sifthound
by khsarvar
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| API_KEYS | No | Optional comma-separated list of API keys. If empty, authentication is disabled. | |
| SEARXNG_URL | No | URL of the SearXNG instance used for search results. | http://localhost:8080 |
| ANSWER_MODEL | No | Model used for generating answers when include_answer is requested. | |
| ANSWER_EFFORT | No | Effort level for answer generation. | |
| FETCH_TIMEOUT | No | Timeout in seconds for fetching pages. | |
| ANSWER_ENABLED | No | Toggle for the answer feature (e.g., 'true' or 'false'). | |
| CRAWL_MAX_LIMIT | No | Maximum number of pages to crawl or map. | |
| FETCH_MAX_BYTES | No | Maximum bytes to fetch per page. | |
| ANTHROPIC_API_KEY | No | Optional Anthropic API key used when requests set include_answer. | |
| FETCH_CONCURRENCY | No | Maximum number of concurrent fetches. | |
| MCP_ALLOWED_HOSTS | No | Comma-separated list of hostnames the MCP endpoint will respond to besides localhost (e.g., 'search.example.com,search.example.com:*'). | |
| ALLOW_PRIVATE_NETWORKS | No | Set to 'true' to allow fetching private, loopback, or link-local addresses. Defaults to '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
ActivityMaintained
ResponsivenessNo issues