llm-localfirst
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LF_PROBE_TTL | No | Seconds to cache the reachability probe | 30.0 |
| OPENAI_API_KEY | No | OpenAI API key if using OpenAI cloud provider | |
| LF_REASON_MODEL | No | Cloud model for kind='reason' | haiku |
| ANTHROPIC_API_KEY | No | Anthropic API key for cloud fallback/reason | |
| LF_FALLBACK_MODEL | No | Cloud model for non-sensitive fallback | haiku |
| LF_LOCAL_BASE_URL | No | Local OpenAI-compatible endpoint | http://localhost:11434/v1 |
| LF_LOCAL_MODEL_ID | No | Local model id | qwen2.5:7b |
| LF_SENSITIVE_FAIL_CLOSED | No | Keep sensitive calls from ever leaking | true |
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/shaxzodbek-uzb/llm-localfirst'
If you have feedback or need assistance with the MCP directory API, please join our Discord server