leafwiki-mcp AGENTS.md

Repository instructions for LeafWiki MCP, a Python server that lets coding agents discover, organize, revise, favorite, and change LeafWiki pages.

In plain words
What is it for?
Use it when working on this repository, especially when setting it up, changing its MCP tools, or running linting, type checks, formatting checks, and tests.
Why use it?
It gives contributors the setup commands, project boundaries, coding conventions, and quality checks needed to make consistent changes.

Instructions file for CodexOpenCode

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/ipapadop/leafwiki-mcp/agents-md
Clone the repo
git clone --depth 1 https://github.com/ipapadop/leafwiki-mcp

Made for: Codex, OpenCode.

Per session 2,878 This file is loaded in full into every session.
When invoked 2,878 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.

ModelPer sessionOnce invoked
Fable 5 $0.02878 $0.02878
Opus 5 $0.01439 $0.01439
Sonnet 5 $0.00576 $0.00576
Haiku 4.5 $0.00288 $0.00288

Measured 2d ago against content hash 9bf32550bcdf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

leafwiki-mcp AGENTS.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.

AGENTS.md · 249 lines

How it starts

The opening of the file, as written. The whole thing — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Project overview

This repository implements a Python MCP server for a LeafWiki instance. It exposes LeafWiki page discovery, organization, revision, favorite, and mutation operations as MCP tools over stdio. The package uses a src layout and requires Python 3.12 or newer.

The canonical repository is https://github.com/ipapadop/leafwiki-mcp, the default branch is main, and the conventional remote name is origin.

Keep changes focused on this integration. Consult README.md for user-facing setup and the current tool inventory; update it when configuration, commands, or exposed tools change.

Setup and commands

Use uv for dependency management and command execution:

uv sync
uv run leafwiki-mcp

These commands set up and run a source checkout. Do not describe the project as installable from PyPI unless a published distribution and its installation workflow have been verified.

Canonical quality checks are:

uv run ruff check .
uv run ruff format --check .
uv run pyright
uv run pytest

The Quality GitHub Actions workflow runs Ruff lint, Ruff formatting verification, Pyright, and Pytest for pull requests, pushes to main, and manual dispatches. These are the same canonical quality checks required locally before completion.

During development, run the narrowest relevant test first, for example:

uv run pytest tests/test_client.py -q
uv run pytest tests/test_server.py -q
uv run pytest tests/test_client.py::test_get_page_by_path_encodes_query -q

Do not assume a live LeafWiki instance is available for tests. To exercise the server manually, configure LEAFWIKI_URL, LEAFWIKI_USERNAME, and LEAFWIKI_PASSWORD as described in README.md. Authentication-disabled instances need only the URL.

Architecture and boundaries

  • src/leafwiki_mcp/client.py is the LeafWiki HTTP/API boundary. It owns URL normalization, the cookie-preserving HTTPX session, authentication, CSRF handling, request encoding, response validation, API error translation, and page models.
  • src/leafwiki_mcp/server.py is the MCP adaptation layer. LeafWikiTools should remain a collection of typed, synchronous operations that delegate API behavior to LeafWikiClient. create_server() explicitly registers the public tools.
  • src/leafwiki_mcp/__main__.py owns CLI parsing, LEAFWIKI_* environment defaults, client lifetime, authentication, and starting FastMCP with transport="stdio".
  • tests/test_client.py verifies HTTP contracts with httpx.MockTransport, including methods, paths, query parameters, headers, cookies, bodies, parsing, and failures.
  • tests/test_server.py verifies that MCP-facing operations preserve semantics while delegating to a mocked LeafWikiClient.

Read the full file on GitHub · 249 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 · 249 lines · 2,878 tokens per session scan A 9bf32550bcdf

Subscribe to this mod's changes

leafwiki-mcp AGENTS.md is an instructions file published in the GitHub repository ipapadop/leafwiki-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 2,878 tokens to every session, about $0.0144 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.