一个上下文高效的MCP服务器，支持大胆、非常规且突破边界的问题解决。

这是一个基于TypeScript的MCP服务器，基于Anthropic最新的MCP架构模式，实现了针对**上下文空间节省*优化的非常规思维系统。它在保持效率的同时生成并跟踪创造性的问题解决方案。

MCP 规范 2025-11-25 合规 — 使用 @modelcontextprotocol/sdk v1.27.1，工具 title、annotations、outputSchema、structuredContent 响应和 resource_link 内容类型。

建筑：保存上下文的设计

本服务器展示了Anthropic推荐的模式，用于减少98.7%的上下文开销**：

关键的上下文保存功能

1. 按需数据加载资源API

• 思维内容以资源形式存储（[thought://id）
• Claude 仅在明确需要时加载完整内容
• 元数据默认返回，保存令牌

2. 服务器端过滤

• search_thoughts 在本地过滤数据，而不是将未过滤的集合传递给 Claude
• 仅返回匹配结果，而非整个数据集
• 通过源过滤减少上下文消耗

Unconventional Thinking Server (v0.3.0)

A context-efficient MCP server for bold, unconventional, and boundary-breaking problem-solving.

This is a TypeScript-based MCP server that implements an unconventional thinking system optimized for context space savings based on Anthropic’s latest MCP architecture patterns. It generates and tracks creative solutions to problems while maintaining efficiency.

MCP spec 2025-11-25 compliant — uses @modelcontextprotocol/sdk v1.27.1 with tool title, annotations, outputSchema, structuredContent responses, and resource_link content type.

Architecture: Context-Saving Design

This server demonstrates Anthropic’s recommended patterns for reducing context overhead by 98.7%:

Key Context-Saving Features

1. Resources API for On-Demand Data Loading

   • Thought content is stored as resources (thought://id)
   • Claude loads full content only when explicitly needed
   • Metadata is returned by default, saving tokens

2. Server-Side Filtering

   • search_thoughts filters data locally instead of passing unfiltered sets to Claude
   • Only matching results returned, not entire dataset
   • Reduces context consumption by filtering at the source

3. Metadata-First Returns

   • Tools return only essential metadata + resource URIs
   • Full thought content accessible via Resources API
   • Claude decides whether to fetch full content based on need

4. Persistent File-Based Storage

   • Data persists in .thoughts/ directory
   • No in-memory bloat accumulating across sessions
   • Easy to inspect and debug thoughts locally

Features

Tools (All Context-Efficient, MCP spec 2025-11-25)

Each tool now includes:

• title — human-readable display name shown in client UIs
• annotations — behaviour hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint)
• outputSchema — JSON Schema describing the structured result
• structuredContent in responses — machine-readable output conforming to the schema
• resource_link content items — explicit links clients can subscribe to or fetch

---

• generate_unreasonable_thought — Generate new unconventional thoughts

  • Returns resource_link + structuredContent, not raw text blobs
  • Can build upon or rebel against previous thoughts
  • Full thought content available via Resources API

• branch_thought — Create new branches of thinking

  • Supports directions: more_extreme, opposite, tangential (now enum-typed)
  • Returns resource_link + structuredContent for the new branch

• search_thoughts — Efficient metadata search

  • Filters by branchId, isRebellion, challengesAssumption
  • Returns structuredContent with typed count + thoughts array
  • Includes limit parameter to control result size

Resources (On-Demand Content Loading)

• Each thought available as a resource: thought://[thoughtId]
• Metadata includes: isRebellion, challengesAssumption, timestamp, branch info