omoshiro-mcp
omoshiro-mcp
基于研究的MCP服务器,用于分析有趣性 / 面白さ。
此服务器不对内容进行评分。它返回评估视角、概念边界、交互模式和研究参考,以便调用AI自行进行分析。
原则
返回评估视角;不对内容进行评分。
本体论区分了:
原始视角:AI可以直接检查或相对于受众模型构建的视角
衍生动态:随时间变化,如预测误差或不确定性减少
复合状态/机制:兴趣、好奇心、悬念、幽默、洞察、心流、敬畏、沉浸
结果:享受、注意力、记忆、学习、坚持等。
这避免了将所有内容归结为一个无意义的interestingness_score。
Related MCP server: AI Evaluator MCP Server
MCP端点
部署在Vercel上时,使用:
https://<your-project>.vercel.app/mcp协议:MCP Streamable HTTP / JSON-RPC。
工具
get_lenses
返回针对目标的一组精选原始视角。
示例参数:
{
"target_type": "oogiri",
"analysis_goal": "humor"
}search_lenses
通过自然语言术语搜索原始和复合结构。
{
"query": "unexpected but understandable"
}get_lens
返回原始视角的定义、诊断问题、概念边界、适用性和可推断性。
{"id":"novelty"}get_composite
返回复合机制/状态及其输入结构。
{"id":"suspense"}list_ontology
列出完整的本体论和核心参考文献。
核心原始视角
当前v0.1版本包含21个原始视角:
novelty
complexity
comprehensibility
processing_fluency
relevance
information_gap
knowability
uncertainty
expectation_strength
outcome_significance
conflict_instability
violation
benignness
vastness
accommodation_demand
challenge
competence
control
autonomy
feedback_clarity
relatedness
衍生动态
prediction_error
information_gain
uncertainty_reduction
gap_resolution
conflict_resolution
comprehension_gain
fluency_gain
mastery_progress
复合机制/状态
interest
curiosity
suspense
humor_benign_violation
humor_incongruity_resolution
insight
flow
awe
transportation
复合不是一个分数。例如:
Interest ≈ novelty/complexity × sufficient comprehensibility
Curiosity ≈ information gap × knowability × relevance × uncertainty
Suspense ≈ uncertainty × expectation strength × outcome significance
Benign-violation humor ≈ violation × benignness
Awe ≈ vastness × accommodation demand这些是概念模式,而非经过验证的通用公式。
可推断性
每个视角包含一个inferability字段:
direct:通常可以直接从内容本身检查audience_model_required:依赖于先验知识、文化、体裁期望等experience_required:没有受众/玩家证据时,不应断言实际心理状态
例如,novelty是相对于受众的,而实际的flow或transportation不能仅通过阅读作品可靠地断言。
示例工作流程
用户问:
こんなエンジニアは嫌だ。どんなエンジニア?
回答:キーボードがでかすぎて部屋に入らない
调用AI:
调用
get_lenses({ target_type: "oogiri", analysis_goal: "humor" })接收视角,如
expectation_strength、violation、benignness、novelty、comprehensibility、processing_fluency自行执行实际分析
不要求MCP输出幽默分数
研究基础
v0.1本体论基于以下工作:
Silvia, P. J. (2005). What Is Interesting? Exploring the Appraisal Structure of Interest. Emotion.
Loewenstein, G. (1994). The Psychology of Curiosity: A Review and Reinterpretation. Psychological Bulletin.
Kang, M. J. et al. (2009). The Wick in the Candle of Learning: Epistemic Curiosity Activates Reward Circuitry and Enhances Memory. Psychological Science.
Reber, R., Schwarz, N., & Winkielman, P. (2004). Processing Fluency and Aesthetic Pleasure. Personality and Social Psychology Review.
McGraw, A. P. & Warren, C. (2010). Benign Violations: Making Immoral Behavior Funny. Psychological Science.
Keltner, D. & Haidt, J. (2003). Approaching Awe, a Moral, Spiritual, and Aesthetic Emotion. Cognition and Emotion.
Ryan, R. M., Rigby, C. S., & Przybylski, A. (2006). The Motivational Pull of Video Games. Motivation and Emotion.
Busselle, R. & Bilandzic, H. (2009). Measuring Narrative Engagement. Media Psychology.
该本体论是对这些文献的工程综合,并非声称某篇论文定义了完整结构。
开发
该服务器有意保持轻依赖,并作为Vercel无服务器端点在api/mcp.js中实现。
对/mcp的GET请求返回服务器元数据。MCP客户端应使用POST JSON-RPC请求进行initialize、tools/list和tools/call。
许可证
MIT
This server cannot be installed
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 Servers
- Alicense-qualityCmaintenanceAn MCP server that evaluates whether retrieval methods and AI outputs are grounded in long narrative manuscripts by retrieving evidence and scoring coverage deterministically, without external model APIs. It provides tools for chunking, indexing, retrieval, and evaluation.1MIT
- Alicense-qualityDmaintenanceA comprehensive framework for evaluating AI responses using Inspect AI and Petri-style behavioral assessment patterns. Built as an MCP server for real-time evaluation during AI development.MIT
- AlicenseAqualityAmaintenanceAn MCP server that evaluates claims by counting independent story origins, giving AI agents a verdict on reporting corroboration rather than truth.2981MIT
- Alicense-qualityDmaintenanceA hosted MCP server that supplies ten channels of short-form content (stories, puzzles, jokes, etc.) for AI briefing agents to embed in daily emails to humans.MIT
Related MCP Connectors
MCP server providing access to the Scorecard API to evaluate and optimize LLM systems.
Hosted MCP server for creators: writing analysis, headline scoring, reading time, social lengths.
MCP server for Grok Imagine AI video generation
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/take-code-0427/omoshiro-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server