Argus API Spend MCP Server

town.argus/argusv1.0.1

Track API spend, credit balances and runway across OpenAI, Anthropic, OpenRouter and 25 more.

remoteofficial registry

context tax

~569 tok/turn10 tools

security

100/100

cold start

hosted

freshness

Active2d ago

Our reading of Argus API Spend, from the data

Argus API Spend is a ai & llm tools MCP server, listed in the official MCP Registry.

Its 10 tools add about 569 tokens to every model turn, lighter than the ai & llm tools median of 1,003 tokens across 228 measured servers (measured 2026-10-19).

Maintenance is active: the last public signal was 2 days ago (2026-10-17). For comparison, 59% of ai & llm tools servers are active or maintained.

It runs as a hosted endpoint, so there is nothing to install.

Install Argus API Spend MCP server

claude mcp add --transport http town-argus-argus https://api.argus.town/mcp

{
  "mcpServers": {
    "town-argus-argus": {
      "url": "https://api.argus.town/mcp"
    }
  }
}

{
  "mcpServers": {
    "town-argus-argus": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://api.argus.town/mcp"
      ]
    }
  }
}

Or add it as a custom connector under Settings → Connectors. The config above bridges via mcp-remote.

{
  "servers": {
    "town-argus-argus": {
      "type": "http",
      "url": "https://api.argus.town/mcp"
    }
  }
}

{
  "mcpServers": {
    "town-argus-argus": {
      "serverUrl": "https://api.argus.town/mcp"
    }
  }
}

Remote endpoints

streamable-httphttps://api.argus.town/mcp

Context tax

Connecting this server adds ~569 tokens of tool definitions to every model turn (lean, 10 tools). Measured 2026-10-19 via its hosted endpoint; o200k tokenizer, worst case for clients that load all tools up front. How we measure

Model	Per 1,000 turns	With prompt caching
Claude Opus 5.5	$2.28	$0.114
Claude Sonnet 5.5	$1.14	$0.114
Claude Haiku 5.5	$0.057	—

Input prices as of 2026-10-06. Excludes your own prompt and output.

Tools (10)

connect_provider120 tok
Connect a provider to THIS project with a credential. Validates the credential against the provider before storing it (encrypted), then queues the initial sync. Args: provider (id from list_available_providers), secret (the provider API key), credential_type (optional), label (optional). Only pass secrets your operator gave you for this purpose.
get_request_costs90 tok
Recent itemized per-request costs for a provider (model, tokens, cost in USD, provenance). Args: provider (string), limit (number, default 25, max 100).
get_cost_accuracy61 tok
Cost-accuracy state per provider: whether itemized costs are exact, estimated, or unreconciled, with the drift % between Argus's itemized total and the provider's own reported spend.
list_available_providers57 tok
Providers that can be connected with an API key (poll plane). Anything else can still be tracked by sending telemetry — see https://argus.town/docs/ingest.
sync_connection49 tok
Queue an immediate balance/usage/plan refresh for one connection. Args: connection_id.
get_overview47 tok
Cross-provider rollup: balance, burn rate, days-to-zero, month-to-date spend, projection, rate-limit headroom.
get_provider42 tok
Full metrics + rate-limit snapshots for one connection id.
get_advisories42 tok
All current advisories (top-up, upgrade, near-limit, spend-spike) across providers.
get_rate_limit_status36 tok
Latest rate-limit headroom and error rate across the org's providers.
list_connections29 tok
List the org's connected providers and status.

Security signals

100/100 — no known issues found as of 2026-10-19, from the checks below. This is not a guarantee of safety; review what a server can do before connecting it.

Deductions

No findings from the checks that ran.

Checks

✓Tool descriptions (prompt-injection and hidden-text heuristics)
○Repository hygiene (archived, activity, license, security policy) — pending
○Package metadata (install scripts, provenance) — pending
○Source scan (secrets, CVEs, risky code) by vectra-guard — pending

Scan it yourself before installing with vectra-guard, the open-source agent security CLI. Scoring rules

Freshness

Active — last maintenance signal 2d ago. The newest of the signals below sets the band.

Last commit (default branch)
no data · GitHub
Latest release
no data · GitHub
Package published
no data · npm/PyPI
Registry entry updated
2026-10-17 · 2d ago · official registry · v1.0.1

How it compares in AI & LLM Tools

Against the most-starred ai & llm tools servers we index. Token cost is per model turn, measured from each server's live tool list.

Server	Stars	Tools	Tokens / turn	Freshness	Runs
Argus API Spend (this)	—	10	569	Active	hosted
Memory	91,356	—	not measured	Active	local
Claude Flow	76,638	—	not measured	Active	local
Next AI Draw.io	36,318	—	not measured	Active	local
Serena Agent	30,371	—	not measured	Active	local
Trycua	30,160	—	not measured	Active	—

All ai & llm tools MCP servers

FAQ

›How do I install the Argus API Spend MCP server in Claude Code?

Run: claude mcp add --transport http town-argus-argus https://api.argus.town/mcp. For Cursor, VS Code, Claude Desktop and Windsurf, use the install tabs above.

›Does Argus API Spend require an API key?

No required environment variables are declared in its published metadata.

›Can I use Argus API Spend as a remote (hosted) MCP server?

Yes. It is a hosted MCP server; connect to its URL with any client that supports remote MCP.

›Is Argus API Spend in the official MCP registry?

Yes, as town.argus/argus.

›How many tokens does Argus API Spend add to my context?

Its tool definitions total about 569 tokens, resent on every turn.

Sources and method

Official MCP Registry entry: updated 2026-10-17
Tool list (tools/list), measured by us: 2026-10-19
Security signals, computed by us: 2026-10-19
Last checked against all sources: 2026-10-19

The description, packages and links come from the maintainer's own published metadata. Token cost, security signals, freshness and the reading above are MCPSkillHub's own measurements; see the methodology. Editorial standards are owned by Ramachandra Vikas Chamarthi, Founder & AI HPC Architect. Spot an error? Request a correction or claim the listing.