A Model Context Protocol (MCP) server to fetch data from Paylocity API endpoints.
A Model Context Protocol (MCP) server to fetch data from Paylocity API endpoints. That is what the mcppaylocity mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.
The server publishes 9 tools. What each one is for:
fetch_employees — Fetches all employees for a companyfetch_employee_details — Fetches details for a specific employeefetch_employee_earnings — Fetches earnings data for a specific employeefetch_company_codes — Fetches company codes for a specific resourcefetch_employee_local_taxes — Fetches local taxes for a specific employeefetch_employee_paystatement_details — Fetches pay statement details for a specific dateResources — The server implements Paylocity API resources with: - Custom paylocity:// URI scheme for accessing Paylocity data - The following resources areTools — The server implements the following tools: - fetch_employees - Fetches all employees for a company - Takes optional company_id parameter -Debugging — Since MCP servers run over stdio, debugging can be challenging. For the best debugging experience, we strongly recommend using the [MCPInstallation goes through your MCP client rather than a global install: point it at @modelcontextprotocol/inspector on npm and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.
Configuration is passed through the environment: PAYLOCITY_CLIENT_ID, PAYLOCITY_CLIENT_SECRET, UV_PUBLISH_TOKEN. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.
Plenty of developer tooling servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. McpPaylocity's toolset — fetch_employees, fetch_employee_details, fetch_employee_earnings and 6 more — is a fair guide to whether it matches your workflow. It is maintained by mz462; worth a glance at recent repository activity before you build anything load-bearing on it.
SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.
| Tool | What it does |
|---|---|
| fetch_employees | Fetches all employees for a company |
| fetch_employee_details | Fetches details for a specific employee |
| fetch_employee_earnings | Fetches earnings data for a specific employee |
| fetch_company_codes | Fetches company codes for a specific resource |
| fetch_employee_local_taxes | Fetches local taxes for a specific employee |
| fetch_employee_paystatement_details | Fetches pay statement details for a specific date |
| Resources | The server implements Paylocity API resources with: - Custom paylocity:// URI scheme for accessing Paylocity data - The following resources are available: - paylocity://employees/{company_id} - List all employees for a c |
| Tools | The server implements the following tools: - fetch_employees - Fetches all employees for a company - Takes optional company_id parameter - fetch_employee_details - Fetches details for a specific employee - Takes required |
| Debugging | Since MCP servers run over stdio, debugging can be challenging. For the best debugging experience, we strongly recommend using the [MCP Inspector](https://github.com/modelcontextprotocol/inspector). |
"mcpServers": {
"mcpPaylocity": {
"command": "uv",
"args": [
"--directory",
"/path/to/mcpPaylocity",
"run",
"mcppaylocity"
]
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| PAYLOCITY_CLIENT_ID | Configuration value read at startup. | Optional |
| PAYLOCITY_CLIENT_SECRET | Credential the server authenticates with. | Yes |
| UV_PUBLISH_TOKEN | Credential the server authenticates with. | Yes |
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Microsoft's official browser automation server — drive a real browser through the accessibility tree, no screenshots needed.
GitHub's official server — repos, issues, pull requests, Actions and code security, straight from your assistant.
Issue tracking at the speed of conversation — Linear's official hosted server with OAuth and zero install.
Local repository surgery — status, diffs, commits, branches and history for any repo on disk.
Timezone sanity for AI — current time anywhere and correct conversions, without the model doing date math.