AI App MCP
Server Configuration
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 |
Instructions
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.
Capabilities
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 | {} |
Tools
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. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| rag_answer_prompt | Reusable prompt template for grounded RAG answers. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| runtime_config | Expose safe runtime configuration. |
TDQS
Scored across 5 tools
All tools have distinct roles: search and get_document are clearly separate (search vs. reading full doc), build_rag_prompt and normalize_user_query serve different pipeline stages, and health_check is standalone. Slight potential confusion exists between search_knowledge_base and get_document, but descriptions resolve this.
All tool names follow a consistent verb_noun snake_case pattern: search_knowledge_base, get_document, build_rag_prompt, normalize_user_query, health_check. The pattern is predictable and readable.
Five tools is a well-scoped count for a RAG-focused server. Each tool serves a clear purpose in the pipeline, and the count feels neither too thin nor overly heavy.
The set covers the core RAG flow (normalize, search, retrieve, build prompt) plus health check. Missing operations like adding/updating knowledge base documents or a combined retrieve tool, but these are minor gaps for the apparent scope.