# Agent Server

> Use this tool when you need to build and manage AI agent systems with persistent memory and workflow integration, solving problems of context retention and automation scalability in SaaS applications. It provides a RESTful API interface for agent management, user authentication, and workflow triggers, accepting API keys and workflow data as inputs and outputting managed agent instances and workflow events. Ideal for developers building commercial AI employee systems that require multi-tenancy, easy deployment, and integration with existing tools.

Canonical page: https://skillsregistry.net/skills/leadbroaf-agent  
JSON: https://api.skillsregistry.net/v1/skills/leadbroaf-agent

## Description

This MCP server provides a foundation for building AI agent systems with persistent memory and workflow integration, designed specifically for SaaS deployment and monetization. Built by Matthew Smith using Node.js, TypeScript, Express, and PostgreSQL with Prisma ORM, it offers core functionality for agent management, persistent memory storage per agent, user authentication with API key management, and n8n workflow integration through trigger endpoints. The implementation features Docker containerization for easy deployment, database migrations for schema management, and a RESTful API structure that supports multi-tenant SaaS applications, making it valuable for developers building AI employee systems that need to maintain context across sessions, integrate with existing workflow automation tools, and scale as commercial offerings.

## Trust

- **Trust score (0–1):** 1.00
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** database
- **Updated:** 2026-09-19

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/leadbroaf-agent)
- **Repository:** <https://github.com/leadbroaf/mcp-agent-server>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "leadbroaf-agent"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/leadbroaf-agent` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/leadbroaf-agent/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt