search_webLABSCO SUMMARY
Extraction that knows when it got half the article.
Completeness assessment runs after every successful extraction, scoring signals like trailing ellipses, feed truncation markers and mid-sentence endings, and returning whether the text is complete with a confidence value. Above 85% confidence it keeps trying the next extractor instead of handing back a partial page — which is the difference between a research pack built on articles and one built on RSS teasers. The other structural decision worth understanding: budgets, sessions and evidence live in the HTTP authority, so restarting the MCP adapter cannot fork the accounting.
What it is
A retrieval platform for AI agents. It routes queries across search providers by tier — free ones first, budget-exhausted ones skipped automatically — extracts full page text rather than links, recovers dead URLs, and writes what it finds into a local corpus with traceable artifacts. The MCP server is a stateless adapter over its authenticated HTTP API.
What you get
- Web search with provider fusion, restrictable to free tier-0 providers only, and optional per-provider score attribution on each result —
search_web - Full text from a URL with a completeness assessment attached, and link expansion —
extract_content,expand_links - Recovery when a URL is dead, paywalled or radically changed, using Wayback Machine and archive fallbacks —
recover_url - Three workflows that produce local artifacts, not just responses: recover a dead article with a citation-backed report, capture the important pages of a site on-domain, and build a docs-plus-research pack —
recover_dead_article,capture_site,build_research_pack - Operational reads: provider health and remaining budgets —
search_health,search_budgets - Four search modes selecting provider order within each tier: discovery, research, recovery and grounding
- Multi-turn sessions through a session id, so follow-up searches are refined by earlier context
Requirements
Zero-key to start: pip install argus-search gives you DuckDuckGo and Yahoo with no accounts. Python 3.11 or higher. For MCP, pipx install argus-search[mcp] then argus mcp init --global --client all, which writes native configs for Claude Code, Codex CLI, OpenCode and Cursor. Production MCP delegates to an authenticated HTTP authority — set ARGUS_AUTHORITY_URL and ARGUS_AUTHORITY_TOKEN; a local broker requires ARGUS_MCP_STANDALONE set to true and is rejected in production. Provider keys are all optional and named per provider, including ARGUS_BRAVE_API_KEY, ARGUS_TAVILY_API_KEY and ARGUS_WOLFRAM_API_KEY. Remote transports need ARGUS_API_KEY. The package is argus-search (version 1.6.4); status is beta.
Setup effort
One command — pipx install 'argus-search[mcp]'
USE CASES
01
Searching without paying for it
Restrict the query to free tier-0 providers, so an agent can run continuously without burning API credits.
02
Getting the article, not the link
Extract the page text and read the completeness assessment before treating it as the full piece.
03
Recovering something that 404s
Run recovery against the dead URL, and use the workflow when you want a saved report and manifest rather than a one-off response.
04
Building a reference pack on an unfamiliar library
Capture the official documentation site on-domain and combine it with non-official sources into one research pack on disk.
05
Refining a search over several turns
Pass a session id so follow-up queries are informed by the earlier ones instead of starting cold.
12 tools
Listed in project docs. Your client may show a different list.
extract_contentrecover_urlexpand_linkssearch_healthsearch_budgetsrecover_dead_articlecapture_sitebuild_research_packtest_providercookie_healthvalyu_answerBEFORE YOU INSTALL
What to know first
Tools you get
12 tools named in the project's documentation.
Requires
- argus on PATH (pipx install 'argus-search[mcp]')
- Python 3.11+
- No keys for the local development broker (ARGUS_MCP_STANDALONE=true)
- Against a production Argus authority: ARGUS_AUTHORITY_URL and ARGUS_AUTHORITY_TOKEN; the remote HTTP blocks also need ARGUS_API_KEY
INSTALLATION
Connect your client
Server setup
TERMINAL
pipx install 'argus-search[mcp]'MCP Clients
Claude Code
CLAUDE CODE · JSON
{
"mcpServers": {
"argus": {
"type": "http",
"url": "http://<YOUR_SERVER>:<YOUR_PORT>/mcp",
"headers": {
"Authorization": "Bearer <YOUR_ARGUS_API_KEY>"
}
}
}
}Codex
CODEX · TOML
[mcp_servers.argus]
command = "argus"
args = ["mcp", "serve"]
[mcp_servers.argus.env]
ARGUS_MCP_STANDALONE = "true"OpenCode
OPENCODE · JSON
{
"mcp": {
"argus": {
"type": "remote",
"url": "http://<YOUR_SERVER>:<YOUR_PORT>/mcp",
"enabled": true,
"headers": {
"Authorization": "Bearer <YOUR_ARGUS_API_KEY>"
}
}
}
}Cursor
CURSOR · JSON
{
"mcpServers": {
"argus": {
"command": "argus",
"args": [
"mcp",
"serve"
],
"env": {
"ARGUS_MCP_STANDALONE": "true"
}
}
}
}Gemini CLI
GEMINI CLI · TERMINAL
gemini mcp add argus http://<YOUR_SERVER>:<YOUR_PORT>/mcp -t http -H "Authorization: Bearer <YOUR_ARGUS_API_KEY>"Antigravity
ANTIGRAVITY · JSON
{
"mcpServers": {
"argus": {
"serverUrl": "http://<YOUR_SERVER>:<YOUR_PORT>/mcp",
"headers": {
"Authorization": "Bearer <YOUR_ARGUS_API_KEY>"
}
}
}
}
