# AIOps Field Notes (oci · ghcr.io/labaccessnow/aiops-field-notes-mcp:0.1.1)

Audit an MCP config, price a model, size a GPU, explain network config drift. Key-free.

- Trust score: 48/100 (low)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-20

## Components

- oci · `ghcr.io/labaccessnow/aiops-field-notes-mcp:0.1.1`: 48/100 (this document), [markdown](https://verifymcp.io/servers/labaccessnow-aiops-field-notes-mcp/ghcr-io-labaccessnow-aiops-field-notes-mcp-0-1-1.md), [page](https://verifymcp.io/servers/labaccessnow-aiops-field-notes-mcp/ghcr-io-labaccessnow-aiops-field-notes-mcp-0-1-1)

## Channel facts

- Registry: `oci`
- Package: `ghcr.io/labaccessnow/aiops-field-notes-mcp:0.1.1`
- 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 2026-09-20.

- **Supply Chain Security**: 0/100
  - Malware scan not yet available for this package.
  - Known CVEs could not be checked: this artifact ships no SBOM, so there is no dependency list to read. Publishing one would let us assess it.
  - Install-script risk not yet assessed.
  - Dependency health could not be checked: this artifact ships no SBOM, so there is no dependency list to read. Publishing one would let us assess it.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 14 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 80/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 821 tokens (~117/item across 7 items; 7 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 50/100
  - Stability observed for 15 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.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 7 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 7 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### How do I install the AIOps Field Notes MCP server?

AIOps Field Notes runs locally as a container image, launched with docker run --rm -i ghcr.io/labaccessnow/aiops-field-notes-mcp:0.1.1. Ready-made configuration for Claude, Cursor, VS Code, Codex and 3 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add labaccessnow-aiops-field-notes-mcp -- docker run --rm -i ghcr.io/labaccessnow/aiops-field-notes-mcp:0.1.1
```

### Cursor

```json
{
  "mcpServers": {
    "labaccessnow-aiops-field-notes-mcp": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/labaccessnow/aiops-field-notes-mcp:0.1.1"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "labaccessnow-aiops-field-notes-mcp": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/labaccessnow/aiops-field-notes-mcp:0.1.1"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add labaccessnow-aiops-field-notes-mcp -- docker run --rm -i ghcr.io/labaccessnow/aiops-field-notes-mcp:0.1.1
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "labaccessnow-aiops-field-notes-mcp": {
      "type": "local",
      "command": [
        "docker",
        "run",
        "--rm",
        "-i",
        "ghcr.io/labaccessnow/aiops-field-notes-mcp:0.1.1"
      ],
      "enabled": true
    }
  }
}
```

### Hermes

```yaml
mcp_servers:
  labaccessnow-aiops-field-notes-mcp:
    command: "docker"
    args: ["run", "--rm", "-i", "ghcr.io/labaccessnow/aiops-field-notes-mcp:0.1.1"]
```

### Netclaw

```json
{
  "McpServers": {
    "labaccessnow-aiops-field-notes-mcp": {
      "Transport": "stdio",
      "Command": "docker",
      "Arguments": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/labaccessnow/aiops-field-notes-mcp:0.1.1"
      ]
    }
  }
}
```

### Other

```json
{
  "mcpServers": {
    "labaccessnow-aiops-field-notes-mcp": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/labaccessnow/aiops-field-notes-mcp:0.1.1"
      ]
    }
  }
}
```

## 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.

### 2026-09-19 (score 48, +1)

No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-16 (score 47, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-14 (score 46, +1)

No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-13 (score 45, +4)

- [functional improvement] Stability: unverified → 0.27

### 2026-09-05 (score 41)

First indexed and scored.

## MCP tools (7)

### `estimate_llm_cost` (~146 tokens)

Price a workload across current frontier and open-weights models. Give tokens per request and monthly request volume; returns cost per request and per month for every model, cheapest first, with the caveats that move the number (batch discounts, prompt caching, intro pricing that expires).

Input parameters:

- `filter` (string): Optional substring to limit the table, e.g. 'claude' or 'gemini'.
- `input_tokens` (number, required): Input tokens per request (a typical chat turn is 1000-3000 with context).
- `output_tokens` (number, required): Output tokens per request (typically 200-800).
- `requests_per_month` (number, required): Requests per month.

### `check_vram_fit` (~137 tokens)

Work out whether an open-weights model fits on a given GPU. Takes parameter count in billions, quantisation bit width and context length; returns weights + KV cache + overhead in GB and which common cards (and Macs) have room.

Input parameters:

- `context_tokens` (number): Context window you intend to use, in tokens.
- `params_b` (number, required): Parameter count in billions, e.g. 70 for a 70B model.
- `quant_bits` (number): Bits per weight: 16 (fp16), 8 (int8/fp8), 5, 4 (Q4) are typical.

### `audit_mcp_config` (~127 tokens)

Review an MCP client config before you trust it. Paste the JSON from .mcp.json, claude_desktop_config.json or any equivalent and it flags unpinned packages that auto-update, secrets written in plaintext, filesystem roots scoped to the whole home directory, shell entrypoints, privileged containers, credentials on the command line, unauthenticated or plain-HTTP remote servers, and database access that is not read-only — each with the fix. Nothing is read from disk; pass the text.

Input parameters:

- `config` (string, required): Contents of the MCP config file, as JSON text.

### `lookup_mcp_server` (~95 tokens)

Look up an MCP server in the curated AIOps Field Notes directory: what it connects to, who maintains it, and whether it is a reference, vendor or community server. Search by name, capability or category. An unlisted server is not condemned — the answer says how to vet it yourself.

Input parameters:

- `query` (string): Name, capability or category, e.g. 'postgres', 'browser', 'vendor'.

### `explain_config_diff` (~142 tokens)

Explain what changed between two network device config snapshots, in plain English. Works on EdgeOS, MikroTik RouterOS, OPNsense, Cisco IOS-style and EdgeSwitch configs: strips volatile lines, groups changes by config section, and tags each with a risk level and why it matters (security, routing, access, connectivity). Deterministic — no model call, nothing leaves the machine.

Input parameters:

- `after` (string, required): The later config snapshot.
- `before` (string, required): The earlier config snapshot.
- `device` (string): Optional device name, for the summary line.
- `vendor` (string): Optional vendor hint; detected from the config when omitted.

### `check_config_compliance` (~102 tokens)

Run a CIS/PCI starter pack over one network device config: telnet disabled, SSH enabled, no default SNMP community, remote logging, time sync, login banner, hashed credentials, a firewall or ACL, and idle timeout. Deterministic regex checks with framework references, so two reviewers get the same result.

Input parameters:

- `config` (string, required): The device config text.
- `vendor` (string): Optional vendor hint; detected from the config when omitted.

### `latest_field_note` (~72 tokens)

The most recent This Week in AIOps episodes — what shipped in models, agents and MCP, and what it means for the systems you run. The only tool here that touches the network; it reads a public RSS feed.

Input parameters:

- `count` (number): How many recent episodes to return (default 3).

## Diagnostics

Captured diagnostic sections: Provenance. The full working is on the page: https://verifymcp.io/servers/labaccessnow-aiops-field-notes-mcp/ghcr-io-labaccessnow-aiops-field-notes-mcp-0-1-1#diagnostics

## Score history

- 2026-09-20: 48
- 2026-09-19: 48
- 2026-09-18: 47
- 2026-09-17: 47
- 2026-09-16: 47
- 2026-09-15: 46
- 2026-09-14: 46
- 2026-09-13: 45
- 2026-09-12: 41
- 2026-09-11: 41
- 2026-09-10: 41
- 2026-09-09: 41
- 2026-09-08: 41
- 2026-09-07: 41
- 2026-09-06: 41
- 2026-09-05: 41

## Common questions

### What is the AIOps Field Notes MCP server?

AIOps Field Notes is an MCP server listed in the public MCP registry as io.github.labaccessnow/aiops-field-notes-mcp. Audit an MCP config, price a model, size a GPU, explain network config drift. Key-free. This page covers its container image (ghcr.io/labaccessnow/aiops-field-notes-mcp:0.1.1).

### Is the AIOps Field Notes MCP server safe to use?

AIOps Field Notes scores 48 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 AIOps Field Notes MCP server expose?

AIOps Field Notes exposes 7 tools: estimate_llm_cost, check_vram_fit, audit_mcp_config, lookup_mcp_server, explain_config_diff, and 2 more. Their descriptions and schemas cost roughly 821 tokens of context every time the server is loaded.

### Is the AIOps Field Notes MCP server still maintained?

AIOps Field Notes is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the AIOps Field Notes MCP server under?

AIOps Field Notes declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- Repository: https://github.com/labaccessnow/aiops-field-notes-mcp
- Website: https://aiopsfieldnotes.com/tools/
- Changelog RSS feed: https://verifymcp.io/servers/labaccessnow-aiops-field-notes-mcp/ghcr-io-labaccessnow-aiops-field-notes-mcp-0-1-1.xml
- Changelog JSON feed: https://verifymcp.io/servers/labaccessnow-aiops-field-notes-mcp/ghcr-io-labaccessnow-aiops-field-notes-mcp-0-1-1.json
- HTML version of this page: https://verifymcp.io/servers/labaccessnow-aiops-field-notes-mcp/ghcr-io-labaccessnow-aiops-field-notes-mcp-0-1-1
