agentfetch
by SID1ART
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| REDIS_URL | No | Redis connection for caching + job queue | |
| OLLAMA_URL | No | Ollama endpoint for local LLM extraction | |
| SEARXNG_URL | No | SearXNG instance for search (falls back to DuckDuckGo) | |
| OLLAMA_MODEL | No | Ollama model name | llama3.2 |
| AGENTFETCH_PORT | No | API server port | 8080 |
| ANTHROPIC_API_KEY | No | For Claude-powered agent_extract | |
| AGENTFETCH_CACHE_TTL | No | Cache TTL in seconds | 3600 |
| AGENTFETCH_PROXY_LIST | No | Comma-separated proxy URLs or JSON array | |
| AGENTFETCH_MAX_RETRIES | No | Max retries for failed requests | 2 |
| AGENTFETCH_COOKIES_FILE | No | Path to cookies file (Netscape or JSON) | |
| AGENTFETCH_DOMAIN_DELAY | No | Delay between requests to same domain | 0.5 |
| AGENTFETCH_ROBOTS_CHECK | No | Enable robots.txt compliance | false |
| AGENTFETCH_PROXY_STRATEGY | No | round-robin or random | round-robin |
| AGENTFETCH_STATIC_TIMEOUT | No | HTTP fetch timeout (seconds) | 15 |
| AGENTFETCH_BROWSER_TIMEOUT | No | Playwright browser timeout (seconds) | 30 |
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
ActivityInactive
ResponsivenessNo issues