Generate deployment-ready AI agent system prompts directly from Claude Code, Claude Desktop, or any MCP client.
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
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 |
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-mcp
Web interface at getpromptforge.net
The MCP server is backed by a Next.js web application. See mcp-server/README.md for full MCP documentation.
MIT
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.
| Name | Required | Description | Default |
|---|---|---|---|
| industry | No | Industry context (e.g. "Finance", "Healthcare"). Helps the engine reference industry-specific tools and frameworks. | |
| agent_desc | No | Short description of the agent specialty (e.g. "Automated scoring, loan analysis"). If omitted and agent_name matches a registry agent, the registry description is used. | |
| agent_name | Yes | The agent role name (e.g. "Credit Risk Underwriter", "Medical Scribe", "SOC Analyst Agent"). Can be any role — not limited to the built-in registry. | |
| user_context | No | Your role and situation for personalization (e.g. "I'm a solo financial advisor serving retirees in Florida"). Pro feature on the web app, available to all MCP users. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must cover behavioral traits. It states the tool requires an API key and returns an 8-section prompt, but it does not disclose side effects (e.g., if it makes external API calls), safety implications, or whether it is read-only. Some key behavioral context is missing.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two short sentences. The first sentence immediately states the purpose and output, and the second adds the key requirement. There is no wasted text, and the structure is front-loaded for quick understanding.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description outlines the output structure (8 sections) and the environment variable requirement, providing good context for a tool with no output schema. However, it could be more complete by specifying the return type (e.g., string or object) and any additional details about the generation process.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
All four parameters have descriptions in the input schema (100% coverage), so the schema already explains parameter meaning. The description adds context about the API key requirement and the output structure, but does not provide additional semantics beyond what the schema offers, resulting in a baseline score of 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool generates a deployment-ready AI agent system prompt using the v2 engine. It specifies the exact output (8-section system prompt) and distinguishes it from sibling tools (list_agents, list_industries) which only retrieve lists, not generate prompts.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description mentions the requirement of the ANTHROPIC_API_KEY environment variable, giving clear usage context. However, it does not explicitly state when not to use this tool or suggest alternative approaches, leaving a gap in guidance for the AI agent.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List all 251 Prompt Forge agents grouped by industry. Returns agent names and descriptions. Use this to discover available agents before calling generate_prompt.
| Name | Required | Description | Default |
|---|---|---|---|
| search | No | Search agents by name or description keyword (e.g. "compliance", "SEO"). | |
| industry | No | Filter to a specific industry (e.g. "Finance", "Healthcare"). Omit to list all industries. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must fully disclose behavioral traits. It only says 'list' and 'returns', implying a read operation, but does not explicitly state it's non-destructive, safe, or disclose any side effects, rate limits, or authentication needs.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, front-loaded with the core purpose and result. Every sentence adds value; no fluff.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the low complexity (2 optional params, no output schema), the description is complete. It mentions the count 251, the grouping, and the return fields, which suffices for an agent to use the tool correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema covers 100% of parameter descriptions, so baseline is 3. The description does not add extra meaning beyond the schema; it only reiterates the grouping by industry, which is already implied by the 'industry' parameter.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool lists all 251 Prompt Forge agents grouped by industry, and returns agent names and descriptions. It differentiates from sibling 'generate_prompt' by indicating its use before that tool.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly says to use this tool to discover agents before calling generate_prompt, providing clear usage context. However, it does not mention when not to use it or explicitly reference the sibling 'list_industries'.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List all 41 Prompt Forge industries with agent counts and Pro-only status.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description bears full responsibility for behavioral disclosure. It mentions the output includes agent counts and Pro-only status but fails to disclose non-obvious traits like rate limits, authentication needs, or whether the operation is read-only. This is a significant gap for a tool with no annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that is concise, front-loaded with the key action and resource, and contains no superfluous information. Every word contributes to understanding the tool's purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (0 parameters, no output schema), the description adequately conveys what the tool returns. However, it could mention that it is a read operation or provide the output format. Still, it is largely complete for its minimal complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
No parameters exist, so schema coverage is 100%. The description adds value by specifying the returned data (agent counts, Pro-only status) beyond the empty schema, making the tool's output clear. This justifies a score above the baseline of 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (list), the resource (industries), and the specific fields returned (agent counts, Pro-only status). It effectively distinguishes from sibling tools generate_prompt and list_agents, which have different purposes.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies the tool is for listing industries, but it does not explicitly provide when to use it versus alternatives like list_agents. There is no usage guidance or exclusion criteria, leaving the agent to infer context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
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.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Your prompt library inside your AI: 1,000+ pro templates, frameworks, vocab & pipelines.
Agent-native security, trust, reliability, data and procurement tools for AI workflows.
150+ vertical AI expert bots as agent tools. $1 bots run on YOUR machine - your data stays yours.
Sovereign Agent OS — Persistent Memory, Governance & Compliance for AI Agents.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/ChillZone2025/prompt-forge'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
