Skip to content
MCP server

SecOps Field Notes

CVSS scoring, IOC extraction, email header triage and KEV lookup for analysts

Runs locallyStatus and history
Install
Pricing
Open source
Platforms
CLI, self-hosted
Runs
Locally
Version
0.1.1
Listing updated
3 days ago

About SecOps Field Notes

SecOps 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.

The routine bench work of a security analyst, exposed as tools. Everything except the KEV lookup runs on your own machine, takes text as input and reads nothing from disk. The one network call fetches CISA's exploited-vulnerabilities feed, cached for an hour.

The CVSS tool computes the 3.1 base score the way FIRST specifies, using integer arithmetic in the rounding step so floating-point noise cannot push a 4.0 to 4.1; the README notes the Log4Shell vector scores 10.0. The email header tool puts the Received chain in order, computes hop delays, finds the first public IP and reads SPF, DKIM and DMARC results, then warns about mismatches such as a different Reply-To domain.

Other tools pull IOCs out of reports and defang them, identify hash types by shape, decode JWTs without verifying signatures, convert timestamps including Windows FILETIME, and peel layered encodings. Licensed MIT.

Install

Run in a terminal

claude mcp add secops-field-notes-mcp -- docker run -i --rm ghcr.io/getlarkwright/secops-field-notes-mcp:0.1.1

Add to claude_desktop_config.json

{
  "mcpServers": {
    "secops-field-notes-mcp": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "ghcr.io/getlarkwright/secops-field-notes-mcp:0.1.1"
      ]
    }
  }
}
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "secops-field-notes-mcp": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "ghcr.io/getlarkwright/secops-field-notes-mcp:0.1.1"
      ]
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "secops-field-notes-mcp": {
      "type": "stdio",
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "ghcr.io/getlarkwright/secops-field-notes-mcp:0.1.1"
      ]
    }
  }
}

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

{
  "mcpServers": {
    "secops-field-notes-mcp": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "ghcr.io/getlarkwright/secops-field-notes-mcp:0.1.1"
      ]
    }
  }
}

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

{
  "mcpServers": {
    "secops-field-notes-mcp": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "ghcr.io/getlarkwright/secops-field-notes-mcp:0.1.1"
      ]
    }
  }
}

Tools this server provides (10)

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

cvss_score
CVSS 3.1 base score from a vector or metrics.
extract_iocs
Extract and defang indicators from text.
defang_text
Defang or refang URLs and addresses.
analyze_email_headers
Order the Received chain and read SPF, DKIM and DMARC.
identify_hash
Identify a hash type by shape.
decode_jwt
Decode a JWT header and payload.
convert_timestamp
Convert epoch, FILETIME, ISO 8601 and RFC 2822 timestamps.
decode_layers
Chain common decodings and show each layer.
lookup_kev
Check whether a CVE is in CISA's KEV list.
latest_field_note
What got exploited this week.

What it does

CVSS 3.1 scoring
Computes base scores from a vector or the eight metrics.
IOC extraction
Pulls IPs, domains, URLs, emails, CVE ids and hashes, defanged on output.
Email header triage
Orders the Received chain, reads SPF/DKIM/DMARC and flags mismatches.
KEV lookup
Checks a CVE against CISA's list, with date added, due date and ransomware use.
JWT decoding
Shows header and payload with dates, flagging alg:none and tokens that never expire.
Layered decoding
Chains base64, hex, URL, HTML-entity and ROT13 steps and shows each layer.

Good for

  • Score a CVE from its vector for a ticket
  • Defang indicators before pasting a report into chat
  • Triage a suspicious email from raw headers
  • Check if a vulnerability is exploited in the wild
  • Identify an unknown password hash format

Pricing

Open source

Free, MIT licence

Prices change. Check secopsfieldnotes.com before you buy.

SecOps Field Notes FAQ

Which tool touches the network?

Only lookup_kev, which reads CISA's feed and caches it for an hour; latest_field_note reads an RSS feed.

Does decode_jwt verify signatures?

No. It decodes and says so on every result.

Which hash types can it identify?

It covers bcrypt, Argon2, yescrypt, Unix crypt, LM:NT, MD5/NTLM and the SHA-1 and SHA-2 family, by shape.

Does it need an account?

No account, key or telemetry; it is free and MIT licensed.

Is SecOps Field Notes free?

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

How do I add SecOps Field Notes to Claude Code?

Run this command in your terminal: claude mcp add secops-field-notes-mcp -- docker run -i --rm ghcr.io/getlarkwright/secops-field-notes-mcp:0.1.1

What are the best alternatives to SecOps Field Notes?

The closest alternatives to SecOps Field Notes are REA, Codebase Memory, XERJ, Claude Code Ultimate Guide and Nautilus Compass Memory.

Alternatives to SecOps 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. 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
  4. MCP server for searching the Claude Code Ultimate Guide from any MCP client

    Runs locally
    • Open source
    • 6.5K GitHub stars
    • AI models and LLM tooling
  5. Local-first long-term memory layer for AI agents, served over MCP

    Not checked yet
    • 5 tools
    • Remote
    • Open source
    • 1.3K GitHub stars
    • Knowledge and memory
  6. Agent Roast

    MCP server

    Offline review that flags agent changes which weaken tests, assertions or CI

    Runs locally
    • Open source
    • 4 Hacker News points
    • Developer tools