deephr-mcp

deephr-mcp

Read-only MCP server that proxies deepHR's API to MCP clients, enabling interaction with deepHR modules such as payroll and employees through natural language.

Category
Visit Server

README

deephr-mcp

Read-only MCP server exposing deepHR's modules to MCP clients (Claude Desktop / Claude Code). It proxies read calls to the deepHR backend /api/* over HTTP, authenticating with a service account and refreshing the JWT on 401.

Install (clients)

No clone needed — run it straight from GitHub with npx:

claude mcp add deephr -s user \
  -e DEEPHR_API_URL=https://deephr.your-cloud-domain.com \
  -e DEEPHR_EMAIL=you@yourco.com \
  -e DEEPHR_PASSWORD=... \
  -- npx -y github:leevydanomalik/deephr-mcp

(If/when published to npm, swap the last line for npx -y deephr-mcp.)

-s user makes it global (available in every project on that machine). Each user only changes DEEPHR_API_URL (the deployed backend) and their own login. Needs Node >= 18.

Run (local dev)

DEEPHR_EMAIL=svc@yourco.com DEEPHR_PASSWORD=... bun run src/server.ts

The backend must be running (default http://localhost:4445).

Build & publish (maintainers)

bun run build     # bundles src/ -> dist/server.js (node ESM, shebang, npx-runnable)
npm publish       # prepublishOnly runs the build automatically

deephr-mcp is an unscoped public package — npm login once, then npm publish.

Env

Var Default Purpose
DEEPHR_API_URL http://localhost:4445 Backend base URL
DEEPHR_EMAIL (required) Service-identity login (use an admin/superadmin account)
DEEPHR_PASSWORD (required) Service-identity password

Register in Claude Code / Desktop

{
  "mcpServers": {
    "deephr": {
      "command": "bun",
      "args": ["run", "/ABSOLUTE/PATH/deepHR/mcp/src/server.ts"],
      "env": {
        "DEEPHR_API_URL": "http://localhost:4445",
        "DEEPHR_EMAIL": "svc@yourco.com",
        "DEEPHR_PASSWORD": "..."
      }
    }
  }
}

Tools

~16 facade tools (deephr_payroll, deephr_employees, …). Each takes { operation, params }. See a tool's description for its operation catalog.

Maintaining the registry

Routes are scanned from backend/src/app/api:

bun run scan   # regenerates src/registry/<facade>.ts + index.ts

Hand-tune hot operations (better summaries, real query schemas) in src/registry/annotations.ts — that layer survives re-scans.

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured