AgentForge MCP server
org.sciscale/agentforge-mcp·v0.1.4·2 starsTurn rough requests into rigorously structured prompts, for any coding agent.
2 stars35 downloads/wk
Reviews
Write oneNobody has reviewed AgentForge yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
AgentForge tools (1)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
agentforge_refine_prompt
Public scan report
scanner v0.1.9 · 2026-09-27 · same rubric, same numbers if you re-run it
- Code scan3 source files scanned25/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitystatic API keys via environment variables6/15
- Maintenancelast push 122 days ago8/15
- Maintainer identitynamespace and repository owner differ; website matches verified namespace6/10
How AgentForge compares
Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 69/100
- higher than 35% of 4,460 AI and agents servers
- Tools
- 1
- the typical AI and agents server has 6
- Tools that change things
- 0%
- typical: 0%. Fewer write tools means less an agent can break
- GitHub stars
- 2
- more than 65% of 2,711 AI and agents servers
- Downloads a week
- 35
- more than 25% of 1,538 AI and agents servers with a package
What its tools let an agent do: 1 read
Install AgentForge in Claude Code, Cursor or VS Code
Runs npx -y agentforge-mcp on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add agentforge-mcp -- npx -y agentforge-mcp
What the publisher says
From the AgentForge repository's README, as published. We do not edit it. Read it on GitHub
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:
the things you'd have forgotten to mention;
- extracts the real requirements — the edge cases, the acceptance criteria,
Cursor wants directives, Aider wants tight context;
- formats for your specific agent — Claude Code wants file:line references,
dimensions before it leaves the engine.
- quality-checks before returning — every prompt is scored across 12
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:
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 — agentforgerefineprompt
Returns the refined prompt, plus its Quality Engine score and your remaining daily usage.
Free vs Pro
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
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
AgentForge: common questions
- Is AgentForge MCP server safe?
- With care: it is graded C, so read the findings first (69/100). Read the AgentForge safety report
- How do I install AgentForge?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does AgentForge need an API key?
- Yes. The registry entry asks for
AGENTFORGE_API_KEY. - Is AgentForge maintained?
- The last commit was 160 days ago (2026-05-28). The latest release is v0.1.4.
- What can I use instead of AgentForge?
- Servers from other publishers that do the same job: Serena MCP: the IDE for your agent MCP server, Figma Context MCP server and Agent-Native Plan MCP server.
- How does AgentForge compare with other AI and agents MCP servers?
- safety score 69/100 (higher than 35% of 4,460 AI and agents servers); tools 1 (the typical AI and agents server has 6); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.
Alternatives to AgentForge
Same job from other publishers: the closest match first, then the best rated.
- Serena MCP: the IDE for your agentA powerful toolkit for coding, providing semantic retrieval and editing capabilities.not reviewedWidely usedC
- Figma ContextGive your coding agent access to your Figma data. Implement designs in any framework in one-shot.not reviewedWidely usedB
- Agent-Native PlanStructured visual plans and PR recaps with diagrams, prototypes, annotations, and sharingnot reviewedEstablishedA
- SuperCompressCompress coding-agent context ~64%. Hosted Neural Keep MCP for Cursor/Claude/Codex.not reviewedEstablishedB
- ImageAI image generation and editing with prompt optimization and quality presetsnot reviewedEstablishedB