worksection-mcp CLAUDE.md

Repository instructions for developing and checking a Python MCP server, a service that exposes tools to an AI assistant. They document dependency installation, formatting, linting, type checks, tests, and architecture.

In plain words
What is it for?
Use them to install dependencies, run the full check suite or individual tests, inspect the architecture, and perform live end-to-end checks when credentials and data are available.
Why use it?
They give contributors the project’s expected commands and checks, reducing guesswork when changing the code.

Instructions file

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/pbv7/worksection-mcp/claude-md
Clone the repo
git clone --depth 1 https://github.com/pbv7/worksection-mcp
Per session 2,032 This file is loaded in full into every session.
When invoked 2,032 The same file — it is already loaded in full.
Security scan B 1 finding. Scan, not verified.
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 $0.02032 $0.02032
Opus 5 $0.01016 $0.01016
Sonnet 5 $0.00406 $0.00406
Haiku 4.5 $0.00203 $0.00203

Measured 2d ago against content hash 999ae214ff5b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

worksection-mcp CLAUDE.md scanned grade B with 1 finding 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 2d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- **Claude Code MCP config** goes in `~/.claude.json` (under `mcpServers`), NOT `~/.claude/settings.json`.
CLAUDE.md · 180 lines

How it starts

The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Commands

# Install dependencies
uv sync --frozen --extra dev

# Run all checks (format, lint, lint-docs, typecheck, test) — mirrors CI
make check

# Individual checks
make format          # ruff format (writes)
make lint            # ruff check (read-only)
make lint-docs       # markdownlint-cli2 on all *.md
make typecheck       # mypy + pyright

# Tests
make test            # pytest with coverage (HTML + term)
make test-fast       # pytest without coverage
uv run pytest tests/test_tools/test_analytics.py         # single file
uv run pytest tests/test_server.py::test_create_server   # single test
uv run pytest -k "oauth"                                 # pattern match

# Live E2E test for large response offload (requires real credentials + data)
uv run python tests/live_large_response_offload_roundtrip.py -v

# Package management — always use uv, never pip
uv add <pkg>                   # add runtime dep
uv add --optional dev <pkg>    # add dev dep
uv lock                        # regenerate uv.lock after pyproject.toml changes

Architecture

Source Layout

src/worksection_mcp/
├── server.py          # composition root — create_server()
├── mcp_protocols.py   # ToolRegistrar / ResourceRegistrar protocols
├── large_response.py  # LargeResponseStore + LargePayloadToolRegistrar
├── logging_config.py  # unified logging pipeline
├── auth/              # OAuth2Manager, token storage, SSL, callback server
├── cache/             # FileCache (disk) + SessionCache (in-memory)
├── client/            # WorksectionClient (api.py) + RateLimiter
├── config/            # Settings (pydantic-settings, .env)
├── resources/         # files.py + offload.py (MCP resources)
├── tools/             # one module per domain; offload.py = helper tools
└── utils/             # date_utils.py + response_utils.py

Server Startup

server.py:create_server() is the composition root. It wires all singletons:

Read the full file on GitHub · 180 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. 2d ago First seen · 180 lines · 2,032 tokens per session scan B 999ae214ff5b

Subscribe to this mod's changes

worksection-mcp CLAUDE.md is an instructions file published in the GitHub repository pbv7/worksection-mcp (2 stars, last pushed 3mo ago), licensed MIT. It adds 2,032 tokens to every session, about $0.0102 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.