# Silvanexum (npm · @silvanexum/mcp)

Spend control for AI agents - cost attribution, budget caps, and signed runs as MCP tools.

- Trust score: 63/100 (medium)
- Change this week: +23
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `@silvanexum/mcp`: 63/100 (this document), [markdown](https://verifymcp.io/servers/silvanexum-silvanexum/silvanexum-mcp.md), [page](https://verifymcp.io/servers/silvanexum-silvanexum/silvanexum-mcp)
- pypi · `silvanexum-mcp`: 5/100, [markdown](https://verifymcp.io/servers/silvanexum-silvanexum/silvanexum-mcp-2.md), [page](https://verifymcp.io/servers/silvanexum-silvanexum/silvanexum-mcp-2)

## Channel facts

- Registry: `npm`
- Package: `@silvanexum/mcp`
- Version: `0.4.0`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Supply Chain Security**: 87/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (96 of 100), so this covers what we could see, not the whole tree.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (96 of 100), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 19/100
  - Repository check failed: the declared repository URL returned HTTP 404.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (Apache-2.0).
  - Actively maintained (last published 26 days ago).
  - Security-disclosure policy not yet verified: we couldn't inspect the source repository.
- **Schema Quality & AI Usability**: 71/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 727 tokens (~72/item across 10 items; 10 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 23/100
  - Stability observed for 7 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add silvanexum-silvanexum -- npx -y @silvanexum/mcp
```

### Codex

```bash
codex mcp add silvanexum-silvanexum -- npx -y @silvanexum/mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "silvanexum-silvanexum": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@silvanexum/mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add silvanexum-silvanexum --command npx --arg -y --arg @silvanexum/mcp
```

### Hermes

```yaml
mcp_servers:
  silvanexum-silvanexum:
    command: "npx"
    args: ["-y", "@silvanexum/mcp"]
```

### Other

```json
{
  "mcpServers": {
    "silvanexum-silvanexum": {
      "command": "npx",
      "args": [
        "-y",
        "@silvanexum/mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-03 (score 63, +48)

- [security regression] Provenance: unverified → fail
- [security improvement] Install scripts: unverified → pass
- [security improvement] Known CVEs: unverified → partial
- [functional improvement] Stability: unverified → 0.23
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] License: unverified → pass
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] Schema quality: unverified → good
- [functional] Licence: Apache-2.0

### 2026-08-02 (score 15, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-08-01 (score 0, −31)

- [security regression] Malware scan: pass → unverified
- [functional regression] Tool coverage: 100 → unverified

### 2026-07-31 (score 31, +13)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-28 (score 18, −22)

- [functional regression] Tool coverage: 100 → unverified
- [functional] First check of Schema quality: unverified

### 2026-07-27 (score 40)

First indexed and scored.

## MCP tools (10)

### `search_agents` (~88 tokens)

Search agents

Search the Silvanexum marketplace for agents, ranked by PROVEN OUTCOMES (real run corpus + reputation), not stars. Returns proof-ranked listings.

Input parameters:

- `category` (string): Filter by listing category.
- `q` (string): Free-text query, e.g. 'legal contract review'.
- `sort` (string): Ranking. Default: proof (by signed-run corpus + reputation).

### `get_agent` (~30 tokens)

Get agent

Fetch an agent's configuration and earned reputation by id.

Input parameters:

- `agentId` (string, required): The agent id.

### `get_reputation` (~43 tokens)

Get reputation

Get an agent's earned reputation — volume-aware trust score, success rate, and confidence, derived from signed runs.

Input parameters:

- `agentId` (string, required): The agent id.

### `run_agent` (~77 tokens)

Run agent

Run an agent on a prompt. The run is captured, secret-scrubbed, and cryptographically signed. Returns the answer plus a replayable, signed trace URL. Requires the `run` scope.

Input parameters:

- `agentId` (string, required): The agent id to run.
- `prompt` (string, required): The input/instruction for the agent.

### `get_run` (~42 tokens)

Get run

Fetch a run's full signed trace (the step-by-step model/tool/agent timeline) by id.

Input parameters:

- `runId` (string, required): The run/execution id.

### `deploy_template` (~71 tokens)

Deploy template

Deploy a 1-click vertical agent template into a ready, signed agent (M11). Note: template endpoints may be 'planned' / not yet live on a given deployment.

Input parameters:

- `params` (object): Template parameter values (key → value).
- `templateId` (string, required): The template id to deploy.

### `wallet_balance` (~19 tokens)

Wallet balance

Get the org's credit balance and recent ledger activity.

### `get_spending` (~116 tokens)

Get spending

Agent FinOps — cost attribution. Spend rolled up by a dimension (agent / project / model / provider) over a time window, from real run telemetry + the mesh ledger. Read-only. Answers 'which agent/model burned the budget?'.

Input parameters:

- `groupBy` (string): Dimension to attribute spend by. Default: agent.
- `since` (string): Window start — relative ('-7d', '-24h') or ISO. Default -30d.
- `to` (string): Window end — ISO. Default now.

### `list_budgets` (~56 tokens)

List budgets

Agent FinOps — list spend caps (budgets), each with its live computed spend, remaining, and state (ok / warn / exceeded) for the current period.

Input parameters:

- `scopeType` (string): Filter budgets by scope.

### `create_budget` (~185 tokens)

Create budget

Agent FinOps — create a spend cap over an org / project / agent for a period. With enforcement 'block', a run or mesh hop that would breach the cap is rejected server-side (HTTP 402). Requires a key with write scope.

Input parameters:

- `alertThresholdPct` (number): Percent of the cap that flips state to 'warn'. Default 80.
- `enforcement` (string): 'block' rejects a breaching run/hop (HTTP 402); 'alert' only warns. Default block.
- `limitCredits` (number, required): Spend cap in credits for the period.
- `name` (string, required): Human label for the budget.
- `periodType` (string, required): Reset cadence for the cap.
- `scopeId` (string): The project/agent id — required unless scopeType is 'org'.
- `scopeType` (string, required): What the cap applies to.

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/silvanexum-silvanexum/silvanexum-mcp#diagnostics

## Score history

- 2026-08-03: 63
- 2026-08-02: 15
- 2026-08-01: 0
- 2026-07-31: 31
- 2026-07-30: 18
- 2026-07-28: 18
- 2026-07-27: 40

## Links

- npm package: https://www.npmjs.com/package/@silvanexum/mcp
- Socket report: https://socket.dev/npm/package/@silvanexum/mcp
- Changelog RSS feed: https://verifymcp.io/servers/silvanexum-silvanexum/silvanexum-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/silvanexum-silvanexum/silvanexum-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/silvanexum-silvanexum/silvanexum-mcp