feat: Use llm.txt for doc reference. rewrite this pr to include searc…

[JackYPCOnline]

Use llm.txt for doc reference. rewrite this pr to include search doc based on frequency and relevance & fetch doc from uri.

Example:

from mcp import stdio_client, StdioServerParameters
from strands import Agent
from strands.tools.mcp import MCPClient


stdio_mcp_client = MCPClient(lambda: stdio_client(
    StdioServerParameters(
        command="python",
        args=["-m", "strands_mcp_server"],
    )
))

with stdio_mcp_client:

    tools = stdio_mcp_client.list_tools_sync()
    print(f"Found {len(tools)} tools: {[tool.tool_name for tool in tools]}")

    agent = Agent(
        tools=tools,
        model="anthropic.claude-3-5-sonnet-20241022-v2:0"
    )

    result = agent("tell me about agent to agent")

#Response:

[08/19/25 10:56:07] INFO     Processing request of type ListToolsRequest                                                                                                                                                                                                                                    server.py:624
Found 2 tools: ['search_docs', 'fetch_doc']
I'll search the documentation for information about agent to agent communication or interactions.
Tool #1: search_docs
[08/19/25 10:56:10] INFO     Processing request of type CallToolRequest                                                                                                                                                                                                                                     server.py:624
Let me fetch the full content of the Agent2Agent (A2A) documentation to provide more detailed information.
Tool #2: fetch_doc
[08/19/25 10:56:13] INFO     Processing request of type CallToolRequest                                                                                                                                                                                                                                     server.py:624
Based on the documentation, I can provide a comprehensive overview of Agent-to-Agent (A2A) functionality:

Agent-to-Agent (A2A) is an open standard protocol that enables seamless communication between AI agents across different platforms and implementations. Here are the key aspects: ....................

Issue #, if available:

Description of changes:

By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.

[JackYPCOnline]

This PR Idea is from: #19 & https://github.com/strands-agents/mcp-server/pull/16/files#diff-f4b60e9da664fbce692fa02c180e3d7381a83eccdfdec27b6cabe284c81b5f4f

[JackYPCOnline]

For change in this file, I just copy pasted from our repo to revert

[JackYPCOnline]

remove this to avoid eager import.