SKILLEMALL.ai
GitHub ↗ RU Sign in

AC mcp-builder

Bootstraps new Model Context Protocol (MCP) servers from a natural language description. Use when the user asks to build an MCP server, create an MCP tool, scaffold an MCP integration, or add MCP capabilities to an existing project. NOT for: general API design, non-MCP tool building, or frontend tasks.

ClawHub Agent Skills author: Tony Simons v1.0.0 MIT-0 2 files body ≈ 410 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process C 59/100 · Has gaps — weak spots: inputs and preconditions, failures and branches, consistency

IntegrationAI and agentstype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
A
96/100
safety, quality, tests
Safety 60%
100
Quality 40%
89
Run on models
none yet
Process rating
C
59/100
Has gaps
Inputs and preconditions w 11
0
Failures and branches w 10
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten

How to improve

    For the model run — optional
    • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
    • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

    Guard findings · 0

    ✓ No critical or high findings

    Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • note frontmatter-key unknown frontmatter key "source"
    • note frontmatter-key unknown frontmatter key "agency_score"

    Process rating: all ten parameters 59/100

    • 0Inputs and preconditions. Does not say what the process needs to start
    • 0Failures and branches. Linear process with no failure handling
    • 0Progress reporting. Says nothing while it works
    • 40Consistency. Frontmatter name (mcp-builder) differs from the folder (agentic-atlas-mcp-builder)
    • 60Tools and files. Uses tools (python) that frontmatter does not declare
    • 60Result and completion. Output format stated, no completion criterion
    • 100Steps. 16 steps
    • 100When it triggers. States when to use and when not to
    • 100Execution cost. Instruction body is 410 tokens
    • 100Running it twice. No mutating operations

    Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

    Quality signals

    • +5Description has no quoted example phrases that should trigger the skill
    • +1No license
    • +2Single-language instructions
    • +4Description says when NOT to use the skill
    • +3Description length 303: enough signal without eating the budget
    • +4Structure: 7 headings
    • +3Step-by-step instructions: 16 items
    • +3Output format is stated explicitly
    • +4Has examples (2 code blocks)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.

    External checks

    ClawHub: clean
    This instruction-only skill is aligned with its stated purpose of generating MCP server scaffolds and does not request credentials, persistence, or hidden access.
    LLM: benign (high) · VirusTotal: · 29 May 2026