Callingly MCP integration for AI agents.
Connect AI agents to Callingly through 12 structured actions, including get agent schedule, create call, and delete lead. Review authentication, inputs, work…
- ACTION CONTRACTS
- 12
- 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 Callingly integration exposes
The Callingly Agent App exposes 12 provider-backed actions for communication and productivity work. Its current contract lets an authorized agent retrieve the weekly schedule for one callingly agent, create a callingly call from lead details and routing information, and delete a callingly lead by id. 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 Callingly account, granted provider permissions, workspace policy, region, plan, and upstream API behavior.
VERIFIED ACTION SAMPLE
Real Callingly capabilities.
Showing 12 of 12 actions. Risk labels are conservative signals based on operation names, not substitutes for provider documentation or runtime policy.
get_agent_scheduleREADRetrieve the weekly schedule for one Callingly agent.
INPUTS: agentId
create_callWRITECreate a Callingly call from lead details and routing information.
INPUTS: account_id / team_id / first_name / last_name / phone_number
delete_leadHIGH IMPACTDelete a Callingly lead by ID.
INPUTS: leadId
get_callREADRetrieve one Callingly call by ID.
INPUTS: callId
get_leadREADRetrieve one Callingly lead by ID.
INPUTS: leadId
get_teamREADRetrieve one Callingly team by ID.
INPUTS: teamId
list_agentsREADList Callingly agents for the current account or a specified client account.
INPUTS: account_id
list_callsREADList Callingly calls with optional date, team, and pagination filters.
INPUTS: start / end / teamId / accountId / limit
list_leadsREADList Callingly leads with optional date or phone number filters.
INPUTS: start / end / phone_number / accountId
list_team_agentsREADList agents assigned to one Callingly team.
INPUTS: teamId
list_teamsREADList Callingly teams for the current account or a specified client account.
INPUTS: accountId
update_leadWRITEUpdate a Callingly lead by ID.
INPUTS: leadId / id / fname / lname / email
INPUT CONTRACTS
Know what the action needs before it runs.
get_agent_schedule
agentIdOPTIONAL- Callingly agent identifier.
create_call
account_idOPTIONAL- Agency account identifier used when acting on behalf of a client account.
team_idREQUIRED- Callingly team identifier.
first_nameREQUIRED- Lead first name to use for the call.
last_nameREQUIRED- Lead last name to use for the call.
phone_numberREQUIRED- Lead phone number for the call.
delete_lead
leadIdOPTIONAL- Callingly lead identifier.
get_call
callIdOPTIONAL- Callingly call identifier.
PROVIDER-SPECIFIC WORKFLOWS
Jobs this Agent App can support
Inspect Get Agent Schedule
Retrieve the weekly schedule for one Callingly agent. Use this as a bounded discovery step, retain the returned identifier, and avoid expanding the read beyond the task's stated scope.
get_agent_scheduleControl Create Call
Create a Callingly call from lead details and routing information. Resolve the target first, present material changes for confirmation, and make retries idempotent where the provider supports it.
create_callVerify with Get Call
Retrieve one Callingly call by ID. Compare the returned provider state with the intended outcome and preserve stable IDs or canonical links in the run record.
get_callSAFETY BOUNDARY
Operate Callingly with explicit limits
- Authorize Callingly with API key and grant only the provider access required by the selected actions.
- 3 actions are change-capable by name. Confirm the target identity and material parameters before allowing a write.
- Treat `delete_lead` as high-impact operations and require an explicit approval boundary.
- No provider scope string is declared on the sampled actions. Verify the connected account's actual permissions in Callingly rather than assuming unrestricted access.
- After a call, inspect the structured result and execution record before reporting that the Callingly task completed successfully.
CONNECTION MODEL
API key
Callingly bearer token used with the Authorization header. Create it under Settings > API Keys in the Callingly dashboard: https://callingly.com/dashboard/settings/api_keys
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
- 9
- WRITE SIGNALS
- 2
- HIGH IMPACT
- 1
- 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 Callingly.