agentforge-mcp
Refines prompts for Windsurf (Codeium), adapting to its directive-based style.
agentforge-mcp
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.
agentforge.sciscale.org · Quick start · npm

agentforge-mcp is the Model Context Protocol
server for AgentForge. One tool, one job: turn
a vague request into a sharp one.
Why
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.
Related MCP server: MCP Prompt Cleaner
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:
claude mcp add agentforge --env AGENTFORGE_API_KEY=af_your_key -- npx -y agentforge-mcpCursor / Windsurf / Claude Desktop — add to your MCP config
(~/.cursor/mcp.json, ~/.codeium/windsurf/mcp_config.json, etc.):
{
"mcpServers": {
"agentforge": {
"command": "npx",
"args": ["-y", "agentforge-mcp"],
"env": { "AGENTFORGE_API_KEY": "af_your_key" }
}
}
}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 | |
| — | Your task in plain language (1–4000 chars). Rough is fine. |
|
|
|
|
|
|
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.

→ Try it now at agentforge.sciscale.org
Paste a request, pick your target tool, copy the prompt — generation history and advanced modes included:

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 | |
| — | Required. Your API key. |
|
| Override the endpoint (rarely needed). |
Develop
npm install
npm run build # tsc -> dist/
node dist/index.js # runs on stdioLicense
MIT — see LICENSE.
agentforge-mcp is part of AgentForge — a SciScale studio product.
Available Tools
1 toolagentforge_refine_promptRefine a prompt with AgentForgeA
Turn a rough, plain-language coding request into a structured, tool-tuned prompt for an AI coding agent.
AgentForge extracts the real requirements, fills in missing edge cases, formats the prompt for the target agent's conventions, and runs it through a Quality Engine before returning it. Reach for this when a request is vague or under-specified and you want a sharper prompt before handing it to a coding agent.
Args:
request (string, required): the coding task in plain language, 1-4000 chars.
target_tool (string): one of claude-code, codex, cursor, aider, continue, windsurf, kimi, generic. Default: claude-code.
style (string): plan-first, direct-edit, or explore-first. Default: plan-first.
Returns the refined prompt as text. structuredContent additionally carries: { "prompt": string, "tier": "free" | "pro", "quality": { "score": number, "max_score": number, "passed": boolean } | null, "usage": { "used_today": number, "limit": number | null } }
Errors are returned as text, e.g.:
"API key not configured" — set AGENTFORGE_API_KEY.
"invalid or revoked API key" (401) — check the key at agentforge.sciscale.org.
"daily free limit reached" (429) — upgrade to Pro for unlimited calls.
| Name | Required | Description | Default |
|---|---|---|---|
| request | Yes | The coding task or feature request, in plain language. Rough and under-specified is fine — that is exactly what gets refined. | |
| target_tool | No | The AI coding agent the prompt is formatted for. | claude-code |
| style | No | Execution style baked into the prompt: 'plan-first' plans before coding, 'direct-edit' makes the smallest change, 'explore-first' maps the codebase first. | plan-first |
Output Schema
| Name | Required | Description |
|---|---|---|
| prompt | Yes | The refined, tool-tuned prompt — hand this to your coding agent. |
| tier | Yes | Account tier that produced it: 'free' or 'pro'. |
| quality | Yes | Quality Engine score, or null if scoring was unavailable. |
| usage | Yes | Today's usage for this account; 'limit' is null for unlimited Pro. |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations convey side-effect potential (not readOnly, not destructive). Description adds context: uses API key, daily limit, quality engine. No contradiction with 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?
Well-structured with sections, bullet points, and front-loaded main action. A bit lengthy but every sentence adds value.
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?
Covers return format (text + structuredContent), errors, API usage, and all parameters. Output schema exists, so return detail is sufficient.
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 has 100% coverage with descriptions. Description adds extra nuance: 'request' accepts rough input, lists enum options for target_tool and style with explanations.
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?
Description clearly states verb 'refine', resource 'prompt', and the transformation from rough to structured. With no sibling tools, differentiation is not needed.
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 'Reach for this when a request is vague or under-specified'. Also lists error conditions. Lacks explicit when-not-to-use, but given no siblings, that is acceptable.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
1 tool update
v0.1.4- First observed
agentforge_refine_prompt
TDQS
With only one tool, there is no possibility of confusion between tools. The single tool has a clear, distinct purpose.
The single tool name 'agentforge_refine_prompt' follows a consistent verb_noun pattern with a server prefix. As there is only one tool, naming consistency is perfect.
Having a single tool is appropriate for the focused purpose of prompt refinement, but it falls on the low end of the typical well-scoped range (3-15 tools). The server could potentially benefit from a few related tools, but the current count is not problematic.
The tool fully covers its domain: it refines a coding request with parameters for target tool and style, and returns the refined prompt along with quality and usage information. There are no obvious missing features for its stated purpose.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
Turn PRDs and product ideas into structured specs so coding agents build your intent, not theirs.
Lints + auto-fixes how AI coding agents discover any new product. 24 rules, 6 tools, score 0-100.
Production-readiness for your AI coding agents.
Codebase intelligence for agents: 152 structured artifacts across 21 programs, one call.
Related MCP Servers
- AlicenseBqualityDmaintenanceIntelligently engineers and optimizes prompts for Claude Code with automatic language detection, task type recognition, and interactive refinement capabilities. Works entirely offline without external API dependencies to transform natural language requests into structured, Claude Code-optimized prompts.412MIT
- AlicenseNot gradedqualityDmaintenanceEnhances and cleans raw prompts using AI to make them more clear, actionable, and effective. Provides quality assessment, suggestions, and supports both general and code-specific optimization modes.1MIT
- FlicenseAqualityCmaintenanceRefines and improves AI prompts using workspace-aware context from your project's tech stack, structure, and dependencies. Includes tools to analyze prompt quality and generate well-structured prompts from raw ideas.42095-
- AlicenseNot gradedqualityCmaintenanceTransforms static coding standards into a queryable live data store for AI agents, delivering task-specific rules and fix guidance on demand. This optimizes context window usage through progressive disclosure, ensuring agents apply relevant governance without loading massive documentation.2MIT
Appeared in Searches
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/sciscale-studio/agentforge-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server