mcp-llm-offload
by seaosinc
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LLM_MODEL | No | Default model id as the provider names it. | |
| XAI_MODEL | No | Default model for xAI Grok provider. | |
| GROQ_MODEL | No | Default model for Groq provider. | |
| LLM_API_KEY | No | Generic fallback API key for the default provider. | |
| LLM_TIMEOUT | No | Request timeout in seconds. Default is 300. | |
| XAI_API_KEY | No | API key for xAI Grok. | |
| GROQ_API_KEY | No | API key for Groq. | |
| LLM_BASE_URL | No | Generic fallback base URL for the default provider. | |
| LLM_PROVIDER | No | Default provider name (e.g., lmstudio, ollama, openrouter, grok, openai, groq, together, deepinfra, mistral). Default is lmstudio. | |
| OLLAMA_MODEL | No | Default model for Ollama provider. | |
| OPENAI_MODEL | No | Default model for OpenAI provider. | |
| MISTRAL_MODEL | No | Default model for Mistral AI provider. | |
| LLAMACPP_MODEL | No | Default model for llama.cpp provider. | |
| LMSTUDIO_MODEL | No | Default model for LM Studio provider. | |
| OPENAI_API_KEY | No | API key for OpenAI. | |
| TOGETHER_MODEL | No | Default model for Together AI provider. | |
| DEEPINFRA_MODEL | No | Default model for DeepInfra provider. | |
| MISTRAL_API_KEY | No | API key for Mistral AI. | |
| OLLAMA_BASE_URL | No | Override endpoint for Ollama provider. | |
| OPENROUTER_MODEL | No | Default model for OpenRouter provider. | |
| OPENROUTER_TITLE | No | Optional OpenRouter ranking header for title. | |
| TOGETHER_API_KEY | No | API key for Together AI. | |
| DEEPINFRA_API_KEY | No | API key for DeepInfra. | |
| LLAMACPP_BASE_URL | No | Override endpoint for llama.cpp provider. | |
| LMSTUDIO_BASE_URL | No | Override endpoint for LM Studio provider. | |
| OPENROUTER_API_KEY | No | API key for OpenRouter. | |
| OPENROUTER_REFERER | No | Optional OpenRouter ranking header for referer. | |
| OPENROUTER_BASE_URL | No | Override endpoint for OpenRouter provider. |
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
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
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- 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/seaosinc/mcp-llm-offload'
If you have feedback or need assistance with the MCP directory API, please join our Discord server