Argosvix MCP Server — Watchlist

MCP100 Assessment

Watchlist / Tracking

Why we’re tracking it

Follow-up value is specific to Argosvix LLM observability and approval control-plane tools: Do customer accounts remain excluded from internal operations while budget and policy gates evolve?

Reviewed Oct 5, 2026 · Documentation review; complete setup workflow not independently tested

Best fit

LLM observability and runtime-control operations for cost, latency, errors, alerts, evals and gates.

What we know

Official observability MCP that queries LLM usage/health data and can operate alerts, evaluations, prompt/runtime controls, budget gates, policy gates and approval gates.

Maintenance / activity evidence

@argosvix/mcp-server 1.1.2 published 2026-09-03T05:50:01.452Z

Tracking evidence observed Oct 5, 2026. These dated signals do not establish current maintenance. Reviewed enrichment confidence: high.

Verification gaps / watch-outs

Installation and comprehensive security have not been independently audited.
Read observability plus potentially write alert/eval/gate configuration. Writes: Create/update alerts; Operate evaluations; Create/change budget/policy/human-approval gates.
Argosvix API key.
Sensitive access: LLM telemetry, Cost and error records, Optional captured content if enabled

Runtime controls can alter production model behavior; changes should be reviewed.

Full authority, access and evidence limits are available in Review context and Access & risk.

All limitations / Review context

Do customer accounts remain excluded from internal operations while budget and policy gates evolve?

The bounded review of the publisher's documented Argosvix LLM observability and approval control-plane tools and release notices identified no disclosed material condition preventing an accurately scoped public tracking entry. The resource's operational permissions remain uncertainty; this assessment does not certify installation safety.

Runtime controls can alter production model behavior; changes should be reviewed.
Read observability plus potentially write alert/eval/gate configuration.
Argosvix API key.
Default SDK telemetry excludes prompt/completion bodies unless content capture is enabled; MCP operates on Argosvix account data.
Reviewed write actions: Create/update alerts; Operate evaluations; Create/change budget/policy/human-approval gates
Sensitive access: LLM telemetry, Cost and error records, Optional captured content if enabled
Installation, client compatibility and comprehensive security have not been independently audited. Authentication and access depend on the configured services.
Runtime behavior, dependencies and undisclosed vulnerabilities were not independently audited.
Documented tool authority and any remote data handling must be checked before installation or use.
Tool inventory, client matrix and permissions completeness were not requirements for this Radar tracking review.
Some tools are internal/forbidden to customer accounts.
Prompt/completion capture is opt-in in the underlying SDK, but telemetry data is provider-hosted.
Large tool surface is versioned and can drift.
Repository/tool-surface details were corroborated from the package's public mirror/catalog page; keep exact tool counts non-canonical.

Original activity observations

@argosvix/mcp-server 1.1.2 published 2026-09-03T05:50:01.452Z

Technical identity

npm/@argosvix/mcp-server

Exact implementation source: https://www.npmjs.com/package/@argosvix/mcp-server ↗
Reviewed resource type: MCP Server
Repository identity: argosvix/mcp-server
Package identity: npm:@argosvix/mcp-server

Evidence & Sources

Evidence basis: Recorded source evidence
Setup runtime verification: Not independently runtime-tested by MCP100 for this setup workflow.

Reviewed Oct 5, 2026 · Latest source observation Oct 8, 2026

Package registry metadata ↗
@argosvix/mcp-server
Recorded package identity, distribution or download evidence.
Package registry ↗
@argosvix/sdk
Recorded package identity, distribution or download evidence.
Includes references whose attribution is not established.
Evidence source ↗
argosvix.com/
Source material retained for this review.
Includes references whose attribution is not established.
Directory reference ↗
glama.ai/mcp/servers/argosvix/mcp-server/tree
Source material retained for this review.
Includes references whose attribution is not established.

Setup · Watchlist

Install & Agents

Publisher instructions.

Source evidence observed Oct 14, 2026.

Additional setup details required — see the specific gaps below.

Install / connect
MCP100 setup guide
Publisher-documented install or connect path; prerequisites and any extra host configuration remain required.
publisher install or stdio launch · Publisher instructions
npm install -g @argosvix/mcp-server
reviewed install or registration · MCP100 composed guide
npx -y @argosvix/mcp-server
Configure / authenticate
MCP100 setup guide
Keyless registration exposes tool catalogue and only public read-only tools; private tools require ARGOSVIX_API_KEY from dashboard.
Check connection
Suggested check
Inspect MCP tools and keyless `get_synth_daily`, not private actions.
Remove / uninstall / revoke
MCP100 setup guide
If registered in Claude Code under the name `argosvix`, remove the client entry with `claude mcp remove argosvix`. For other MCP hosts remove the matching server/connector in that host’s MCP settings. Remove a globally installed software package separately if applicable; this does not delete data or revoke a service credential.
Client removal, software uninstall, persistent-data deletion and credential revocation are separate actions.
Remove client registration · Claude Code only · MCP100 composed guide
claude mcp remove argosvix

Official Documentation & Sources

https://www.npmjs.com/package/@argosvix/mcp-server ↗

What it does

Official observability MCP that queries LLM usage/health data and can operate alerts, evaluations, prompt/runtime controls, budget gates, policy gates and approval gates.

Capability: Cloud & DevOps
Resource type: MCP Server
Best fit: LLM observability and runtime-control operations for cost, latency, errors, alerts, evals and gates.

Representative uses

Query LLM cost/token/error/latency data
Inspect anomalies and account health
Create/manage alerts and evaluations
Operate runtime budget/policy/approval controls

Limitations

Some tools are internal/forbidden to customer accounts.
Prompt/completion capture is opt-in in the underlying SDK, but telemetry data is provider-hosted.
Large tool surface is versioned and can drift.
Repository/tool-surface details were corroborated from the package's public mirror/catalog page; keep exact tool counts non-canonical.

Reviewed access

Access & risk

Review the exact access boundary before connecting this MCP to accounts, credentials, or sensitive data.

Authentication: Argosvix API key.
Permissions: Read observability plus potentially write alert/eval/gate configuration.
Data handling: Default SDK telemetry excludes prompt/completion bodies unless content capture is enabled; MCP operates on Argosvix account data.
Cost: plan_based
Risk and cautions: Runtime controls can alter production model behavior; changes should be reviewed.

Access scope and cautions

Write actions: Create/update alerts Operate evaluations Create/change budget/policy/human-approval gates
Sensitive access: LLM telemetry Cost and error records Optional captured content if enabled
Risk level: high

FAQ

Based on reviewed evidence as of 2026-10-08. Watchlist tracking is not a recommendation or a security certification.

Which tasks are documented for this implementation?

The reviewed tasks include: Query LLM cost/token/error/latency data; Inspect anomalies and account health; Create/manage alerts and evaluations; Operate runtime budget/policy/approval controls.

What setup and authentication are documented?

Recorded installation/entrypoint step: npx -y @argosvix/mcp-server. Recorded transport: stdio, http. Recorded environment-variable notes: ARGOSVIX_API_KEY. No configuration values are supplied here. Prerequisites: Argosvix account for account-specific tools. These are the documented setup details, not a claim that installation or client compatibility was independently tested. Authentication: Argosvix API key for account operations.

Can it modify data or perform write operations?

Documented write actions include: Create/update alerts; Operate evaluations; Create/change budget/policy/human-approval gates. Recorded permission boundary: Read observability plus potentially write alert/eval/gate configuration.

What data-handling boundary should I consider?

Default SDK telemetry excludes prompt/completion bodies unless content capture is enabled; MCP operates on Argosvix account data. Recorded sensitive-access context: LLM telemetry; Cost and error records; Optional captured content if enabled.

What limitations and risks should I check before use?

Runtime controls can alter production model behavior; changes should be reviewed. Some tools are internal/forbidden to customer accounts. Prompt/completion capture is opt-in in the underlying SDK, but telemetry data is provider-hosted. Large tool surface is versioned and can drift. Repository/tool-surface details were corroborated from the package's public mirror/catalog page; keep exact tool counts non-canonical. Runtime behavior, dependencies and undisclosed vulnerabilities were not independently audited. Documented tool authority and any remote data handling must be checked before installation or use.

What cost model is recorded?

The reviewed cost model is plan based. This classification does not establish current prices, quotas or the cost of every downstream operation. Check the applicable service terms before authorizing paid actions.