Local LLM MCP Tool
by Marcel-MSC
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| N_THREADS | No | Number of CPU threads | 4 |
| MODEL_PATH | Yes | Path to your GGUF model file | |
| CONTEXT_SIZE | No | Maximum context window size | 2048 |
| N_GPU_LAYERS | No | GPU layers (use -1 for all, 0 for CPU only) | 0 |
| SESSION_AUTO_TRIM | No | Automatically trim history when limits exceeded | true |
| STREAMING_ENABLED | No | Enable streaming responses (tokens sent incrementally) | false |
| SESSION_HISTORY_DIR | No | Directory for storing conversation history | history |
| SESSION_MAX_MESSAGES | No | Maximum messages per session (older messages trimmed) | 40 |
| STREAMING_CHUNK_SIZE | No | Approximate chunk size for streaming (characters) | 50 |
| SESSION_MAX_FILE_BYTES | No | Maximum size per session file (bytes) | 2097152 |
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
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
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/Marcel-MSC/local-llm-mcp-tool'
If you have feedback or need assistance with the MCP directory API, please join our Discord server