Versatile-Mcp
by MSelcukAkbas
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| RAG_N_CTX | No | Context size for the RAG model | 2048 |
| RAG_TOP_K | No | Number of top results to retrieve in RAG | 5 |
| MCP_DATA_DIR | No | Directory for MCP data storage | .data |
| RAG_N_THREADS | No | Number of threads for RAG computation | 4 |
| MCP_DB_TIMEOUT | No | Timeout in seconds for database operations | 30 |
| RAG_CHUNK_SIZE | No | Chunk size for RAG document splitting | 512 |
| REMOTE_LOG_DIR | No | Directory for storing remote operation logs | ./logs/remote |
| RAG_N_GPU_LAYERS | No | Number of GPU layers for model acceleration | 0 |
| RAG_CHUNK_OVERLAP | No | Overlap between chunks in RAG | 64 |
| EMBEDDING_MODEL_PATH | No | Path to the embedding model file for hybrid RAG | resources/models/embedding_model.gguf |
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/MSelcukAkbas/versatile-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server