Call
Retrieve one CallRail call by account ID and call ID. Use this as a bounded discovery step, retain the returned identifier, and avoid expanding the read beyond the task's stated scope.
get_callVerify with Get Form Submission
Retrieve one CallRail form submission by account ID and form submission ID. Compare the returned provider state with the intended outcome and preserve stable IDs or canonical links in the run record.
get_form_submissionSAFETY BOUNDARY
Operate CallRail with explicit limits
- Authorize CallRail with API key and grant only the provider access required by the selected actions.
- The current action names appear read-oriented, but returned CallRail data may still be sensitive and should be minimized before it enters model context.
- Do not infer permission from catalog visibility. Workspace policy, connection identity, and upstream authorization still govern execution.
- No provider scope string is declared on the sampled actions. Verify the connected account's actual permissions in CallRail rather than assuming unrestricted access.
- After a call, inspect the structured result and execution record before reporting that the CallRail task completed successfully.
CONNECTION MODEL
API key
CallRail API key used with the Authorization: Token token header. Create or view API keys from your CallRail account integration settings: https://support.callrail.com/hc/en-us/articles/5712444672909-CallRail-s-API-documentation.
Working Machines stores provider credentials behind the execution boundary. An agent can use an authorized connection identity, but catalog discovery alone does not reveal OAuth tokens, API keys, or provider secrets.
- READ SIGNALS
- 6
- WRITE SIGNALS
- 0
- HIGH IMPACT
- 0
- REVIEW SIGNALS
- 0
EVIDENCE AND AVAILABILITY
Provider reference
Action names, input fields, authentication types, and counts on this page are generated from the Working Machines provider catalog. Provider behavior, quotas, object semantics, account eligibility, and regional availability remain governed by CallRail.