# Agent Observability (npm · agent-observability-mcp)

Agent observability: structured logging, cost tracking, and compliance audit trails

- Trust score: 54/100 (low)
- Change this week: +36
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `agent-observability-mcp`: 54/100 (this document), [markdown](https://verifymcp.io/servers/blueskylineassets-agent-observability/agent-observability-mcp.md), [page](https://verifymcp.io/servers/blueskylineassets-agent-observability/agent-observability-mcp)

## Channel facts

- Registry: `npm`
- Package: `agent-observability-mcp`
- Version: `1.1.0`
- 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**: 70/100
  - No malware found by supply-chain analysis.
  - CVE check failed: a known high-severity CVE affects @modelcontextprotocol/sdk 0.5.0, a direct dependency. A fixed version is available.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (13 of 14), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 19/100
  - Repository check failed: no source repository is declared.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 216 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 304 tokens (~101/item across 3 items; 3 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 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**: 20/100
  - Spec-recency check failed: implements MCP spec 2024-11-05; the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add blueskylineassets-agent-observability -- npx -y agent-observability-mcp
```

### Codex

```bash
codex mcp add blueskylineassets-agent-observability -- npx -y agent-observability-mcp
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add blueskylineassets-agent-observability --command npx --arg -y --arg agent-observability-mcp
```

### Hermes

```yaml
mcp_servers:
  blueskylineassets-agent-observability:
    command: "npx"
    args: ["-y", "agent-observability-mcp"]
```

### Other

```json
{
  "mcpServers": {
    "blueskylineassets-agent-observability": {
      "command": "npx",
      "args": [
        "-y",
        "agent-observability-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 54, +4)

- [functional improvement] Stability: unverified → 0.27

### 2026-08-02 (score 50, +20)

- [security improvement] Malware scan: unverified → pass
- [functional improvement] Schema quality: unverified → good

### 2026-07-31 (score 30, −8)

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

### 2026-07-30 (score 38, −18)

- [security regression] Malware scan: pass → unverified

### 2026-07-28 (score 56, +38)

- [security regression] CVE-2025-66414 affects this package: high
- [security regression] Provenance: unverified → fail
- [security regression] Known CVEs: unverified → fail
- [security improvement] Install scripts: unverified → pass
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] License: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] Maintenance: unverified → pass
- [functional] First check of Schema quality: fail
- [functional] First check of Schema quality: pass
- [functional] First check of Tool coverage: 100
- [functional] First check of Schema quality: unverified
- [functional] Licence: MIT

### 2026-07-27 (score 18)

First indexed and scored.

## MCP tools (3)

### `log_event` (~118 tokens)

Log an agent event with metadata for observability and compliance tracking. Cost: ~$0.0001 per log (100K free/month).

Input parameters:

- `agent_id` (string): Identifier for the agent generating this log
- `event_type` (string, required): Type of event: 'api_call', 'decision', 'transaction', 'error', 'state_change'
- `metadata` (object): Structured metadata: provider, cost_usd, latency_ms, tokens_used, model, etc.
- `severity` (string): Event severity level (default: info)

### `query_logs` (~108 tokens)

Query logged events with filters. Returns recent logs matching criteria.

Input parameters:

- `agent_id` (string): Filter by agent ID
- `event_type` (string): Filter by event type
- `from_date` (string): Start date (ISO 8601 format)
- `limit` (number): Maximum number of results (default: 10, max: 100)
- `severity` (string): Filter by severity level
- `to_date` (string): End date (ISO 8601 format)

### `get_cost_analytics` (~78 tokens)

Get cost breakdown by agent, provider, or time period. Useful for tracking API spending.

Input parameters:

- `from_date` (string, required): Start date (ISO 8601 format)
- `group_by` (string): How to group cost data (default: agent_id)
- `to_date` (string, required): End date (ISO 8601 format)

## Diagnostics

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

## Score history

- 2026-08-03: 54
- 2026-08-02: 50
- 2026-08-01: 30
- 2026-07-31: 30
- 2026-07-30: 38
- 2026-07-28: 56
- 2026-07-27: 18

## Links

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