pluginadvancedGeneral AI

Agentic MCP: Multi-Agent Orchestration on Edge Functions

This is a toolkit for building advanced AI agents that run on 'edge networks', making them faster by being physically closer to users. These agents can search the web, access databases, and automatically hand off tasks to other specialized agents to solve complex problems.

AI SETUP PROMPT

Paste into Claude Code or Codex CLI — it will scan your project and set everything up

# Install & Configure: Agentic MCP: Multi-Agent Orchestration on Edge Functions

## What This Is
This is a toolkit for building advanced AI agents that run on 'edge networks', making them faster by being physically closer to users. These agents can search the web, access databases, and automatically hand off tasks to other specialized agents to solve complex problems.

Source: https://github.com/agenticsorg/edge-agents

## Before You Start

Scan my workspace and analyze:
- The project language, framework, and directory structure
- Existing agent configuration (check for .claude/, .codex/, CLAUDE.md, settings.json, commands/, skills/ directories)
- Whether this repository or a similar tool is already cloned or installed

Then ask me before proceeding:
1. Do I need to configure any service credentials for this plugin (database, API keys, etc.)?
2. Should this be project-scoped or global?

## Fetch the Source

Clone or inspect the repository to understand what needs to be installed:
```bash
gh repo clone agenticsorg/edge-agents
```
Review the README, directory structure, and any install instructions before proceeding.

## What to Implement

This is an **Agent Plugin** — typically an MCP server or capability bundle.

- Install any required npm/pip packages from the source repository
- Register the MCP server in `.claude/settings.json` under the `mcpServers` key with the correct command and args
- Configure any required environment variables or credentials
- Verify the server starts correctly by checking its expected output

## Additional Context

- Install the Agentic MCP package into the user's project using `npm install @agentics.org/agentic-mcp`.
- Scaffold a new Supabase Edge Function. Configure its settings to use the Deno runtime and ensure the project's `import_map.json` is configured to correctly resolve the `@agentics.org/agentic-mcp` package.
- Implement the MCP server within the new edge function. Initialize the OpenAI client using the user's existing API key from their environment variables. Configure the server with a web search tool and a database connection using the user's Supabase credentials.

## Reference Implementation

```
# Install globally
npm install -g @agentics.org/agentic-mcp

# Or as a project dependency
npm install @agentics.org/agentic-mcp
```

## Guidelines

- Adapt everything to my existing project — do not assume a specific stack or directory layout
- Review any fetched code for safety before installing or executing it
- After setup, run a quick verification and show me a summary of exactly what was installed, where, and how to use it

2,609 charactersCompatible with Claude Code & Codex CLI

MANUAL SETUP STEPS

01Install the Agentic MCP package into the user's project using `npm install @agentics.org/agentic-mcp`.
02Scaffold a new Supabase Edge Function. Configure its settings to use the Deno runtime and ensure the project's `import_map.json` is configured to correctly resolve the `@agentics.org/agentic-mcp` package.
03Implement the MCP server within the new edge function. Initialize the OpenAI client using the user's existing API key from their environment variables. Configure the server with a web search tool and a database connection using the user's Supabase credentials.

CODE INTELLIGENCE

bash

# Install globally
npm install -g @agentics.org/agentic-mcp

# Or as a project dependency
npm install @agentics.org/agentic-mcp

FIELD OPERATIONS

Autonomous Customer Support Hub

Build a system where an initial 'triage' agent greets users. Based on the query ('I need a refund' vs. 'How do I use feature X?'), it transfers control to a specialized 'refunds' agent with access to a payments API or a 'documentation' agent with access to a vector database of help articles.

Real-time Market Research Agent

Create an agent that monitors news feeds and social media for keywords. When a keyword is found, it triggers a 'research' agent that uses the web search capability to generate a full report, summarizes it, and posts the summary to a designated Slack channel via API.

STRATEGIC APPLICATIONS

→Automate internal IT support by deploying an agent network that can handle password resets, software installation requests, and access provisioning by interacting with internal APIs, escalating to a human only for complex issues.
→Enhance a SaaS product with a proactive 'onboarding concierge' agent. The agent monitors new user activity and if they seem stuck, it uses its context to offer help, fetch relevant documentation, or schedule a support call via a calendar API.