MCP Local LLM Server
by iagomussel
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MAX_TOKENS | No | Maximum tokens in response. Default: 256. | |
| MODEL_NAME | No | Model name to use. Examples: 'llama3', 'gpt-3.5-turbo', 'claude-3-haiku-20240307', 'gemini-1.5-flash'. | |
| OLLAMA_URL | No | URL of the Ollama server. Default is http://localhost:11434. | |
| TEMPERATURE | No | Temperature for response generation. Default: 0.7. | |
| LLM_PROVIDER | No | Select provider: 'ollama', 'openai', 'anthropic', or 'gemini'. Default is 'ollama'. | |
| GEMINI_API_KEY | No | API key for Google Gemini. | |
| OPENAI_API_KEY | No | API key for OpenAI. | |
| ANTHROPIC_API_KEY | No | API key for Anthropic. | |
| DISABLE_CHAT_SUMMARY_RULE | No | Set to 'true' to disable the chat_end_summary_rule prompt. |
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/iagomussel/mcp-local-llm'
If you have feedback or need assistance with the MCP directory API, please join our Discord server