Schema | AI App MCP

AI App MCP

Describes the environment variables required to run the server.

Name	Required	Description	Default
`MCP_LOG_LEVEL`	No	Log level.	INFO
`MCP_SERVER_NAME`	No	The name of the MCP server.	ai-app-mcp
`MCP_KNOWLEDGE_DIR`	No	Directory containing knowledge files.	./knowledge
`MCP_MAX_TEXT_CHARS`	No	Maximum number of characters for text.	12000

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.

Features and capabilities supported by this server

Protocol revision2025-11-25

Capability	Details
`tools`	{ "listChanged": false }
`prompts`	{ "listChanged": false }
`resources`	{ "subscribe": false, "listChanged": false }
`experimental`	{}

Functions exposed to the LLM to take actions

Name	Description
health_checkA	Return server health and runtime configuration.
normalize_user_queryC	Normalize user text before retrieval, routing, or agent planning.
search_knowledge_baseC	Search local knowledge files by keyword.
get_documentB	Read a document from the configured knowledge directory.
build_rag_promptB	Build a grounded RAG prompt from a question and retrieved context.

Interactive templates invoked by user choice

Name	Description
`rag_answer_prompt`	Reusable prompt template for grounded RAG answers.

Contextual data attached and managed by the client

Name	Description
`runtime_config`	Expose safe runtime configuration.

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

curl -X GET 'https://glama.ai/api/mcp/v1/servers/yh008/Mcp'

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