promptforge
Prompt Forge MCP Server
Generate deployment-ready AI agent system prompts directly from Claude Code, Claude Desktop, or any MCP client.
MCP Quick Install
Claude Code:
claude mcp add --transport stdio promptforge -- npx -y promptforge-mcpClaude Desktop — add to claude_desktop_config.json:
{
"mcpServers": {
"promptforge": {
"command": "npx",
"args": ["-y", "promptforge-mcp"]
}
}
}Related MCP server: agency-mcp-server
MCP Tools
Tool | Description |
| Generate a deployment-ready system prompt for any agent role using the MCP SDK |
| Browse 251 agents across 41 industries |
| List all 41 industries with agent counts and Pro/Free status |
About
Prompt Forge is an AI agent system prompt generator built on the Model Context Protocol (MCP). It exposes three MCP tools that give Claude Code and other MCP clients direct access to a library of 251 professional agent archetypes across 41 industries.
Unlike static prompt libraries, it generates fresh, deployment-ready system prompts on demand using the Anthropic Claude API.
251 agents across 41 industries (Finance, Healthcare, Cybersecurity, Legal, and more)
MCP server published to npm as
promptforge-mcpWeb interface at getpromptforge.net
Web Application
The MCP server is backed by a Next.js web application. See mcp-server/README.md for full MCP documentation.
License
MIT
Available Tools
3 toolsgenerate_promptA
Generate a deployment-ready AI agent system prompt using Prompt Forge's v2 engine. Returns a complete 8-section system prompt (Identity, Capabilities, Guidelines, Domain Knowledge, Interaction Protocol, Output Format, Constraints, First Message). Requires ANTHROPIC_API_KEY environment variable.
Inputs: agent_name (required), industry, agent_desc, user_context.
list_agentsA
List all 251 Prompt Forge agents grouped by industry. Returns agent names and descriptions. Use this to discover available agents before calling generate_prompt.
Inputs: search, industry.
list_industriesA
List all 41 Prompt Forge industries with agent counts and Pro-only status.
Inputs: no named parameters.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 3 tools
Each tool has a clearly distinct purpose: generating prompts, listing agents, and listing industries. No overlap or ambiguity.
All tool names follow a consistent verb_noun pattern using snake_case (generate_prompt, list_agents, list_industries).
Three tools is a compact but reasonable set for a focused prompt generation server, covering the essential workflow without being too sparse.
The tool set covers the core tasks: discovering industries and agents and generating a prompt. A minor gap might be a 'get_agent' tool for more detail, but not essential.
Maintenance
Related MCP Connectors
Contextual prompts and agent skills for 140+ AI platforms.
Your prompt library inside your AI: 1,000+ pro templates, frameworks, vocab & pipelines.
Read-only catalog of 1,900+ real, sourced AI agent use cases with tools, cost and setup prompts.
A growing library of AI agents and growth tools for agencies, in any AI assistant.
Related MCP Servers
- AlicenseAqualityDmaintenanceFinancial intelligence for AI agents. 31 tools across 8 data sources — regime, derivatives, stablecoin flows, momentum, volatility, macro, DeFi, weather patterns, political cycles, seasonality. The context layer between your agent and a bad trade.3122 npm9MIT
- AlicenseAqualityDmaintenanceOn-demand access to 150+ specialist AI agent templates — search, browse, and spawn agents. 150x reduction in context usage vs loading agents locally.4103 npm1MIT
- AlicenseAqualityDmaintenanceProvides AI agents with structured knowledge about 67+ generative AI models, including model recommendations, prompt formatting, parameter guidance, and validation. It acts as a prompt engineering co-pilot that helps agents use their existing tools more effectively.12120 npm3MIT
- AlicenseAqualityDmaintenanceCommunity-driven library of tested prompts for AI agents, enabling search, retrieval, sharing, and rating of prompts.514 PyPIMIT