Argus
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ARGUS_API_KEY | No | Require API key on all endpoints (health exempt) | |
| ARGUS_DB_PATH | No | Unified SQLite database (search, budgets, sessions, extraction cache) | argus.db |
| ARGUS_RATE_LIMIT | No | Requests per window per client IP | 60 |
| ARGUS_EXA_API_KEY | No | Exa API key | |
| ARGUS_CORS_ORIGINS | No | Allowed CORS origins (comma-separated, `*` allows all) | * |
| ARGUS_JINA_API_KEY | No | Jina Reader key (optional) | |
| ARGUS_BRAVE_API_KEY | No | Brave Search API key | |
| ARGUS_SERPER_API_KEY | No | Serper API key | |
| ARGUS_TAVILY_API_KEY | No | Tavily API key | |
| ARGUS_CACHE_TTL_HOURS | No | Result cache TTL | 168 |
| ARGUS_LOG_FULL_RESULTS | No | Dumps everything at debug level if needed | |
| ARGUS_SEARXNG_BASE_URL | No | SearXNG endpoint | http://127.0.0.1:8080 |
| ARGUS_RATE_LIMIT_WINDOW | No | Rate limit window (seconds) | 60 |
| ARGUS_REMOTE_EXTRACT_KEY | No | API key for the remote extraction service | |
| ARGUS_REMOTE_EXTRACT_URL | No | Remote auth extraction service URL (enables Playwright-based extraction for paywall domains) | |
| ARGUS_REMOTE_EXTRACT_TIMEOUT | No | Timeout (seconds) for remote extraction requests | 35 |
| ARGUS_EXTRACTION_CACHE_TTL_HOURS | No | Extraction cache TTL | 168 |
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
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_webC | Search the web using the Argus broker. |
| recover_urlC | Recover a dead, moved, or unavailable URL. |
| expand_linksC | Expand a query with related links for discovery. |
| extract_contentA | Extract clean text content from a URL. Pass domain for authenticated extraction on paywall sites. |
| valyu_answerB | Get an AI-synthesized answer with citations. Uses Valyu Answer API ($0.10+/request). |
| argus_pathsA | Show the resolved Argus runtime storage paths. |
| recover_dead_articleC | Recover a dead article into a local report with citations. |
| capture_siteC | Capture the important parts of a site and summarize them. |
| build_research_packC | Build a local pack with official docs plus external research. |
| search_healthB | Get health status of all search providers. |
| search_budgetsB | Get budget status for all providers. |
| test_providerC | Smoke-test a single provider. |
| cookie_healthA | Get health status of all configured cookie domains. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| provider_status | Current status of all search providers. |
| provider_budgets | Budget status for all providers. |
| routing_policies | Current routing policies for each search mode. |
| corpus_paths | Resolved Argus runtime storage paths. |
TDQS
Scored across 13 tools
Most tools have distinct purposes, but the pair recover_dead_article and recover_url could cause confusion, as both deal with recovery. Descriptions help differentiate, but slight overlap remains.
The majority follow a verb_noun pattern (e.g., search_web, capture_site). Three tools (argus_paths, cookie_health, valyu_answer) deviate with noun_noun patterns, but the inconsistency is minor.
With 13 tools, the set covers essential research and archiving tasks without being overwhelming. Each tool feels justified for the domain.
Core workflows (search, capture, extract, recover, ask) are covered. Minor gaps exist, like missing management of saved packs, but these are not critical for the intended use.