Local Realtime Search
by MirLunaDEV
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| FETCHER | No | Fetcher to use: auto, http, or crawl4ai. Default is auto | auto |
| CACHE_PATH | No | Path to the SQLite cache file | |
| LOCAL_TIMEZONE | No | Timezone for direct date/time answers | |
| LM_STUDIO_MODEL | No | Exact model ID loaded in LM Studio | |
| SEARXNG_BASE_URL | No | Base URL of the SearXNG instance. Default is http://127.0.0.1:8080 | http://127.0.0.1:8080 |
| LM_STUDIO_BASE_URL | No | Base URL of the LM Studio API. Default is http://127.0.0.1:1234/v1 | http://127.0.0.1:1234/v1 |
| LM_STUDIO_MAX_TOKENS | No | Max generation tokens for answer synthesis. Default is '4096' | 4096 |
| SEARCH_TIMEOUT_SECONDS | No | Timeout for search engine queries. Default is '5.0' | 5.0 |
| RESOLVE_FETCH_HOSTNAMES | No | Resolve hostnames before fetching to block private-network DNS targets. Default is 'true' | true |
| WEATHER_TIMEOUT_SECONDS | No | Timeout for conditional wttr.in weather lookups | |
| SYNTHESIS_TIMEOUT_SECONDS | No | Timeout for answer synthesis. Default is '180' | 180 |
| ALLOW_PRIVATE_NETWORK_FETCH | No | Set to 'true' to allow fetching private network URLs. Default is 'false' | false |
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 | |
This server cannot be deployed
Maintenance
ActivitySlowing
ResponsivenessNo issues