What is ndpsc-case-search-mcp CLAUDE.md?

Developer instructions for an MCP server that searches case records from the North Dakota Public Service Commission, a government agency that regulates public utilities. The server reads case listings and documents from the agency's website because there is no official API.

It is for searching cases, viewing case and docket details, and retrieving document text or PDFs through an MCP server built with Python, HTTP requests, and HTML parsing.

It gives developers a clear map of the server's parts, data models, and web-scraping code. That makes it easier to maintain or extend the case-search service.

How HardMCP/ndpsc-case-search-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to HardMCP/ndpsc-case-search-mcp. 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/HardMCP/ndpsc-case-search-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/HardMCP/ndpsc-case-search-mcp

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/hardmcp/ndpsc-case-search-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/hardmcp/ndpsc-case-search-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/hardmcp/ndpsc-case-search-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/hardmcp/ndpsc-case-search-mcp/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/hardmcp/ndpsc-case-search-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/hardmcp/ndpsc-case-search-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 565 This file is loaded in full into every session.

When invoked 565 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.

Model	Per session	Once invoked
Fable 5.1	$0.00565	$0.00565
Opus 5.5	$0.00226	$0.00226
Sonnet 5.5	$0.00113	$0.00113
Haiku 4.5	$0.00056	$0.00056

Measured 2mo ago against content hash 1f0cfec24f29, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ndpsc-case-search-mcp 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 2mo 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 · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ndpsc-case-search-mcp

MCP server for searching North Dakota Public Service Commission case records. Scrapes https://apps.psc.nd.gov/cases/ — no official API exists.

Structure

src/ndpsc_case_search_mcp/
  server.py                    # FastMCP server, health route, main()
  models/
    case.py                    # Pydantic models + enums (CaseSummary, CaseDetail, DocketFile, Jurisdiction, CaseStatus, CaseCategory)
  services/
    scraper.py                 # HTTP scraping helpers (httpx + BeautifulSoup)
  tools/
    __init__.py                # ALL_TOOLS aggregation
    cases.py                   # search_cases, get_case_detail, get_docket_detail
    documents.py               # get_document_text, get_document_pdf

Architecture

Tools are plain async functions registered via mcp.tool(fn) loop in server.py
Each tool module exports an ALL list; tools/__init__.py concatenates them
Models are Pydantic BaseModel subclasses with __str__() for markdown output
Services handle all HTTP interaction with the PSC site
Tools return str — models are joined with SEPARATOR = "\n---\n"
Enums: Jurisdiction, CaseStatus, CaseCategory are str, Enum types used as tool params

Data Source

Site: https://apps.psc.nd.gov/cases/
Search is a POST form; field names: jurisdictionId, caseYear, caseSequence, caseStatusCode, caseTypeCode, caseCategoryCode, entityName, description, filedFromDate, filedToDate, closedFromDate, closedToDate
Dates must be YYYY-MM-DD (ISO format) — MM/DD/YYYY causes 500 errors
Results capped at 100 per search (server-side pagination exists but requires Java session state that doesn't survive scraping)
Case detail docket rows are JS-loaded; docket count is extracted from page text instead

Development

uv sync
uv run ndpsc-case-search-mcp          # HTTP on 0.0.0.0:8000
fastmcp run fastmcp.json              # alternative via fastmcp CLI

Deployment

Docker: docker build -t ndpsc-case-search-mcp .
Compose: compose.yaml with traefik labels for hardmcp.com/ndpsc-case-search/mcp
Transport: HTTP (streamable), stateless mode, port 8000
Health: GET /health

Read the full file on GitHub · 51 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.

2mo ago First seen · 51 lines · 565 tokens per session scan A 1f0cfec24f29

Subscribe to this mod's changes

ndpsc-case-search-mcp CLAUDE.md is an instructions file published in the GitHub repository HardMCP/ndpsc-case-search-mcp (0 stars, last pushed 7mo ago), licensed MIT. It adds 565 tokens to every session, about $0.0023 per session on Opus 5.5. 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.

Legal and compliance Research

ndpsc-case-search-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
ndpsc-case-search-mcp CLAUDE.mdHardMCP/ndpsc-case-search-mcp	Instructions file	0	7mo ago	MIT	A	565	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

ndpsc-case-search-mcp: Instructions file for Claude Code