MCP Long Context Reader
MCP Long Context Reader is a Python-based toolkit designed to overcome the context window limitations and high costs associated with Large Language Models (LLMs) processing extensive documents. It provides a FastMCP server with multiple, powerful strategies for an LLM agent to 'read' and query long documents without needing to load the entire text into its context window.
知识记忆 RAG
0 个平台
0 项功能
安装
uvx mcp-long-context-reader
把上面的配置写入 MCP 客户端的配置文件（Claude Desktop 为 claude_desktop_config.json），重启客户端后生效。
{
"mcpServers": {
"mcp-long-context-reader": {
"command": "uvx",
"args": [
"mcp-long-context-reader"
],
"env": {
"MCP_LLM_MODEL": "<MCP_LLM_MODEL>",
"OPENAI_API_KEY": "<OPENAI_API_KEY>",
"MCP_API_PROVIDER": "<MCP_API_PROVIDER>",
"DASHSCOPE_API_KEY": "<DASHSCOPE_API_KEY>",
"MCP_CACHE_DIRECTORY": "<MCP_CACHE_DIRECTORY>",
"MCP_EMBEDDING_MODEL": "<MCP_EMBEDDING_MODEL>",
"OPENAI_API_BASE_URL": "<OPENAI_API_BASE_URL>",
"MCP_WORKSPACE_DIRECTORY": "<MCP_WORKSPACE_DIRECTORY>"
}
}
}
}把上面的配置写入 MCP 客户端的配置文件（Claude Desktop 为 claude_desktop_config.json），重启客户端后生效。
数据来源：公开的 MCP Server 目录。本站为独立第三方目录，与各 MCP Server 维护方均无隶属或背书关系；名称与简介如实标注，介绍文案由本站再加工。
