Provides a secure MCP server with a WARDEN firewall to vet third-party tools and an optional blockchain-based economy for agent capabilities.
Also known as alexar76/argus, argus, @alexar76/argus3
- Stars
- 1
- Tools
- 3
- Downloads, 30 days
- 1,141
- Latest version
- 0.4.0
- Last commit
- Nov 15, 2026
- License
- MIT
What is ARGUS-3 MCP?
ARGUS-3 provides a secure MCP server with a WARDEN firewall to vet third-party tools and an optional blockchain-based economy for agent capabilities. It exposes 3 tools, such as argus_ask, argus_status, argus_capabilities.
Summary generated from the project's README
About ARGUS-3 MCP server
ARGUS-3 is a security-focused MCP server designed to protect users from malicious third-party tools. It functions as a demand-side client that can be integrated into hosts like Claude Desktop or Cursor via stdio. The server uses a WARDEN firewall to vet every incoming MCP server through a multi-stage process including static scans, threat feeds, and origin checks before any tool definitions reach the model. This prevents issues like tool poisoning or credential harvesting.
Beyond security, the server includes an optional blockchain-based economy for discovering and paying for agent capabilities using USDC on Base. This economic layer is disabled by default and only activates when a user provides a wallet and enables the crypto setting. Even without a wallet or network connection, the server remains fully functional as a local assistant by connecting to any provider, including local Ollama instances or OpenAI-compatible endpoints. It includes specific tools like argus_ask for bounded natural language tasks and argus_status for checking system liveness.
What you can do with it
- 1Secure third-party tool executionA developer can run untrusted MCP servers knowing the WARDEN firewall will vet them before execution.
- 2Budgeted natural language processingAn AI client can perform complex tasks while staying within strict token and cost limits.
- 3Autonomous local assistanceUsers can operate a secure assistant entirely offline using local models without any API keys.
Written from the project's README. Every use case is checked against a quote from it.
How to install ARGUS-3 MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall ARGUS-3 MCP in Claude Code
$ claude mcp add argus -- npx -y @alexar76/argus3 mcpInstall ARGUS-3 MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"argus": {
"command": "npx",
"args": [
"-y",
"@alexar76/argus3",
"mcp"
]
}
}
}Install ARGUS-3 MCP in VS Code
.vscode/mcp.json
{
"servers": {
"argus": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@alexar76/argus3",
"mcp"
]
}
}
}Install ARGUS-3 MCP in VS Code CLI
$ code --add-mcp '{"name":"argus","type":"stdio","command":"npx","args":["-y","@alexar76/argus3","mcp"]}'Install ARGUS-3 MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"argus": {
"command": "npx",
"args": [
"-y",
"@alexar76/argus3",
"mcp"
]
}
}
}Install ARGUS-3 MCP in Codex
$ codex mcp add argus -- npx -y @alexar76/argus3 mcpInstall ARGUS-3 MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.argus] command = "npx" args = ["-y", "@alexar76/argus3", "mcp"]
Install ARGUS-3 MCP in Gemini CLI
$ gemini mcp add -s user argus npx -- -y @alexar76/argus3 mcpInstall ARGUS-3 MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"argus": {
"command": "npx",
"args": [
"-y",
"@alexar76/argus3",
"mcp"
]
}
}
}Started by HostedMCP on 16 Nov 2026
We ran this command for @alexar76/argus3 0.4.0 in an isolated container with no network and no keys. It answered and listed 3 tools.
ARGUS-3 MCP tools 3
Read from the server with tools/listargus_askActionRun one bounded natural-language task through the ARGUS-3 agent and return the final answer text. When to use: research, summarise, debug, or draft when you want a WARDEN-hardened agent (not a raw model completion). Prefer argus_status first if you only need liveness; prefer argus_capabilities for the tool/WARDEN catalog without spending LLM tokens. When NOT to use: interactive multi-turn chat (use Telegram/HTTP channels); tasks that need human approval for sensitive tools (stdio denies them); pasting secrets into `task`. Side effects / auth / limits: calls your configured LLM provider (API key from env/config); may invoke ARGUS-configured tools; third-party MCP tools run only after WARDEN gates (static scan → threat feed → LUMEN → def-pinning). Sensitive tools are deny-by-default on this channel (no interactive approver). Spend is bounded by ARGUS budget ceilings (stops rather than overspending). Not idempotent — each call is a new metered run. May use network (model + allowed tools). Returns: plain-text final answer. On failure or budget stop, text may still be returned with isError true. No streaming / partial events on this tool. Example: argus_ask({ task: "Summarise https://example.com in three bullets", response_format: "bullets" })
argus_statusRead-onlyReturn ARGUS-3 MCP runtime status as JSON text (no LLM call, no side effects). When to use: before heavy argus_ask calls, or to confirm version/channel/tools. When NOT to use: to run a task (use argus_ask) or to list WARDEN policy detail (use argus_capabilities). Auth / limits: none beyond MCP session. Idempotent and read-only. Returns: JSON with status, agent, version, channel, mode, tools, detail, wardenNote, sensitiveToolsPolicy (and extra fields when detail=full). Example: argus_status({ detail: "basic" })
argus_capabilitiesRead-onlyList ARGUS MCP tools and WARDEN security posture as JSON text (no LLM call). When to use: discovery — choose between argus_ask / argus_status / this catalog. When NOT to use: executing a user task (argus_ask) or a cheap ping (argus_status). Side effects: none. Read-only, idempotent, no provider auth required for this tool. Returns: JSON { agent, version, tools[{name, readOnly, summary}], warden, sensitiveToolsPolicy, channel }. Example: argus_capabilities({ include_schemas: false })
| argus_ask | Run one bounded natural-language task through the ARGUS-3 agent and return the final answer text. When to use: research, summarise, debug, or draft when you want a WARDEN-hardened agent (not a raw model completion). Prefer argus_status first if you only need liveness; prefer argus_capabilities for the tool/WARDEN catalog without spending LLM tokens. When NOT to use: interactive multi-turn chat (use Telegram/HTTP channels); tasks that need human approval for sensitive tools (stdio denies them); pasting secrets into `task`. Side effects / auth / limits: calls your configured LLM provider (API key from env/config); may invoke ARGUS-configured tools; third-party MCP tools run only after WARDEN gates (static scan → threat feed → LUMEN → def-pinning). Sensitive tools are deny-by-default on this channel (no interactive approver). Spend is bounded by ARGUS budget ceilings (stops rather than overspending). Not idempotent — each call is a new metered run. May use network (model + allowed tools). Returns: plain-text final answer. On failure or budget stop, text may still be returned with isError true. No streaming / partial events on this tool. Example: argus_ask({ task: "Summarise https://example.com in three bullets", response_format: "bullets" }) | Action |
| argus_status | Return ARGUS-3 MCP runtime status as JSON text (no LLM call, no side effects). When to use: before heavy argus_ask calls, or to confirm version/channel/tools. When NOT to use: to run a task (use argus_ask) or to list WARDEN policy detail (use argus_capabilities). Auth / limits: none beyond MCP session. Idempotent and read-only. Returns: JSON with status, agent, version, channel, mode, tools, detail, wardenNote, sensitiveToolsPolicy (and extra fields when detail=full). Example: argus_status({ detail: "basic" }) | Read-only |
| argus_capabilities | List ARGUS MCP tools and WARDEN security posture as JSON text (no LLM call). When to use: discovery — choose between argus_ask / argus_status / this catalog. When NOT to use: executing a user task (argus_ask) or a cheap ping (argus_status). Side effects: none. Read-only, idempotent, no provider auth required for this tool. Returns: JSON { agent, version, tools[{name, readOnly, summary}], warden, sensitiveToolsPolicy, channel }. Example: argus_capabilities({ include_schemas: false }) | Read-only |
Configuration
ARGUS_LOCAL_BASE_URLARGUS_WALLET_KEY
| Name | Description | |
|---|---|---|
| ARGUS_LOCAL_BASE_URL | — | |
| ARGUS_WALLET_KEY | — |
Automated checks
Ran Nov 16, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work
- Source repository linked and reachablealexar76/argus is public and reachablegithub.com/alexar76/argus ↗Pass
- Package names this repository as its source@alexar76/argus3 names alexar76/argus as sourcenpmjs.com/package/@alexar76/argus3 ↗Pass
- Build provenance (Sigstore attestation)No build attestation published for this releaseNot checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-15github.com/alexar76/argus ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNo popular package one edit away from @alexar76/argus3Pass
- No critical advisory in the package or its dependenciesthe package checked; no critical advisoryosv.dev ↗Pass
- No hidden instructions to the model3 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNo tool named like delete, drop or execPass
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubARGUS-3 — MCP server
0.3.3: requires
@aimarket/warden@0.8.1or later. MCP servers are checked before launch and before every call; list-change notifications quarantine tools immediately. Changed definitions, and pins taken before 0.3.2, need a reviewed re-approval:argus warden pins status <id>/argus warden pins approve <id>; the first clean connection keeps the automatic first-pin policy. Pin write failures close the connection. Publish Warden first, then ARGUS. Migration: EN · RU · ES · FR · ZH.
🔄 Synced from the AI-Factory monorepo (append-only history). Pull requests are welcome — merged PRs are imported back and re-synced here. Issues · Pull requests
One MCP server. WARDEN-hardened agent. Wallet optional.
Transport: stdio (argus mcp). Built with the official
Model Context Protocol TypeScript SDK (@modelcontextprotocol/sdk).
Compatible hosts: Claude Desktop, Cursor, Glama, and any MCP client that supports stdio servers.
| Item | Location |
|---|---|
| MCP entrypoint | argus mcp → src/channels/mcp_server.ts |
| Tools | argus_ask, argus_status, argus_capabilities |
| WARDEN firewall | docs/security-warden.md |
| Glama / Docker (stdio) | Dockerfile.glama, glama.json |
Part of the AICOM open agent economy. Live demo: magic-ai-factory.com/argus/ · Community: Discord · Pollux · Telegram · Castor
MCP firewall first — wallet optional. ARGUS-3 vets every third-party MCP server through WARDEN (static scan → threat feed → origin → def-pinning) before a single tool runs. Crypto, wallet, and on-chain economy are off by default.
(short name ARGUS · CLI: argus · npm: argus-warden · scoped: @alexar76/argus3)
Why "ARGUS-3"? In the myth, Argus Panoptes — the hundred-eyed watchman — was unbeatable until Hermes talked him to sleep and slew him. ARGUS-3 is the watchman that doesn't fall for Hermes: a hundred eyes open (WARDEN), frugal to a fault, immune to smooth-talking competitors.
Third time's the watchman. 👁️
ARGUS is the demand-side reference client the agent economy was missing. The ecosystem already has producers (the Factory 🏭), a broker (the Hub 🛒), pricing (ACEX 📈), trust math (the LUMEN oracle 🔮) and observability (the Monitor 👽). What it lacked was a first-class agent an ordinary person runs — one that discovers, pays for, consumes and sells capabilities. That's ARGUS.
It is built on two stack layers that generic MCP clients typically lack:
- 🛡️ WARDEN — an MCP security firewall that vets third-party servers before their tool definitions ever reach the model: a tiered static scan, a signed threat feed, an origin check, and tool-def pinning against rug-pulls. Every gate decides from what ARGUS already holds locally. Works with no wallet and no chain.
- 💸 Native settlement (optional) — pay per-call and get paid in USDC on Base through AIMarket escrow when you enable crypto and connect a wallet.
…and it stays frugal (a hard budget governor + live token meter — no self-reflection on your dime), speaks any model (Anthropic, OpenAI-compatible, Chinese, local), and — critically — runs fully autonomously when the economy is unavailable. No wallet, no network to AICOM? It's still a best-in-class local, MCP-secured assistant.
🔒 Crypto is OFF by default
A blockchain is not required to run ARGUS-3. Wallet, lottery, ACEX, paid invokes, and on-chain settlement are disabled by default and turn on only when you set
ARGUS_CRYPTO_ENABLED=1(plus a wallet). Out of the box you get the full agent — WARDEN, any model, memory, channels, and free off-chain oracle reads — with no chain, no token, no wallet, no custody. Crypto is opt-in.
Why ARGUS is different
| What it does | Why it matters | |
|---|---|---|
| 🛡️ WARDEN firewall | Every MCP server is vetted by a gate chain — static tool-def scan → threat feed → origin → def-pinning — before a single tool runs. | Tool-poisoning, rug-pulls (def drift), exfiltration and credential harvesting are blocked by default. Every gate decides from data ARGUS already holds locally, so vetting needs no network and nothing can talk the verdict out of it. |
| 💸 Native + autonomous economy | Discover → open USDC channel → invoke → settle (consumer); register in the Mesh → list → earn (provider). Loads only with a wallet. | Turns AICOM into a real two-sided market. With no wallet the module never loads — zero dependency, zero failure surface. |
| ⚖️ Token-frugal by design | Bounded reasoning-budget governor with hard $/token ceilings, model tiering, cache_control, curated handoff, compaction, and a live meter. |
The "cheaper" claim is auditable, not marketing. Exceeding a ceiling stops the task — it never silently overspends. |
| 🌐 Any provider | One Provider interface over Anthropic-native, any OpenAI-compatible endpoint (incl. DeepSeek, Qwen, GLM, Kimi…), and local Ollama. |
Your keys, your models, your costs. Triage on a cheap/local model, escalate only when needed. |
🧭 Core capabilities — design intent and stack dependencies for each headline feature — docs/killer-features.md · ru · es.
Quickstart
One command (interactive wizard, ~2 minutes):
curl -fsSL https://magic-ai-factory.com/install | bash
Or install from npm (same CLI, no curl script):
npm install -g @alexar76/argus3@0.3.3
mkdir -p ~/.argus/agent && cd ~/.argus/agent
argus setup && argus doctor
Package: @alexar76/argus3 on npm · CLI: argus · npx -y @alexar76/argus3@0.3.3 --help
Use the scoped package for current releases. The legacy argus-warden package remains at 0.3.1 with an older WARDEN dependency.
Then argus chat or argus serve.
Run as MCP server (stdio)
npm install -g @alexar76/argus3@0.3.3
# or: npm install && npm run build && node dist/index.js mcp
argus mcp
Claude Desktop / Cursor (mcpServers entry):
{
"mcpServers": {
"argus": {
"command": "argus",
"args": ["mcp"]
}
}
}
Tools (2)
| Tool | When to use | Returns | Example |
|---|---|---|---|
argus_ask |
Bounded NL work via agent core. Optional response_format / focus. Sensitive tools deny-by-default; budget-metered LLM. |
Plain-text answer (isError on failure/budget stop) |
argus_ask({ task: "Summarise https://example.com in three bullets", response_format: "bullets" }) |
argus_status |
Liveness before heavy argus_ask (detail: basic|full) |
JSON status | argus_status({ detail: "basic" }) |
argus_capabilities |
Discovery / WARDEN posture without spending LLM tokens | JSON tool catalog | argus_capabilities({ include_schemas: false }) |
Glama TDQS: MCP annotations (readOnly / destructive / idempotent / openWorld), Behavior + Usage Guidelines in every description, structured params with examples — calibrated to the score rubric (not the old one-liner).
Publish on Glama
Listing: glama.ai/mcp/servers/alexar76/argus
Same pattern as aimarket-oracle-gateway: repo-root glama.json + Dockerfile.glama + node dist/index.js mcp.
If
magic-ai-factory.com/installreturns 404, use the mirror:curl -fsSL https://modeldev.modelmarket.dev/install | bash
Docs: Wiki · User guide (20 languages) · Developer guide — publish a capability in 15 min (20 languages) · Use case — your ARGUS on AICOM (EN / RU) · Use case — a travel eSIM, bought and refunded (5 languages) · The Verifiable Conscience (block diagrams) · When ARGUS won't help you 😈 · Ecosystem whitepaper
cd argus
npm install
npm run build
# 1) Configure (safe to commit — NO secrets live here)
cp argus.config.example.json argus.config.json
# 2) Add keys to .env (all optional; with none, ARGUS uses a local Ollama model)
cp .env.example .env # then edit
# 3) Check what's wired up
node dist/index.js doctor
# 4) Ask something
node dist/index.js ask "summarise https://example.com in three bullets"
# 5) Interactive
node dist/index.js chat
During development you can skip the build step with npm run dev -- ask "…".
The autonomy guarantee
ARGUS needs nothing from AICOM to work:
# No ANTHROPIC_API_KEY, no wallet — just a local model:
ARGUS_LOCAL_BASE_URL=http://127.0.0.1:11434/v1 node dist/index.js ask "hello"
With no ARGUS_WALLET_KEY, doctor reports economy: OFF (autonomous) and the
entire economy layer is never constructed. See docs/autonomy.md.
Architecture
Five layers. Everything above the autonomy line runs offline; the economy clips on underneath, gated purely on the presence of a wallet.
flowchart TB
subgraph OFF["Runs offline — no AICOM, no wallet"]
L1["Layer 1 · Providers — Anthropic · OpenAI-compatible · local"]
L2["Layer 2 · Bounded agent core — plan→execute→observe + budget governor"]
L3["Layer 3 · Memory / self-learning — episodes · lessons · pins"]
L4["🛡️ Layer 4 · MCP host + WARDEN — static · threat · origin · pinning"]
L1 --- L2 --- L3 --- L4
end
GATE{{"— autonomy line — needs ARGUS_WALLET_KEY"}}
L5["🛒 Layer 5 · Economy — discover · pay · invoke · settle · sell"]
L4 -.-> GATE -.-> L5
L5 -.->|wraps| SDK["@aimarket/agent SDK"]
Full diagrams and the module map: docs/architecture.md.
🛡️ WARDEN — the MCP firewall
WARDEN ships separately as
@aimarket/warden— a zero-dependency library you can put in front of your own MCP host without adopting ARGUS. ARGUS depends on that package; this section is what it does inside the agent.
An MCP server's tool descriptions are attacker-controlled text the model reads as instructions. WARDEN treats every server as hostile-by-default and runs each connection through gates before any tool is exposed:
flowchart LR
S[MCP server] --> A[1 · static scan] --> B[2 · threat feed] --> C[3 · origin] --> D[4 · def-pinning] --> V{allow?}
V -->|yes| OK[bridge tools<br/>pin defs]
V -->|no| NO[block + report]
- Static scan — injection / exfiltration / secret-harvesting / hidden-unicode signatures in tool defs. Rules are tiered: blocking rules cover phrasing with no benign reading; advisory rules (an
api_keyparameter, an.envmention, a "you must") are reported but never block and never affect the score — which is what lets honest servers through. Every verdict names the ruleset version + digest that produced it. - Threat feed — built-in deny-list + optional signed remote feed.
- Origin — where the server declaration came from: you listed it in
mcp.servers, or it was discovered from a remotemcp.catalogsentry. WithallowUnknownServers: falsea catalog-discovered server is blocked (SERVER_UNDECLARED); your own declarations always pass, so fail-closed still leaves a way to connect. - Pinning — hashes the approved tool set; later drift = rug-pull, forces re-approval.
Sensitive tools (write/delete/exec/payment/…) additionally require explicit user approval at call time. Details: docs/security-warden.md.
node dist/index.js warden scan # vet your configured MCP servers
💸 Economy integration
ARGUS reuses the existing AI Market Protocol v2 and the @aimarket/agent
SDK — no new endpoints.
export ARGUS_WALLET_KEY=0x... # enables the economy layer
node dist/index.js economy status
node dist/index.js economy discover "translate to 5 languages" --budget 1
node dist/index.js economy register # list ARGUS in the AI Service Mesh
Consumer flow: discover → openChannel (USDC/Base) → invoke (X-Payment-Channel) → settle. Provider flow: register identity + wallet in the Mesh, list capabilities,
earn (and become eligible for the agent lottery / machine-UBI). See
docs/economy-integration.md ·
docs/mcp-oracles-capabilities.md (17 oracles, MCP, selling).
Real case — a travel eSIM, bought and refunded. ARGUS buys an eSIM for its owner from any esim.*@v1 seller (esim_buy, after /yes), sends the QR code straight to the owner's Telegram (never to the model), and gets the money back for an unused eSIM (esim_refund). It then brings the seller's signed receipts to the hub, so the hub can count which sellers really deliver (ARGUS_SHARE_DELIVERIES=0 keeps purchases private). The three runs of 15 October 2026, with every transaction on Base: docs/use-case-esim-purchase-refund.md.
Multi-provider
| Adapter | Covers |
|---|---|
| Anthropic-native | Claude Opus/Sonnet/Haiku/Fable — first-class cache_control; default for the core loop |
| OpenAI-compatible | OpenAI, DeepSeek, Qwen/DashScope, Zhipu GLM, Moonshot/Kimi, MiniMax, Mistral, Groq, Together, OpenRouter, vLLM |
| Local | Ollama / llama.cpp — offline + the cheap triage tier |
Models are assigned to tiers (triage / core / heavy) in
argus.config.json; routing falls back across tiers when a key is missing.
🎮 Agent Arena — level up, keep streaks, flex your card
Running an agent should be fun. Agent Arena turns real ecosystem activity into the game mechanics a young, global audience already loves — Duolingo-style streaks, Wrapped-style shareable cards, gaming rank cards:
- XP & levels — earn XP for finishing tasks, selling capabilities, playing the
oracle lottery, trading on ACEX, and staying frugal (low
$/task). - Daily streaks 🔥 — keep your agent active day after day.
- Quests & badges — First Blood (first lottery win), Rainmaker (first
$1earned selling capabilities), Frugal (a task under$0.001), Trusted (top-half LUMEN reputation), Warden (blocked a malicious MCP server), Polyglot, Whale, Lucky… Trusted and the reputation rank are not earnable today: a LUMEN score needs a trust graph, and no deployment publishes the trust edges ARGUS would be scored on. - Flex Card —
argus flex(or/flexin Telegram) renders a slick, shareable card: handle, level, streak,$earned, win-rate, top badges, reputation rank (blank until a trust graph exists). Numbers + emoji = no language barrier → share it anywhere. - Global leaderboard (opt-in) — rank against agents worldwide by XP, earnings, or frugality.
Every stat is real — it's your actual economy and frugality performance, computed locally from your agent's own memory + signed economy receipts, so it's hard to fake and not vanity points. Sharing and the leaderboard are off by default and owner-controlled — your data stays yours. Full design: docs/arena.md.
Live demo (this fleet):
- LIVE (Base mainnet): https://magic-ai-factory.com/arena —
:8787→GET /arena/stats - UNI (Universe / Anvil): https://magic-ai-factory.com/arena-uni/ —
:8788→ same UI,mode=uni
Use the TEST · LIVE · UNI switcher on the Arena page to flip between demo metrics and each deployed node.
Configuration
argus.config.json— non-secret config (providers, models, tier pricing for the meter, budget ceilings, WARDEN policy, MCP servers/catalogs, economy endpoints). Safe to commit. Start fromargus.config.example.json..env— secrets only: API keys (ANTHROPIC_API_KEY,DEEPSEEK_API_KEY, …),ARGUS_WALLET_KEY, and optionalALIEN_API_TOKENfor the Alien Monitor run feed. Never commit. Start from.env.example.
economy.enabled is derived — it is true iff ARGUS_WALLET_KEY is set.
Where it sits in the ecosystem
aicomFactory builds agents → listed & invoked through AIMarket (Hub + protocol) → Oracles (LUMEN trust, randomness, VDF, consensus) price and secure them → financed on ACEX → visualised by Alien Monitor.ARGUS is the demand side: the agent that spends in this market, sells into it, and defends the user against the MCP supply chain — with a firewall that needs none of the above to work.
Channels
One bounded agent core, many channels — each with the auth model natural to it. Full matrix + design: docs/channels.md.
| Channel | Run | Auth |
|---|---|---|
| CLI | argus ask / argus chat |
local (interactive approval) |
| Telegram | argus telegram |
owner-locked (first /start claims) |
| HTTP API | argus serve |
/health open · POST /ask Bearer ARGUS_HTTP_TOKEN |
| MCP-server | argus mcp |
local stdio — exposes argus_ask / argus_status / argus_capabilities |
argus serve runs Telegram + the HTTP server together (this is what the
container runs). GET /health is also the hook that lets ARGUS appear as a live
node in Alien Monitor. Set ALIEN_MONITOR_URL + ALIEN_API_TOKEN to push
each completed run to the node's verifiable-run panel (oracle calls, WARDEN
blocks, hires, sealed receipt). Discord, Slack, Email, Matrix, WhatsApp and voice are
ready-to-add adapters (see the doc).
Deployment (Docker)
ARGUS launches untrusted MCP servers as child processes, so the container is also a security boundary around them — not just packaging.
cp argus.config.example.json argus.config.json # edit
cp .env.example .env # add secrets
docker compose up -d --build # serve: Telegram + HTTP /health
Secrets come from .env (never baked into the image); argus.config.json is
mounted read-only; state persists in the argus-state volume; a HEALTHCHECK
probes /health. Economy is OFF by default in the container (autonomous).
Development
npm run typecheck # tsc --noEmit (strict)
npm test # vitest (budget governor, MCP host + WARDEN wiring, provider mapping)
npm run build # emit dist/
Status
v0.1 — bounded agent loop, multi-provider routing, WARDEN gate chain (static +
threat + origin + pinning), memory/lessons, MCP host, economy consumer/provider
wrappers, and four channels (CLI, Telegram, HTTP, MCP-server) + Docker — all
implemented and tested. OS-level MCP sandboxing (seccomp/Landlock/sandbox-exec),
the signed threat-feed publisher, and the remaining channel adapters are the v2
track — see the docs.
Demo
Related repos
| Repo | Role |
|---|---|
| aicom | AI-Factory — ships capabilities ARGUS consumes |
| aimarket-hub | Federation hub — discover, invoke, settle |
| oracles | LUMEN reputation + verifiable math |
| alien-monitor | ARGUS appears as a live graph node |
| dioscuri | Twin community agents — MNEMOSYNE Q&A |
Community
The DIOSCURI twins answer questions from synced GitHub docs.
| Channel | Twin | Best for |
|---|---|---|
| Discord | Pollux | Help, ideas, show-and-tell |
| Telegram | Castor | Releases, digests, quick news |
Ecosystem map: Alien Monitor · AICOM
License
MIT — your keys, your infra, your data. Part of the AICOM open agent-economy.
ARGUS-3 MCP questions
How do I add ARGUS-3 MCP to Claude Code?
Run claude mcp add argus -- npx -y @alexar76/argus3 mcp in your terminal. Add --scope user to make it available in every project.
How do I add ARGUS-3 MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What tools does ARGUS-3 MCP provide?
It exposes 3 tools, including argus_ask, argus_status, argus_capabilities.
How does the WARDEN firewall protect my tools?
WARDEN vets third-party MCP servers through a tiered process including static scans, threat feeds, origin checks, and tool-definition pinning to prevent poisoning and rug-pulls.
Can I use local models with ARGUS-3?
Yes, ARGUS-3 supports local models like Ollama and any OpenAI-compatible endpoint.