Argus Retrieval runs on your own machine — the client starts it, so there is no endpoint to ping. 131 installs a week from pypi. Last commit 1 Nov 2026.
Multi-provider search broker for AI agents: 14 providers, 12-step extraction, retrieval workflows.
We read the source, 1 d ago · rules 995398eba69f
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
process = subprocess.Popen(
with patch.dict(os.environ, auth_environment):
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add argus -- uvx argus-search
{
"mcpServers": {
"argus": {
"command": "uvx",
"args": [
"argus-search"
]
}
}
}
[mcp_servers.argus]
command = "uvx"
args = ["argus-search"]
{
"mcpServers": {
"argus": {
"command": "uvx",
"args": [
"argus-search"
]
}
}
}
{
"servers": {
"argus": {
"type": "stdio",
"command": "uvx",
"args": [
"argus-search"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
ARGUS_WOLFRAM_API_KEY (WolframAlpha App ID (2,000 free computed-answer queries/month)), ARGUS_BRAVE_API_KEY (Brave Search API key (2,000 free queries/month)), ARGUS_TAVILY_API_KEY (Tavily API key (1,000 free queries/month)), ARGUS_EXA_API_KEY (Exa API key (1,000 free queries/month)), ARGUS_SERPER_API_KEY (Serper API key (2,500 one-time free queries)), ARGUS_LINKUP_API_KEY (Linkup API key (1,000 free queries/month)), ARGUS_SEARXNG_BASE_URL (SearXNG instance URL (self-hosted, aggregates 70+ engines)), ARGUS_DATA_ROOT (Optional override for the writable Argus runtime corpus root).
Persistent state for AI agent workflows. Save, resume, and replay multi-step workflows.
Web data extraction and browser workflows for AI assistants.
Search and retrieve agent instruction files: system prompts, skills, workflows, and safety filters.
Shared versioned state for multi-agent AI workflows
MCP State Sidecar: durable state persistence for multi-agent AI workflows
Store, retrieve, and pin encrypted files on IPFS via MCP tools for AI agents and workflows
MCP server for agent task workflows with phases, prompts, gates, and multi-agent coordination
Agent Workflow Engine — multi-step MCP workflows with per-step directives and validation.
Answers built from our own checks of this server.