Turn rough requests into rigorously structured prompts, for any coding agent.
org.sciscale/agentforge-mcp — Model Context Protocol (MCP) Server
org.sciscale/agentforge-mcp (agentforge-mcp) is an MCP server that turns rough requests into rigorously structured prompts for any coding agent. It is associated with the agentforge.sciscale.org service and the npm package “agentforge-mcp,” described as producing tool-tuned prompts executable in one pass.
🛠️ Key Features
Converts rough sentences into structured prompts
Produces tool-tuned prompts for coding agents
Implements Model Context Protocol (MCP)
Tagged for agentforge, ai-coding-tools, claude-code, and cursor
🚀 Use Cases
Provide a single rough request and receive a structured prompt
Prepare prompts specifically for AI coding workflows
Use with developer tools and coding agents
⚡ Developer Benefits
Reduces re-explaining intent to an AI coding agent
Returns a structured prompt in one step
⚠️ Limitations
Description does not specify supported tools, integrations, authentication, or exact input/output schema beyond “rough requests” and “structured prompts.”
Stop re-explaining what you want to your AI coding agent.
Hand it one rough sentence — get back a structured, tool-tuned prompt
it can execute in one pass.
You know the loop: you ask your coding agent for something, it misreads the half
you didn't spell out, you correct it, it breaks something else, you re-explain.
The fix isn't a smarter agent — it's a sharper prompt.
AgentForge does the prompt engineering for you. Give it
"add a dark mode toggle that persists" and it:
extracts the real requirements — the edge cases, the acceptance criteria,
the things you'd have forgotten to mention;
formats for your specific agent — Claude Code wants file:line references,
Cursor wants directives, Aider wants tight context;
quality-checks before returning — every prompt is scored across 12
dimensions before it leaves the engine.
Harness engineering is having a moment — but prompt engineering matters more
in the coding-agent era, not less. Tested across 1,000+ real coding cases,
projects with AgentForge in the loop reached a deployable state 147% faster.
Quick start
No install — it runs through npx.
1. Get an API key. Sign in at
agentforge.sciscale.org, open API keys,
and create one. The key is shown once — copy it.
2. Add it to your agent.
Claude Code:
sh
claude mcp add agentforge --env AGENTFORGE_API_KEY=af_your_key -- npx -y agentforge-mcp
Cursor / Windsurf / Claude Desktop — add to your MCP config
(~/.cursor/mcp.json, ~/.codeium/windsurf/mcp_config.json, etc.):
3. Use it. Ask your agent naturally — "refine this with AgentForge, then
build it: add a dark mode toggle that persists."
The tool — agentforge_refine_prompt
Argument
Default
request
—
Your task in plain language (1–4000 chars). Rough is fine.
target_tool
claude-code
claude-code, codex, cursor, aider, continue, windsurf, kimi, generic
style
plan-first
plan-first, direct-edit, explore-first
Returns the refined prompt, plus its Quality Engine score and your remaining
daily usage.
Free vs Pro
Free
Pro
Refinements
3 / day
Unlimited
Quality Engine
scored across 12 dimensions
scored + auto-refined until it passes ≥ 90
Or use the web app
Don't want to wire up an MCP server at all? The same engine — same Quality
Engine, same per-account Pro — runs right in your browser at
agentforge.sciscale.org. No install, no
key, no config.
Paste a request, pick your target tool, copy the prompt — generation history and
advanced modes included:
The web app in action
How it works
agentforge-mcp is a thin client — no engine logic ships in this package. Your
request goes to the AgentForge API, the hosted engine does the extraction,
formatting, and quality-checking, and the prompt comes back. The engine keeps
improving without you ever updating this package.
Configuration
Variable
Default
AGENTFORGE_API_KEY
—
Required. Your API key.
AGENTFORGE_API_URL
https://agentforge.sciscale.org/api/v1/refine
Override the endpoint (rarely needed).
Develop
sh
npm install
npm run build # tsc -> dist/
node dist/index.js # runs on stdio