Schema | local-rag-mcp

local-rag-mcp

Describes the environment variables required to run the server.

Name	Required	Description	Default
`MCP_HOST`	No	SSE 监听地址	127.0.0.1
`MCP_PORT`	No	SSE 监听端口	8042
`LOG_LEVEL`	No	日志级别	INFO
`EMBED_TIMEOUT`	No	Embedding 请求超时（秒）	60.0
`MCP_TRANSPORT`	No	传输模式: `sse` (守护进程) 或 `stdio` (子进程)	sse
`EMBED_BASE_URL`	No	Ollama Embedding 服务地址	http://localhost:11434
`RAG_CHUNK_SIZE`	No	分块大小（字符数）	600
`EMBED_MODEL_NAME`	No	Embedding 模型名称 (1024 维)	bge-m3
`RAG_PROJECT_PATH`	Yes	文档项目目录，启动时自动加载索引 + 文件监控
`RAG_CHUNK_OVERLAP`	No	块间重叠（字符数）	60
`RAG_HYBRID_WEIGHT`	No	混合检索权重 (0=纯BM25, 1=纯向量)	0.7
`RAG_WATCH_DEBOUNCE`	No	文件监控防抖间隔（秒）	1.0

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Server capabilities have not been inspected yet.

Functions exposed to the LLM to take actions

Name	Description
No tools

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/junchenghe01/local-rag-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server