pantheon-mcp
by valado
README.md
# Agents 🤖
A collection of AI agents for various tasks.
## Getting Started 🚀
Welcome to the agents repository! This project contains various AI agent definitions. The definitions can be used by any agentic system that supports markdown.
# Pantheon-MCP Server for Agents

[Homepage](https://pantheon-mcp.com)
An MCP (Model Context Protocol) server that delivers AI agent instructions on demand from this repository's collection of 42+ specialized agents.
```json
{
"mcpServers": {
"pantheon-mcp": {
"type": "stdio",
"command": "npx",
"args": ["-y", "pantheon-mcp"],
"env": {}
}
}
}
```
## Available Tools
The server exposes 3 MCP tools:
### `list_agents`
List all available agents, optionally filtered by category.
```json
{
"name": "list_agents",
"arguments": {
"category": "tech" // optional: business, growth, product, tech
}
}
```
### `get_agent`
Get detailed information about a specific agent by name.
```json
{
"name": "get_agent",
"arguments": {
"name": "react-frontend-dev"
}
}
```
### `search_agents`
Search agents by keywords in name, description, or instructions.
```json
{
"name": "search_agents",
"arguments": {
"keywords": "react",
"category": "tech" // optional filter
}
}
```
## Agent Categories
- **business** (6 agents): business-analyst, cfo-financial-analyzer, compliance-officer, financial-analyst, sales-strategist, startup-mentor
- **growth** (5 agents): conversion-optimizer, growth-marketer, idea-visionary, marketing-copywriter, marketing-strategist
- **product** (3 agents): product-designer, product-manager, product-strategist
- **tech** (28 agents): accessibility-auditor, ai-prompt-engineer, api-designer, aws-cloud-architect, code-reviewer, react-frontend-dev, and many more...
## Installation
To install globally:
```bash
npm install -g pantheon-mcp
npx pantheon-mcp
```
## Development
```bash
npm install
npm run build
npm run dev
```
---
Built with ❤️ and AI
TDQS
A3.7/5.0
Scored across 3 tools
Disambiguation5/5
Each tool targets a distinct operation: retrieving a specific agent by name, listing all agents, and searching by keywords. No overlap in purpose.
Naming Consistency5/5
All tool names follow a consistent verb_noun pattern with snake_case: get_agent, list_agents, search_agents. Perfectly uniform.
Tool Count4/5
Three tools cover the essential query operations for agents. Slightly low count, but well-scoped for a read-only agent directory.
Completeness3/5
Covers retrieval and search but lacks creation, update, or deletion tools. May be intentional for a read-only surface, but from a general perspective, CRUD operations are missing.
Maintenance
ActivityInactive
ResponsivenessNo issues