curl -LsSf https://astral.sh/uv/install.sh | sh

uvx --from mcpdoc mcpdoc \
    --urls LangGraph:https://langchain-ai.github.io/langgraph/llms.txt \
    --transport sse \
    --port 8082 \
    --host localhost

npx @modelcontextprotocol/inspector

{
  "mcpServers": {
    "langgraph-docs-mcp": {
      "command": "uvx",
      "args": [
        "--from",
        "mcpdoc",
        "mcpdoc",
        "--urls",
        "LangGraph:https://langchain-ai.github.io/langgraph/llms.txt",
        "--transport",
        "stdio",
        "--port",
        "8081",
        "--host",
        "localhost"
      ]
    }
  }
}

use the langgraph-docs-mcp server to answer any LangGraph questions -- 
+ call list_doc_sources tool to get the available llms.txt file
+ call fetch_docs tool to read it
+ reflect on the urls in llms.txt 
+ reflect on the input question 
+ call fetch_docs on any urls relevant to the question
+ use this to answer the question

what are types of memory in LangGraph?

claude mcp add-json langgraph-docs '{"type":"stdio","command":"uvx" ,"args":["--from", "mcpdoc", "mcpdoc", "--urls", "langgraph:https://langchain-ai.github.io/langgraph/llms.txt"]}' -s local

$ Claude
$ /mcp 

mcpdoc --yaml sample_config.yaml

mcpdoc --json sample_config.json

mcpdoc --urls LangGraph:https://langchain-ai.github.io/langgraph/llms.txt

mcpdoc --yaml sample_config.yaml --json sample_config.json --urls https://langchain-ai.github.io/langgraph/llms.txt

mcpdoc --yaml sample_config.yaml --follow-redirects --timeout 15

# Sample configuration for mcp-mcpdoc server
# Each entry must have a llms_txt URL and optionally a name
- name: LangGraph Python
  llms_txt: https://langchain-ai.github.io/langgraph/llms.txt

[
  {
    "name": "LangGraph Python",
    "llms_txt": "https://langchain-ai.github.io/langgraph/llms.txt"
  }
]

from mcpdoc.main import create_server

# Create a server with documentation sources
server = create_server(
    [
        {
            "name": "LangGraph Python",
            "llms_txt": "https://langchain-ai.github.io/langgraph/llms.txt",
        },
        # You can add multiple documentation sources
        # {
        #     "name": "Another Documentation",
        #     "llms_txt": "https://example.com/llms.txt",
        # },
    ],
    follow_redirects=True,
    timeout=15.0,
)

# Run the server
server.run(transport="stdio")