是时候突破MCP服务器了…右？

让我们拆解MCP、CLI、文件系统脚本和基于技能的方法之间在构建可重用AI代理工具集时的真实工程权衡。

观看完整视频解析：超越MCP

这次回收的目的

• MCP 服务器是构建可重用工具集的标准方式。但它们并非唯一方式。
• MCP服务器成本巨大——即时上下文丢失。
• 当你只有一个或几个MCP服务器时，这并不算大问题。但随着你扩展到许多代理、许多工具和多种上下文，这种成本很快就会成为瓶颈。
• 那么，大型企业正在使用哪些替代方案来为他们的AI代理构建强大、可重复使用、保持上下文的工具集？

Here我们在本次仓库中探讨了4种具体方法，均实现了Kalshi预测市场的访问data.

四种方法

apps/1_mcp_server/ - MCP 服务器

apps/2_cli/ - CLI

apps/3_file_system_scripts/ - 文件系统脚本

apps/4_skill/ - 技巧

快速启动

1.MCP服务器

2.CLI

3.文件系统脚本

4.技能

Beyond MCP

It’s time to push beyond MCP Servers… Right?

Let’s breakdown real engineering trade offs between MCP, CLI, File System Scripts, and Skills based approaches for building reusable toolsets for your AI Agents.

Watch the full video breakdown here: Beyond MCP

Purpose of this Repo

• MCP Servers are the standard way to build reusable toolsets for your AI Agents. But they are not the only way.
• MCP Servers come with a massive cost - instant context loss.
• When you have a single, or a few MCP Servers, this is not a big deal. But as you scale to many agents, many tools, and many contexts - this cost quickly becomes a bottleneck.
• So what are the alternatives that big players are using to build powerful, reusable, context preserving toolsets for their AI Agents?

Here we explore 4 concrete approaches in this repo, all implementing access to Kalshi prediction market data.

The 4 Approaches

apps/1_mcp_server/ - MCP Server

apps/2_cli/ - CLI

apps/3_file_system_scripts/ - File System Scripts

apps/4_skill/ - Skill

Quick Start

1. MCP Server

cp .mcp.testing .mcp.json

claude --mcp-config .mcp.json

prompt: "kalshi: get exchange status"

2. CLI

# or by agent
claude

prompt: "/prime_kalshi_cli_tools"

prompt: "kalshi: Get exchange status"

prompt: "kalshi: List events"

prompt: "kalshi: List events in JSON"

prompt: "kalshi: List events in JSON, limit 100"

# or by hand
cd apps/2_cli
uv sync
uv run kalshi status
uv run kalshi events
uv run kalshi events --json
uv run kalshi events --json --limit 100

3. File System Scripts

# by agent
claude

prompt: "/prime_file_system_scripts"

prompt: "kalshi: Get exchange status"

prompt: "kalshi: List events"

...

# or by hand
cd apps/3_file_system_scripts/scripts

uv run status.py

uv run *.py

4. Skill

cd apps/4_skill/

claude

prompt: "kalshi markets: Get exchange status"

prompt: "kalshi markets: search for events about 'best ai'" # Note this will trigger the cache build on first run which will take several minutes

...

The 4 Approaches In Detail

• apps/1_mcp_server/ - MCP Server
• apps/2_cli/ - CLI
• apps/3_file_system_scripts/ - File System Scripts
• apps/4_skill/ - Skill

1. MCP Server (apps/1_mcp_server/)

Classic Model Context Protocol implementation

• ✅ Standardized integration - Works with any MCP-compatible client
• ✅ Tool discovery - Auto-exposes 15 tools to LLMs
• ✅ Clean abstractions - MCP protocol handles complexity
• ❌ Instant context loss - Every tool call loses conversational context