mcpField
A
AIOps Field Notes

AIOps Field Notes

Local
aiopsfieldnotes.comCloud & Infra0Updated 6d ago

About AIOps Field Notes

AIOps Field Notes provides tools for AI operations and infrastructure reviews, aimed at agents handling cost, GPU, MCP security, and network configuration questions. It combines local analysis with a single optional public RSS lookup and does not require an account or key.

Key features

  1. 01Estimate monthly model costs
  2. 02Check GPU memory fit for models
  3. 03Audit MCP server configuration risks
  4. 04Explain network configuration changes
  5. 05Check device configuration compliance
  6. 06Fetch the latest field note

Use cases

  1. 01Compare model costs before budgeting
  2. 02Check GPU capacity before ordering hardware
  3. 03Review an MCP config for access risks
  4. 04Assess router changes or baseline compliance

MCP support

Exposes cost, GPU sizing, MCP configuration audit, server lookup, network diff, compliance, and field-note tools to MCP clients. Most analysis runs without network access; the latest field note tool fetches a public RSS feed.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"getlarkwright-aiops-field-notes": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/getlarkwright/aiops-field-notes-mcp:0.1.2"
]
}
}
}
Run commanddocker run -i --rm ghcr.io/getlarkwright/aiops-field-notes-mcp:0.1.2

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
ocighcr.io/getlarkwright/aiops-field-notes-mcp:0.1.2

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

AIOps Field Notes MCP server

Four things I kept doing by hand while running AI in production, turned into tools an agent can call: price a model before committing a budget, size a GPU before ordering one, review an MCP config before trusting it, and explain what changed in a network device config.

Free, MIT, no account, no telemetry.

Install

Pin the version — see audit_mcp_config for why.

Claude Code

claude mcp add aiops-field-notes -- npx -y github:getlarkwright/aiops-field-notes-mcp#v0.1.2

Claude Desktop, Cursor, or any client with a JSON config

{
  "mcpServers": {
    "aiops-field-notes": {
      "command": "npx",
      "args": ["-y", "github:getlarkwright/aiops-field-notes-mcp#v0.1.2"]
    }
  }
}

Docker

{
  "mcpServers": {
    "aiops-field-notes": {
      "command": "docker",
      "args": ["run", "-i", "--rm", "ghcr.io/getlarkwright/aiops-field-notes-mcp:0.1.2"]
    }
  }
}

Node 18 or newer for the npx route; nothing else to configure either way. The server is also in the official MCP registry as io.github.getlarkwright/aiops-field-notes-mcp.

Tools

ToolWhat it answers
estimate_llm_costWhat does this workload cost per month on each model, cheapest first?
check_vram_fitDoes a 70B model at Q4 fit on my 4090 with a 32K context?
audit_mcp_configIs this MCP config safe to trust — what can each server actually reach?
lookup_mcp_serverWhat is this server, who maintains it, and is it reference, vendor or community?
explain_config_diffWhat changed on this router between two snapshots, and how bad is it?
check_config_complianceDoes this device config pass the CIS/PCI basics?
latest_field_noteWhat happened in AI ops this week?
audit_mcp_config

The one I use most. Paste a client config and it reads it the way a reviewer would — every server entry is an access grant, so the questions are what it can reach, who publishes it, and what happens the next time it auto-updates:

6 servers reviewed — 7 high, 6 medium, 0 low.

files
  [high] Package version is not pinned
    files runs "@modelcontextprotocol/server-filesystem" at whatever version is published when it launches.
    fix: Pin it — "@modelcontextprotocol/server-filesystem@<version>" for npm, "@modelcontextprotocol/server-filesystem==<version>" for uvx — and bump deliberately.
  [high] Filesystem root is wide open
    files is granted "/" — that is the whole home directory or the whole disk, including keys and browser profiles.
    fix: Scope the server to the project directories the agent actually works in.
  [medium] Installs without prompting
    files passes -y, so a new release installs and runs with no confirmation.
    fix: Keep the flag only alongside a pinned version, so what installs is what you reviewed.

notes
  [high] Package version is not pinned
    notes runs "some-random-notes-mcp" at whatever version is published when it launches.
    fix: Pin it — "some-random-notes-mcp@<version>" for npm, "some-random-notes-mcp==<version>" for uvx — and bump deliberately.
  [high] Secret is stored in the config file
    notes has NOTES_API_KEY written out in plaintext; config files get committed, synced and screenshared.
    fix: Reference the environment instead — "NOTES_API_KEY": "${NOTES_API_KEY}" — and keep the value in your secret store.
  [medium] Installs without prompting
    notes passes -y, so a new release installs and runs with no confirmation.
    fix: Keep the flag only alongside a pinned version, so what installs is what you reviewed.
  [medium] Publisher not in the tracked set
    "some-random-notes-mcp" is not one of the reference or vendor servers this directory tracks.
    fix: Read the source and check the publisher before wiring it into an agent that touches production.

It also flags shell entrypoints, privileged containers, host-root mounts, credentials on the command line, database access that is not read-only, unauthenticated remote servers, and anything reached over plain HTTP.

What it does not do

  • No account, no signup, no key.
  • No telemetry. Nothing about your usage leaves your machine.
  • No filesystem access. audit_mcp_config takes the config as text, so the server never reads your disk.
  • One network call in the whole package: latest_field_note fetches a public RSS feed. Skip that tool and this server never opens a socket.

The cost table, GPU list and server directory match the calculators at aiopsfieldnotes.com/tools and get re-verified with each weekly episode. Pricing moves — check the vendor's page before you commit a budget to it.

Where the network tools come from

explain_config_diff and check_config_compliance are the read-only core of DriftWatch, which runs the same rules nightly across a fleet and keeps the history. Here you get the single-shot version, on two snapshots you paste, with no storage and no scheduler. That is deliberate: the rules are the useful part, and they work fine on their own.

Licence

MIT © Larkwright LLC. Written by James Son — network, security, and automation engineer — and tested in a live multi-vendor lab. Contributions and corrections welcome.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.