MCPサーバー

whycant

            io.github.sattyamjjain/whycant
        

AI・エージェント公開・接続可能 MCP 2025-11-25

このMCPでできること

Evaluates AI agent ideas with readiness scores, risk findings, verdicts, and shareable published result pages.

browse_explore

Browse the public roast corpus

Page through existing public roasts (the /explore feed) with their shareable /result URLs. Optional free-text query and sort (newest | top | money). Read-only, no rate-limit cost â use it to see whether an idea was already roasted before minting a new one.

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {'sort': {'enum': ['newest', 'top', 'money'], 'type': 'string', 'description': 'Sort order. Default: newest.'}, 'limit': {'type': 'integer', 'maximum': 20, 'minimum': 1, 'description': 'Max 20. Default 10.'}, 'query': {'type': 'string', 'description': 'Free-text filter over name/problem.'}}}

get_stats

Public roast-corpus stats

Live public numbers for whycantwehaveanagentforthis.com: total ideas roasted, live results, % told to ship, % that already exist, roast battles, and how many roasts came in via MCP. Read-only, no rate-limit cost.

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}}

get_verdict

Look up an existing verdict

Fetch a verdict that was already minted, by its result id or slug. Read-only â no new analysis, no rate-limit cost. Returns the same structured verdict shape as roast_idea.

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['id'], 'properties': {'id': {'type': 'string', 'description': 'The /result/[id] id or slug returned by a prior roast_idea call.'}}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['agentName', 'verdict', 'verdictLabel', 'readinessScore', 'readinessBand', 'topRiskCode', 'topRiskTitle', 'percentileFraming', 'savageLine', 'resultUrl', 'scopeCallUrl'], 'properties': {'verdict': {'type': 'string', 'description': 'Real VerdictTier enum value, e.g. SHUT_UP_AND_TAKE_MY_MONEY'}, 'agentName': {'type': 'string'}, 'resultUrl': {'type': 'string', 'description': 'Canonical /result/[id] share URL'}, 'savageLine': {'type': 'string'}, 'topRiskCode': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'description': 'Top OWASP-MCP risk code, e.g. MCP-3'}, 'scopeCallUrl': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'description': 'Cal.com 20-min scope-call URL'}, 'topRiskTitle': {'anyOf': [{'type': 'string'}, {'type': 'null'}]}, 'verdictLabel': {'type': 'string'}, 'readinessBand': {'type': 'string', 'description': 'Letter band A-F'}, 'readinessScore': {'type': 'number', 'description': 'Agent-readiness 0-100'}, 'percentileFraming': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'description': '"You\'re the X% whoâ\x80¦" line'}}, 'additionalProperties': False}

roast_idea

Roast an AI agent idea

Get the full whycantwehaveanagentforthis.com roast for an AI agent idea: the verdict tier, an agent-readiness score (0-100 + band), the top OWASP-MCP security risk, the "you're the X% whoâ¦" framing, and a shareable /result URL. Every call mints a real, persistent result page (its own OG share card) â so roasting from your IDE also publishes it. Anonymous (no token): 3/hour, 10/day. Add a token for higher limits.

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['idea'], 'properties': {'idea': {'type': 'string', 'description': 'The agent idea or problem to analyze, in one or two sentences. e.g. "an agent that auto-declines pointless meetings".'}}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['agentName', 'verdict', 'verdictLabel', 'readinessScore', 'readinessBand', 'topRiskCode', 'topRiskTitle', 'percentileFraming', 'savageLine', 'resultUrl', 'scopeCallUrl'], 'properties': {'verdict': {'type': 'string', 'description': 'Real VerdictTier enum value, e.g. SHUT_UP_AND_TAKE_MY_MONEY'}, 'agentName': {'type': 'string'}, 'resultUrl': {'type': 'string', 'description': 'Canonical /result/[id] share URL'}, 'savageLine': {'type': 'string'}, 'topRiskCode': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'description': 'Top OWASP-MCP risk code, e.g. MCP-3'}, 'scopeCallUrl': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'description': 'Cal.com 20-min scope-call URL'}, 'topRiskTitle': {'anyOf': [{'type': 'string'}, {'type': 'null'}]}, 'verdictLabel': {'type': 'string'}, 'readinessBand': {'type': 'string', 'description': 'Letter band A-F'}, 'readinessScore': {'type': 'number', 'description': 'Agent-readiness 0-100'}, 'percentileFraming': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'description': '"You\'re the X% whoâ\x80¦" line'}}, 'additionalProperties': False}

追加

                            browse_explore
                        

2026年9月17日12:52

追加

                            get_stats
                        

2026年9月17日12:52

追加

                            get_verdict
                        

2026年9月17日12:52

追加

                            roast_idea
                        

2026年9月17日12:52

サーバー情報

バージョン

0.6.0

通信方式

Streamable HTTP

ツール

レイテンシ

3106 ms

最終スキャン

2026年10月1日2:50

初回確認

2026年9月13日2:23

エンドポイント

https://whycantwehaveanagentforthis.com/api/mcp

whycant

このMCPでできること

ツール

最近のツール変更

類似のMCPサーバー

Andreax

GPT55 Model Gateway

GoCreative Agent API

IA-QA — 130+ QA & Dev Tools for AI Agents

Speedbot Autonomous Work Network

H/M Blindspot Challenge Platform

NOT FOR HUMANS

Agent^Rider