mcpField
T
TalentHR MCP by usefulapi

TalentHR MCP by usefulapi

Remote
usefulapi.ioBusiness & Marketing1Updated today

About TalentHR MCP by usefulapi

TalentHR MCP by usefulapi connects an AI client to TalentHR records, reports and recruiting data. It combines HR data reads with actions for time-off requests and internal applicant notes.

Key features

  1. 01Read employee and organization records
  2. 02Review leave, benefits and assets
  3. 03Access applicants and recruiting data
  4. 04Retrieve headcount and HR reports
  5. 05Book or decide time-off requests
  6. 06Add notes to applications

Use cases

  1. 01Look up employee history and benefits
  2. 02Review leave requests and balances
  3. 03Check hiring and headcount reports
  4. 04Record an applicant note or handle leave

MCP support

An MCP server that exposes TalentHR employee, leave, recruiting and report data, along with tools to request or decide leave and add applicant notes. OAuth sign-in connects the account; write actions can trigger notifications.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://talenthr.usefulapi.io/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

TalentHR MCP by usefulapi

Connect

  • Claude (claude.ai, Desktop): open Customize → Connectors, click + Add → Add custom connector, and paste https://talenthr.usefulapi.io/mcp.
  • Claude Code: claude mcp add --transport http talenthr https://talenthr.usefulapi.io/mcp, then run /mcp to log in.
  • VS Code: Add to VS Code.
  • Cursor and other clients: add the URL as a remote MCP server:
{
  "mcpServers": {
    "talenthr": {
      "url": "https://talenthr.usefulapi.io/mcp"
    }
  }
}

Add only the URL. Do not add an Authorization header or an API key to the client config: the server signs you in with OAuth, and the login page asks for your TalentHR credentials.

Step-by-step setup, where to find your credentials, and FAQ: https://usefulapi.io/talenthr/

Tools

ToolTypeWhat it does
talenthr_list_employeesreadList employees (directory)
talenthr_get_directory_filtersreadGet directory filters
talenthr_get_employeereadGet an employee
talenthr_get_employee_jobreadGet an employee's job history
talenthr_get_organization_chartreadGet the organization chart
talenthr_list_departmentsreadList departments
talenthr_list_divisionsreadList divisions
talenthr_list_locationsreadList locations
talenthr_list_job_titlesreadList job titles
talenthr_list_time_off_typesreadList time off types
talenthr_list_employee_time_off_requestsreadList an employee's time off requests
talenthr_get_employee_time_off_budgetsreadGet an employee's time off balances
talenthr_get_calendarreadGet the time off calendar
talenthr_list_holidaysreadList holidays
talenthr_list_benefitsreadList benefits
talenthr_get_employee_benefitsreadGet an employee's benefits
talenthr_list_assetsreadList company assets
talenthr_get_employee_assetsreadGet an employee's assets
talenthr_list_job_positionsreadList job positions
talenthr_list_job_position_applicantsreadList applicants of a job position
talenthr_list_applicantsreadList all applicants
talenthr_get_applicantreadGet an applicant
talenthr_get_headcount_reportreadGet the headcount report
talenthr_get_hires_leaves_reportreadGet the hires and leaves report
talenthr_get_time_off_reportreadGet the time off report
talenthr_list_time_tracking_entriesreadList time tracking entries
talenthr_create_time_off_requestwriteBook a time off request
talenthr_reply_time_off_requestwriteApprove or reject a time off request
talenthr_create_applicant_notewriteAdd a note to a job application
talenthr_usage_statusmetaUsage status (free-tier meter)
talenthr_request_featuremetaRequest a missing feature
talenthr_upgrademetaUpgrade to Pro or Pro+
talenthr_cancel_subscriptionmetaCancel the Pro subscription

read tools are read-only; write tools mutate data (clients should confirm them); meta tools report usage, manage your subscription or send a feature request.

Pricing

PlanPriceLimit
Free (per TalentHR tenant/key)$050 tool calls / month
Pro (per TalentHR tenant/key)$9/mo or $90/yr (2 months free)Unlimited*

*Pro has a fair use limit of 10,000 tool calls a month on this server. For more, write to [email protected].

Pro covers this server only. Subscribe with talenthr_upgrade (it returns a Stripe Checkout link). Cancel any time with talenthr_cancel_subscription: Pro continues to the end of the paid period, with no refund for the current period, and running talenthr_upgrade before then undoes the cancel. Or write to [email protected].

License

MIT.

HR data, notifications and access

Requested employee, candidate, compensation and other HR records pass to your chosen AI client and LLM provider; API keys do not. Only connect data authorized for that processing. Scope and revoke a dedicated API key in TalentHR to control access.

Booking time off emails the manager, or notifies the employee when the manager is unavailable. Preapproved requests bypass manager approval when permitted and should be used only for an explicitly approved request. Approving/rejecting pending time off emails the employee. Applicant notes are internal and visible to hiring staff. No hires, terminations, pay changes or attachments are exposed.

No request is automatically retried; check TalentHR before repeating an uncertain write. Usage and billing follow the tenant domain when the key can read domain settings, otherwise the key itself. Rotating a key without domain-settings access can change that identity. Independent integration; no vendor approval or endorsement claimed.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.