Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

MCP Wizard — measured AI agent skill | DecimalAI

loocor/mcp-wizard

NewSkillScoreMaintained

Generate MCP server drafts from requirements.

agent-toolingby loocor

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

AI Engineer pack

1 · One-time — install the CLI (docs ↗)

pip install decimalai

2 · Get the skill — writes .claude/skills/loocor-mcp-wizard/SKILL.md

decimalai skills pull loocor-mcp-wizard --out .claude/skills/

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/loocor-mcp-wizard/SKILL.md https://app.decimal.ai/s/loocor-mcp-wizard/SKILL.md

Raw file: /s/loocor-mcp-wizard/SKILL.md ↗ · machine-readable summary at /s/loocor-mcp-wizard.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 4h ago

Yes — +9% lift-53% tokens0% turns23% of whole cases pass with skill (5/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-20	✗→✓	▲ Improved	-70%	0%
case-05	✗→✓	▲ Improved	-20%	0%
case-15	✗→✓	▲ Improved	-51%	0%
case-19	✗→✓	▲ Improved	-46%	0%
case-22	✗→✓	▲ Improved	9%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

loocor / codmate

payload/internal-skills/mcp-wizard/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 8/3/2026Version v1

Skill contents

SKILL.md

MCP Wizard

Overview

Generate a CodMate MCP server draft based on user intent. Output only JSON that matches the schema.

Instructions

Determine server kind (stdio, sse, streamable_http).
Provide command/args/env for stdio, or url/headers for network kinds.
If unclear, return mode "question" with follow-up questions.

Output

Return only JSON.

Want to see if loocor/mcp-wizard would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.