mcp-cliniko

create_appointment

Schedule a new patient appointment in Cliniko by specifying start time, practitioner, appointment type, and business. Optionally add patient ID and notes.

Instructions

Create a new appointment

Input Schema

TableJSON Schema

Name	Required	Description
`starts_at`	Yes	Appointment start time (ISO 8601)
`patient_id`	No	Patient ID (optional for walk-ins)
`practitioner_id`	Yes	Practitioner ID
`appointment_type_id`	Yes	Appointment type ID
`business_id`	Yes	Business ID
`notes`	No	Appointment notes

Implementation Reference

src/tools/appointments.ts:94-120 (handler)

The MCP tool registration and handler for 'create_appointment'. Registers the tool with server.tool('create_appointment', ...), defines the input schema inline, and calls client.createAppointment(input) on execution.

server.tool('create_appointment', {
  description: 'Create a new appointment',
  inputSchema: {
    type: 'object',
    properties: {
      starts_at: { type: 'string', description: 'Appointment start time (ISO 8601)' },
      patient_id: { type: 'number', description: 'Patient ID (optional for walk-ins)' },
      practitioner_id: { type: 'number', description: 'Practitioner ID' },
      appointment_type_id: { type: 'number', description: 'Appointment type ID' },
      business_id: { type: 'number', description: 'Business ID' },
      notes: { type: 'string', description: 'Appointment notes' }
    },
    required: ['starts_at', 'practitioner_id', 'appointment_type_id', 'business_id']
  },
}, async (input: z.infer<typeof AppointmentCreateSchema>) => {
  try {
    const appointment = await client.createAppointment(input);
    return {
      content: [{
        type: 'text',
        text: JSON.stringify(appointment, null, 2)
      }]
    };
  } catch (error) {
    throw new Error(`Failed to create appointment: ${error instanceof Error ? error.message : 'Unknown error'}`);
  }
});

src/tools/appointments.ts:15-22 (schema)

Zod schema for create_appointment input validation: starts_at (required), patient_id (optional), practitioner_id (required), appointment_type_id (required), business_id (required), notes (optional).

const AppointmentCreateSchema = z.object({
  starts_at: z.string().describe('Appointment start time (ISO 8601)'),
  patient_id: z.number().optional().describe('Patient ID (optional for walk-ins)'),
  practitioner_id: z.number().describe('Practitioner ID'),
  appointment_type_id: z.number().describe('Appointment type ID'),
  business_id: z.number().describe('Business ID'),
  notes: z.string().optional().describe('Appointment notes'),
});

src/cliniko-client.ts:114-126 (helper)

ClinikoClient.createAppointment method - sends POST /appointments to the Cliniko API with the appointment data as JSON body. This is the underlying API call that the handler delegates to.

async createAppointment(appointment: {
  starts_at: string;
  patient_id?: number;
  practitioner_id: number;
  appointment_type_id: number;
  business_id: number;
  notes?: string;
}): Promise<Appointment> {
  return this.request<Appointment>('/appointments', {
    method: 'POST',
    body: JSON.stringify(appointment),
  });
}

src/tools/appointments.ts:31-316 (registration)

The registerAppointmentTools function exported from appointments.ts. It's called from src/index.ts line 59 to register all appointment-related tools including create_appointment.

export function registerAppointmentTools(server: any, client: ClinikoClient) {
  // List/Search appointments
  server.tool('list_appointments', {
    description: 'List or search for appointments',
    inputSchema: {
      type: 'object',
      properties: {
        patient_id: { type: 'number', description: 'Filter by patient ID' },
        practitioner_id: { type: 'number', description: 'Filter by practitioner ID' },
        business_id: { type: 'number', description: 'Filter by business ID' },
        starts_at: { type: 'string', description: 'Filter appointments starting from (ISO 8601)' },
        ends_at: { type: 'string', description: 'Filter appointments ending before (ISO 8601)' },
        status: { type: 'string', description: 'Filter by status (Active, Cancelled, Did not arrive)' },
        page: { type: 'number', description: 'Page number' },
        per_page: { type: 'number', description: 'Results per page (max 100)' }
      }
    },
  }, async (params: z.infer<typeof AppointmentSearchSchema>) => {
    try {
      const response = await client.listAppointments(params);
      const appointments = response.appointments || [];
      
      return {
        content: [{
          type: 'text',
          text: JSON.stringify({
            appointments,
            total_entries: response.total_entries,
            page: params.page || 1,
            has_more: !!response.links.next
          }, null, 2)
        }]
      };
    } catch (error) {
      throw new Error(`Failed to list appointments: ${error instanceof Error ? error.message : 'Unknown error'}`);
    }
  });

  // Get appointment by ID
  server.tool('get_appointment', {
    description: 'Get a specific appointment by ID',
    inputSchema: {
      type: 'object',
      properties: {
        appointment_id: { type: 'number', description: 'Appointment ID' }
      },
      required: ['appointment_id']
    },
  }, async ({ appointment_id }: { appointment_id: number }) => {
    try {
      const appointment = await client.getAppointment(appointment_id);
      return {
        content: [{
          type: 'text',
          text: JSON.stringify(appointment, null, 2)
        }]
      };
    } catch (error) {
      throw new Error(`Failed to get appointment: ${error instanceof Error ? error.message : 'Unknown error'}`);
    }
  });

  // Create appointment
  server.tool('create_appointment', {
    description: 'Create a new appointment',
    inputSchema: {
      type: 'object',
      properties: {
        starts_at: { type: 'string', description: 'Appointment start time (ISO 8601)' },
        patient_id: { type: 'number', description: 'Patient ID (optional for walk-ins)' },
        practitioner_id: { type: 'number', description: 'Practitioner ID' },
        appointment_type_id: { type: 'number', description: 'Appointment type ID' },
        business_id: { type: 'number', description: 'Business ID' },
        notes: { type: 'string', description: 'Appointment notes' }
      },
      required: ['starts_at', 'practitioner_id', 'appointment_type_id', 'business_id']
    },
  }, async (input: z.infer<typeof AppointmentCreateSchema>) => {
    try {
      const appointment = await client.createAppointment(input);
      return {
        content: [{
          type: 'text',
          text: JSON.stringify(appointment, null, 2)
        }]
      };
    } catch (error) {
      throw new Error(`Failed to create appointment: ${error instanceof Error ? error.message : 'Unknown error'}`);
    }
  });

  // Update appointment
  server.tool('update_appointment', {
    description: 'Update an existing appointment',
    inputSchema: {
      type: 'object',
      properties: {
        appointment_id: { type: 'number', description: 'Appointment ID' },
        starts_at: { type: 'string', description: 'New start time (ISO 8601)' },
        notes: { type: 'string', description: 'Updated notes' },
        patient_id: { type: 'number', description: 'New patient ID' }
      },
      required: ['appointment_id']
    },
  }, async ({ appointment_id, ...updateData }: any) => {
    try {
      const appointment = await client.updateAppointment(appointment_id, updateData);
      return {
        content: [{
          type: 'text',
          text: JSON.stringify(appointment, null, 2)
        }]
      };
    } catch (error) {
      throw new Error(`Failed to update appointment: ${error instanceof Error ? error.message : 'Unknown error'}`);
    }
  });

  // Cancel appointment
  server.tool('cancel_appointment', {
    description: 'Cancel an appointment',
    inputSchema: {
      type: 'object',
      properties: {
        appointment_id: { type: 'number', description: 'Appointment ID' },
        cancellation_reason: { type: 'string', description: 'Reason for cancellation' }
      },
      required: ['appointment_id']
    },
  }, async ({ appointment_id, cancellation_reason }: { appointment_id: number; cancellation_reason?: string }) => {
    try {
      const appointment = await client.cancelAppointment(appointment_id, cancellation_reason);
      return {
        content: [{
          type: 'text',
          text: JSON.stringify(appointment, null, 2)
        }]
      };
    } catch (error) {
      throw new Error(`Failed to cancel appointment: ${error instanceof Error ? error.message : 'Unknown error'}`);
    }
  });

  // Delete appointment
  server.tool('delete_appointment', {
    description: 'Delete an appointment completely',
    inputSchema: {
      type: 'object',
      properties: {
        appointment_id: { type: 'number', description: 'Appointment ID' }
      },
      required: ['appointment_id']
    },
  }, async ({ appointment_id }: { appointment_id: number }) => {
    try {
      await client.deleteAppointment(appointment_id);
      return {
        content: [{
          type: 'text',
          text: `Appointment ${appointment_id} has been deleted successfully`
        }]
      };
    } catch (error) {
      throw new Error(`Failed to delete appointment: ${error instanceof Error ? error.message : 'Unknown error'}`);
    }
  });

  // Get available times
  server.tool('get_available_times', {
    description: 'Get available appointment times for a practitioner',
    inputSchema: {
      type: 'object',
      properties: {
        business_id: { type: 'number', description: 'Business ID' },
        practitioner_id: { type: 'number', description: 'Practitioner ID' },
        from: { type: 'string', description: 'Start date for availability check (YYYY-MM-DD)' },
        to: { type: 'string', description: 'End date for availability check (YYYY-MM-DD)' }
      },
      required: ['business_id', 'practitioner_id', 'from', 'to']
    },
  }, async (params: z.infer<typeof AvailableTimesSchema>) => {
    try {
      const availableTimes = await client.getAvailableTimes(params);
      return {
        content: [{
          type: 'text',
          text: JSON.stringify({
            available_times: availableTimes,
            total: availableTimes.length,
            ...params
          }, null, 2)
        }]
      };
    } catch (error) {
      throw new Error(`Failed to get available times: ${error instanceof Error ? error.message : 'Unknown error'}`);
    }
  });

  // List practitioners (helper for appointments)
  server.tool('list_practitioners', {
    description: 'List all practitioners',
    inputSchema: {
      type: 'object',
      properties: {
        page: { type: 'number', description: 'Page number' },
        per_page: { type: 'number', description: 'Results per page' }
      }
    },
  }, async ({ page, per_page }: { page?: number; per_page?: number }) => {
    try {
      const response = await client.listPractitioners({ page, per_page });
      const practitioners = response.practitioners || [];
      
      return {
        content: [{
          type: 'text',
          text: JSON.stringify({
            practitioners,
            total_entries: response.total_entries,
            page: page || 1,
            has_more: !!response.links.next
          }, null, 2)
        }]
      };
    } catch (error) {
      throw new Error(`Failed to list practitioners: ${error instanceof Error ? error.message : 'Unknown error'}`);
    }
  });

  // List appointment types (helper for appointments)
  server.tool('list_appointment_types', {
    description: 'List all appointment types',
    inputSchema: {
      type: 'object',
      properties: {
        page: { type: 'number', description: 'Page number' },
        per_page: { type: 'number', description: 'Results per page' }
      }
    },
  }, async ({ page, per_page }: { page?: number; per_page?: number }) => {
    try {
      const response = await client.listAppointmentTypes({ page, per_page });
      const appointmentTypes = response.appointment_types || [];
      
      return {
        content: [{
          type: 'text',
          text: JSON.stringify({
            appointment_types: appointmentTypes,
            total_entries: response.total_entries,
            page: page || 1,
            has_more: !!response.links.next
          }, null, 2)
        }]
      };
    } catch (error) {
      throw new Error(`Failed to list appointment types: ${error instanceof Error ? error.message : 'Unknown error'}`);
    }
  });

  // List businesses (helper for appointments)
  server.tool('list_businesses', {
    description: 'List all businesses',
    inputSchema: {
      type: 'object',
      properties: {}
    },
  }, async () => {
    try {
      const response = await client.listBusinesses();
      const businesses = response.businesses || [];
      
      return {
        content: [{
          type: 'text',
          text: JSON.stringify({
            businesses,
            total_entries: response.total_entries,
          }, null, 2)
        }]
      };
    } catch (error) {
      throw new Error(`Failed to list businesses: ${error instanceof Error ? error.message : 'Unknown error'}`);
    }
  });
}

src/index.ts:57-63 (registration)

Registration hook in main entry point - calls registerAppointmentTools(toolRegistry, clinikoClient) which registers create_appointment along with other appointment tools.

// Register all tools
registerPatientTools(toolRegistry, clinikoClient);
registerAppointmentTools(toolRegistry, clinikoClient);
registerSyntheticDataTools(toolRegistry, clinikoClient);
registerEnhancedSyntheticDataTools(toolRegistry, clinikoClient);
registerInvoiceTools(toolRegistry, clinikoClient);
registerDemoInvoiceTools(toolRegistry, clinikoClient);

Tool Definition Quality

C2.9/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are present, so the description fully bears the burden of behavioral disclosure. It only states 'Create', implying a write operation, but does not mention any side effects, required permissions, or error conditions. This is insufficient for a mutation tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence that conveys the core purpose. It is front-loaded and wastes no words, though it could be slightly more informative without harming conciseness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has 6 parameters (4 required) and no output schema, the description is overly minimal. It does not explain what the tool returns, any constraints on inputs, or how it behaves under failure. A more complete description would include return value or side effects.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 100% schema description coverage, the structured schema already documents all parameters. The description adds no additional meaning beyond the schema, so a baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Create a new appointment' clearly states the action and resource, but does not distinguish this tool from siblings like 'update_appointment' or 'delete_appointment'. It is concise and direct, earning a 4 for clear purpose without differentiation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives such as 'cancel_appointment' or 'get_appointment'. The description lacks any context about prerequisites or use cases, leaving the agent without decision support.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Latest Blog Posts

Lightport: Open-Sourcing Glama's AI Gateway
By punkpeye on April 27, 2026.
open source
OpenAI
Tool Definition Quality Score (TDQS)
By punkpeye on April 3, 2026.
mcp
The Hackers Who Tracked My Sleep Cycle
By punkpeye on March 26, 2026.
security

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/andymillar84-cyber/mcp-cliniko'

If you have feedback or need assistance with the MCP directory API, please join our Discord server