fieldcure-mcp-publicdata: Instructions file for Claude Code

CLAUDE.md

fieldcure-mcp-publicdata CLAUDE.md is an instructions file for Claude Code from fieldcure/fieldcure-mcp-publicdata. It costs 2,058 tokens per session, scanned A, original, MIT.

Repository instructions for a .NET MCP server that connects AI clients to more than 80,000 Korean public-data APIs. They describe the server layout, API-key handling, request validation and response conversion.

In plain words
What is it for?
Use them when developing or testing this public-data MCP server. They cover API discovery, API descriptions, API calls, key resolution, domain allowlisting, XML-to-JSON conversion and error handling.
Why use it?
They give an agent the project’s build, test and credential rules before it changes the server. This reduces errors around API authentication, unsafe outbound requests and Korean XML or character encoding.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions Claude Code.

This is fieldcure/fieldcure-mcp-publicdata's own configuration. It tells Claude Code how to work on fieldcure-mcp-publicdata itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything fieldcure-mcp-publicdata configures →

Reuse

Borrowing it

Nothing to install: this file belongs to fieldcure/fieldcure-mcp-publicdata. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/fieldcure/fieldcure-mcp-publicdata/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/fieldcure/fieldcure-mcp-publicdata

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for fieldcure-mcp-publicdata CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/fieldcure/fieldcure-mcp-publicdata/claude-md/github.svg)](https://agentmods.dev/instructions/fieldcure/fieldcure-mcp-publicdata/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/fieldcure/fieldcure-mcp-publicdata/claude-md"><img src="https://agentmods.dev/badge/instructions/fieldcure/fieldcure-mcp-publicdata/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for fieldcure-mcp-publicdata CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/fieldcure/fieldcure-mcp-publicdata/claude-md"><img src="https://agentmods.dev/badge/instructions/fieldcure/fieldcure-mcp-publicdata/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,058 This file is loaded in full into every session.
When invoked 2,058 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.02058 $0.02058
Opus 5 $0.01029 $0.01029
Sonnet 5 $0.00412 $0.00412
Haiku 4.5 $0.00206 $0.00206

Measured 8d ago against content hash 25faa83d3203, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

fieldcure-mcp-publicdata CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

FieldCure.Mcp.PublicData.Kr

MCP server that bridges LLM clients to 80,000+ Korean public data APIs on data.go.kr. Distributed as a .NET tool (fieldcure-mcp-publicdata-kr) and NuGet package (FieldCure.Mcp.PublicData.Kr).

Solution layout

src/FieldCure.Mcp.PublicData.Kr/
├── Program.cs                     # stdio MCP server entry point (no startup hard-fail)
├── Services/
│   ├── ApiKeyResolver.cs          # env var → Elicitation → soft-fail chain + session cache
│   ├── InvalidApiKeyException.cs  # Signals upstream auth rejection (401/403 or body)
│   ├── KeyedCall.cs               # resolve → run → invalidate → retry helper
│   ├── PublicDataHttpClient.cs    # HTTP proxy with serviceKey injection
│   ├── DomainWhitelist.cs         # SSRF prevention via host whitelist
│   ├── ResponseNormalizer.cs      # XML → JSON normalization, EUC-KR support
│   └── ErrorCodeMapper.cs         # Korean guidance for data.go.kr result codes
└── Tools/
    ├── DiscoverApiTool.cs         # discover_api
    ├── DescribeApiTool.cs         # describe_api
    └── CallApiTool.cs             # call_api

tests/FieldCure.Mcp.PublicData.Kr.Tests/   # MSTest — DomainWhitelist, ErrorCodeMapper, ResponseNormalizer

Build & test

dotnet build                        # build the project
dotnet test                         # run MSTest suite
pwsh scripts/publish-nuget.ps1      # pack → sign (EV dongle) → push
pwsh scripts/publish-nuget.ps1 -SkipSign -SkipPush   # local pack only

publish-nuget.ps1 expects a Fieldcure GlobalSign code-signing cert on the USB dongle and a NUGET_API_KEY env var (or -NuGetApiKey). Never bypass signing unless explicitly asked.

Credential model (ADR-001)

This repo is the Phase 1 pilot for ADR-001 MCP Credential Management. The principles below must hold for any future change; they also apply verbatim to the Phase 2 (Essentials v2.1) and Phase 3 (Outbox v2.0) rollouts.

Read the full file on GitHub · 145 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 145 lines · 2,058 tokens per session scan A 25faa83d3203

Subscribe to this mod's changes

fieldcure-mcp-publicdata CLAUDE.md is an instructions file published in the GitHub repository fieldcure/fieldcure-mcp-publicdata (0 stars, last pushed 3mo ago), licensed MIT. It adds 2,058 tokens to every session, about $0.0103 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.