Skip to content
MCP server

AIOps Field Notes

Price LLM workloads, size GPUs and audit MCP configs from your coding agent

Runs locallyStatus and history
Install
Pricing
Open source
Platforms
CLI, self-hosted
Runs
Locally
Version
0.1.2
Listing updated
3 days ago

About AIOps Field Notes

AIOps Field Notes is an open-source MCP server for knowledge and memory. It runs locally on your machine and is started by your AI client.

Four chores the author kept doing by hand became tools: pricing a model before committing a budget, checking whether a GPU can hold a model, reviewing an MCP config before trusting it, and explaining what changed between two network device configs. The set runs without keys or accounts and sends no telemetry.

The config auditor is the centrepiece. Paste a client config and it treats each server entry as an access grant, flagging unpinned package versions, a filesystem root of "/", secrets written in plaintext, -y installs that skip confirmation and publishers outside the set the directory tracks. Each finding comes with a suggested fix.

It installs through npx from GitHub with a pinned tag, or as a Docker image, and needs Node 18 or newer for the npx route. Pricing data and the server directory it consults are the ones maintained for the AIOps Field Notes site.

Install

Run in a terminal

claude mcp add aiops-field-notes-mcp -- docker run -i --rm ghcr.io/getlarkwright/aiops-field-notes-mcp:0.1.2

Add to claude_desktop_config.json

{
  "mcpServers": {
    "aiops-field-notes-mcp": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "ghcr.io/getlarkwright/aiops-field-notes-mcp:0.1.2"
      ]
    }
  }
}
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "aiops-field-notes-mcp": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "ghcr.io/getlarkwright/aiops-field-notes-mcp:0.1.2"
      ]
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

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

Add to ~/.codeium/windsurf/mcp_config.json

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

Add to your client's MCP settings (most use this shape)

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

Tools this server provides (7)

Taken from the project documentation; the running server may differ.

estimate_llm_cost
Monthly cost of a workload on each model, cheapest first.
check_vram_fit
Whether a model at a quantization and context fits a GPU.
audit_mcp_config
Reviews an MCP config for what each server can reach.
lookup_mcp_server
Who maintains a server and what category it falls in.
explain_config_diff
What changed between two network device configs and how bad it is.
check_config_compliance
Checks a device config against CIS/PCI basics.
latest_field_note
What happened in AI ops this week.

What it does

MCP config audit
Rates each server entry by what it can reach, with severity and a fix.
LLM cost estimate
Compares monthly cost of a workload across models, cheapest first.
VRAM fit check
Tests whether a model at a given quantization and context fits a GPU.
Server lookup
Says who maintains an MCP server and whether it is reference, vendor or community.
Config diff explainer
Describes what changed on a router between two snapshots and how risky it is.
CIS/PCI basics check
Tests a device config against compliance basics.

Good for

  • Review an MCP client config before adding a new server
  • Budget a monthly LLM bill across several models
  • Check if a 70B model at Q4 fits on a 4090
  • Explain an overnight router config change
  • Look up who publishes an unfamiliar MCP server

Pricing

Open source

Free, MIT licence

Prices change. Check aiopsfieldnotes.com before you buy.

AIOps Field Notes FAQ

Does it need an account or key?

No. It is described as free, MIT licensed, with no account and no telemetry.

How do I install it?

Run claude mcp add with npx and the pinned GitHub tag v0.1.2, or use the ghcr.io Docker image; the npx route needs Node 18 or newer.

Why pin the version?

An unpinned package runs whatever version is published at launch, which the config auditor itself flags as a high-severity issue.

Is AIOps Field Notes free?

Yes. AIOps Field Notes is open source, so you can use and self-host it for free.

How do I add AIOps Field Notes to Claude Code?

Run this command in your terminal: claude mcp add aiops-field-notes-mcp -- docker run -i --rm ghcr.io/getlarkwright/aiops-field-notes-mcp:0.1.2

What are the best alternatives to AIOps Field Notes?

The closest alternatives to AIOps Field Notes are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.

Alternatives to AIOps Field Notes

  1. REA

    MCP server

    CLI and MCP server that lets coding agents reverse engineer apps and binaries

    Runs locally
    • Open source
    • 464K GitHub stars
    • Developer tools
  2. Codebase Memory

    MCP server

    Local MCP server that builds a code knowledge graph for AI coding agents

    Runs locally
    • Open source
    • 48.7K GitHub stars
    • Knowledge and memory
  3. GitHub

    MCP server

    Official MCP server connecting AI assistants to GitHub repos, issues and workflows

    Not checked yet
    • Remote
    • Open source
    • 34.5K GitHub stars
    • Developer tools
  4. MCP toolkit giving coding agents symbol-level code retrieval and editing

    Runs locally
    • Open source
    • 31.5K GitHub stars
    • Developer tools
  5. XERJ

    MCP server

    Local search engine for AI agents with cited answers over your code and docs

    Runs locally
    • Open source
    • 19.2K GitHub stars
    • Knowledge and memory
  6. Ouroboros

    MCP server

    Spec-first layer that pins requirements and verifies results of AI coding agent work

    Runs locally
    • Open source
    • 6.4K GitHub stars
    • Developer tools