Argus API Spend
REMOTE · API.ARGUS.TOWN
Track API spend, credit balances and runway across OpenAI, Anthropic, OpenRouter and 25 more.
Available components
Last scanned (28 minutes ago)
Scores higher than 45% of remote servers
Reachable. Last reached 23 Oct 2026.
Category AI and Machine Learning
How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →
Endpoint Security46
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- Authorisation not fully verified: no authorisation is required to call this server, and 12 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe. See how to fix → View diagnostics → Unverified
- HTTPS enforcement could not be verified: the plaintext port answered with HTTP 405, which proves neither a plaintext path nor enforcement. View diagnostics → Unverified
- HSTS check failed: the Strict-Transport-Security header is absent. See how to fix → View diagnostics → Fail
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability68
- AI-judged instruction clarity (good).Pass
- Tool/resource definitions use about 800 tokens (~66/item across 12 items; 12 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management13
- Stability observed for 4 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage69
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 8% of tool parameters carry a description.Partial
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 12 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 12 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 22 Oct 26 +1
- Tool “connect_provider” rewrote its description, which is the text the model reads security
- Tool “get_cost_accuracy” rewrote its description, which is the text the model reads security
- Tool “get_overview” rewrote its description, which is the text the model reads security
- Tool “get_provider” rewrote its description, which is the text the model reads security
- Schema quality: 43 → 66 ▼ functional
- Tool coverage: 13% → 8% ▼ functional
- New tool “create_connect_link” functional
- New tool “get_connect_link” functional
- “connect_provider” added an optional parameter “meta” cosmetic
- 21 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.
- 20 Oct 26 0
- Stability: unverified → 0.03 ▲ functional
- 19 Oct 26 +28
- Authorization: fail → unverified ▼ security
- Transport: unverified → pass ▲ security
- Injection markers: unverified → pass ▲ security
- First check of Judged manipulation: pass security
- MCP protocol: unverified → pass ▲ functional
- Tool coverage: unverified → 100 ▲ functional
- First check of Schema quality: fail functional
- First check of Destructive annotations: pass functional
- First check of Schema quality: pass functional
- First check of Tool coverage: 13 functional
- First check of Schema quality: good functional
- 17 Oct 26 28
First indexed and scored.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 23 Oct 2026 · Probed https://api.argus.town/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=argus.town | CN=WE1,O=Google Trust Services,C=US | 16 Sept 2026 | 15 Dec 2026 | ECDSA 256 | ECDSA-SHA256 | 5216bebb2e7c47e50e05cfe9add8104b |
| SANs: argus.town, api.argus.town, *.api.argus.town | ||||||
| CN=WE1,O=Google Trust Services,C=US (CA) | CN=GTS Root R4,O=Google Trust Services LLC,C=US | 13 Dec 2023 | 20 Feb 2029 | ECDSA 256 | ECDSA-SHA384 | 7ff31977972c224a76155d13b6d685e3 |
| CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) | CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE | 15 Nov 2023 | 28 Jan 2028 | ECDSA 384 | SHA256-RSA | 7fe530bf331343bedd821610493d8a1b |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of api.argus.town. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| town. | present | 63256 | 8 | Verified |
| argus.town. | absent | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication No authorisation required
The endpoint answered without asking for a token. Anyone who knows the URL can reach it.
| Result | No authorisation required |
|---|---|
| HTTP status | 200 |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://api.argus.town/mcp | Verified | 200 | |
| http (plaintext) | http://api.argus.town/mcp | Inconclusive | 405 |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
connect_provider ~164
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), meta (optional object of non-secret fields, e.g. OpenRouter admin_key needs {tracked_key: <key name, label or hash>} inside meta, not at the top level; Cloudflare Containers needs {account_id} and takes optional {billing_day}). Only pass secrets your operator gave you for this purpose.
| Name | Type | Req | Description |
|---|---|---|---|
| credential_type | string | – | – |
| label | string | – | – |
| meta | object | – | – |
| provider | string | yes | – |
| secret | string | yes | – |
No output schema declared.
No examples provided.
create_connect_link ~113
Hand a provider credential to Argus without it passing through you: returns a single-use URL (valid 1 hour) where your operator pastes the key. Show the URL to your operator, then poll get_connect_link for the connection id. Prefer this over connect_provider whenever you don't already hold the secret. Args: provider (id from list_available_providers), credential_type (optional), label (optional).
| Name | Type | Req | Description |
|---|---|---|---|
| credential_type | string | – | – |
| label | string | – | – |
| provider | string | – | – |
No output schema declared.
No examples provided.
get_advisories ~30
All current advisories (top-up, upgrade, near-limit, spend-spike) across providers.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_connect_link ~47
Status of a connect link: pending, submitting (the human is mid-submit), done (with connection_id), expired, or locked after repeated bad credentials.
| Name | Type | Req | Description |
|---|---|---|---|
| id | string | yes | – |
No output schema declared.
No examples provided.
get_cost_accuracy ~94
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. 'unreconciled' means no provider anchor has been compared yet; where one exists (OpenRouter) it covers only calls sent through the connected key. spend_basis qualifies mtdSpendUsd (see get_overview).
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_overview ~105
Cross-provider rollup: balance, burn rate, days-to-zero, month-to-date spend, projection, rate-limit headroom. Per provider, spend_basis says where month-to-date spend comes from: 'reported' (provider usage or itemized events) or 'observed_since_connected' (summed balance drops since observed_since, so spend before that date is missing); balance_scope says whether the balance covers the 'account', the connected 'key' or is 'unknown'.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_provider ~56
Full metrics + rate-limit snapshots for one connection id. Includes spend_basis ('reported' | 'observed_since_connected'), observed_since and balance_scope ('account' | 'key' | 'unknown').
| Name | Type | Req | Description |
|---|---|---|---|
| connectionId | string | yes | – |
No output schema declared.
No examples provided.
get_rate_limit_status ~24
Latest rate-limit headroom and error rate across the org's providers.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_request_costs ~71
Recent itemized per-request costs for a provider (model, tokens, cost in USD, provenance). Args: provider (string), limit (number, default 25, max 100).
| Name | Type | Req | Description |
|---|---|---|---|
| limit | number | – | – |
| provider | string | yes | Provider id, e.g. 'openrouter' |
No output schema declared.
No examples provided.
list_available_providers ~45
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.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
list_connections ~17
List the org's connected providers and status.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
sync_connection ~34
Queue an immediate balance/usage/plan refresh for one connection. Args: connection_id.
| Name | Type | Req | Description |
|---|---|---|---|
| connection_id | string | yes | – |
No output schema declared.
No examples provided.
How do I install the Argus API Spend MCP server?
Argus API Spend is a hosted endpoint at https://api.argus.town/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · api.argus.town
claude mcp add --transport http town-argus-argus 'https://api.argus.town/mcp'
What is the Argus API Spend MCP server?
Argus API Spend is an MCP server listed in the public MCP registry as town.argus/argus. Track API spend, credit balances and runway across OpenAI, Anthropic, OpenRouter and 25 more. This page covers its hosted endpoint (https://api.argus.town/mcp).
Is the Argus API Spend MCP server safe to use?
Argus API Spend scores 58 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the Argus API Spend MCP server expose?
Argus API Spend exposes 12 tools: list_connections, get_overview, get_provider, get_rate_limit_status, get_advisories, and 7 more. Their descriptions and schemas cost roughly 800 tokens of context every time the server is loaded.
Does the Argus API Spend MCP server require authentication?
No. We connected to Argus API Spend without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the Argus API Spend MCP server still maintained?
Argus API Spend is still listed as active in the MCP registry. We last reached this channel on 23 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.