What is kwork-mcp CLAUDE.md?

Project instructions for kwork-mcp, a server that exposes tools for managing the Kwork freelance marketplace through Claude. They describe the project layout, commands, authentication, errors, and testing.

Use them when developing, testing, or troubleshooting kwork-mcp and its Kwork marketplace tools.

They give an agent the project-specific context needed to work safely and consistently in the codebase. They also document how to check formatting, run tests, and start the server.

kwork-mcp CLAUDE.md — Instructions file by simonether

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/simonether/kwork-mcp/claude-md

Clone the repo

git clone --depth 1 https://github.com/simonether/kwork-mcp

Per session 1,424 This file is loaded in full into every session.

When invoked 1,424 The same file — it is already loaded in full.

Security scan A 0 findings. 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.

Model	Per session	Once invoked
Fable 5	$0.01424	$0.01424
Opus 5	$0.00712	$0.00712
Sonnet 5	$0.00285	$0.00285
Haiku 4.5	$0.00142	$0.00142

Measured 2d ago against content hash 4e1690319ecc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

kwork-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 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.

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 · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

kwork-mcp

MCP server exposing 25 tools for managing Kwork freelance marketplace via Claude. Wraps pykwork (kwork>=0.2.0) with FastMCP 3.x.

Commands

uv run ruff check . — lint
uv run ruff format --check . — format check
uv run python -m pytest tests/ -x -v — run tests
uv run python -m pytest tests/ -x -v --cov=kwork_mcp --cov-report=term-missing — tests + coverage
uv run python -m kwork_mcp — start server (stdio)

Project Map

src/kwork_mcp/
  __init__.py        — main() entry point (loguru -> stderr, then server.run stdio)
  __main__.py        — python -m kwork_mcp
  config.py          — KworkConfig (pydantic-settings, KWORK_ env prefix)
  session.py         — KworkSessionManager (lazy auth, token persistence, web login, get_exchange_info)
  server.py          — FastMCP("kwork", lifespan=lifespan), tool registration
  errors.py          — api_guard() context manager (KworkException -> ToolError, auto-relogin on 401)
  rate_limiter.py    — InProcessRateLimiter (sliding window, deque + asyncio.Lock)
  utils.py           — shared utilities (formatting, validation, response helpers, tool annotations)
  tools/             — 8 modules, 28 tools (profile, projects, offers, orders, dialogs, kworks, categories, notifications)
tests/               — config, rate_limiter, session, errors, utils, tools tests (97 tests)

Architecture

FastMCP 3.x lifespan yields {"session": KworkSessionManager} — tools access via ctx.lifespan_context["session"]
Auth priority: KWORK_TOKEN env -> ~/.kwork_token file -> fresh login (KWORK_LOGIN + KWORK_PASSWORD)
Rate limiter: in-process sliding window (no Redis) — call session.rate_limit() before every API call
Web flow: submit_offer requires ensure_web_client() (triggers web_login("/exchange") once)
Transport: stdio only — all logging to stderr via loguru (stdout = MCP JSON-RPC)
pykwork direct: use kwork.Kwork (aka KworkClient) directly, NOT Pikka's wrapper
Auto-relogin: api_guard(session=session) catches 401 and calls session.relogin()
Error sanitization: error details go to loguru (stderr), not to the agent; mask_error_details=True on FastMCP
Tool annotations: ANNO_READ / ANNO_WRITE / ANNO_DESTRUCTIVE from utils.py
Input validation: validate_positive_int() (alias validate_positive_id), validate_page(), validate_not_empty() from utils.py

Read the full file on GitHub · 93 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.

2d ago First seen · 93 lines · 1,424 tokens per session scan A 4e1690319ecc

Subscribe to this mod's changes

kwork-mcp CLAUDE.md is an instructions file published in the GitHub repository simonether/kwork-mcp (3 stars, last pushed 1mo ago), licensed MIT. It adds 1,424 tokens to every session, about $0.0071 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.

Debugging Planning Testing claude freelance kwork mcp mcp-server python

deepagents AGENTS.md

AGENTS.md instructions for langchain-ai/deepagents, covering global development guidelines for the deep agents monorepo, corridor security analysis, development workflow, suppressing ruff rules and pr conventions.

langchain-ai/deepagents · 2,268 tokens

python-cheatsheet copilot-instructions.md

Copilot instructions for labex-labs/python-cheatsheet, covering python cheatsheet - ai coding assistant instructions, project overview, architecture & key patterns, content structure and routing & layout system.

labex-labs/python-cheatsheet · 1,155 tokens

autoharness AGENTS.md

Instructions for tigerless-labs/autoharness: This repo uses Open Knowledge — collaborative markdown via MCP. .open-knowledge/config.yml (with optional /.open-knowledge/config.yml; CLI/env may override) is the path contract: content.dir is the root for relative paths; content.include lists globs that add markdown…

tigerless-labs/autoharness · 2,201 tokens

kwork-mcp CLAUDE.md