appflowy

appflowy is a skill for Claude Code, Codex from ChaosChild/appflowy-mcp. It costs 55 tokens per session (1,381 once invoked), scanned A, original, MIT.

A connector for reading and writing content in AppFlowy, a workspace app for documents and databases.

In plain words
What is it for?
Use it to find workspaces and pages, create or update Markdown documents, and query or edit database rows.
Why use it?
It handles the IDs needed to find the right workspace, page, or database and includes safeguards for updating or replacing content.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to find workspaces and pages, create or update Markdown documents, and query or edit database rows.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/chaoschild/appflowy-mcp/appflowy
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.

Any agent
npx skills add ChaosChild/appflowy-mcp --skill appflowy
Clone the repo
git clone --depth 1 https://github.com/ChaosChild/appflowy-mcp

Made for: Claude Code, Codex.

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 appflowy

README.md
[![agentmods](https://agentmods.dev/badge/skills/chaoschild/appflowy-mcp/appflowy/github.svg)](https://agentmods.dev/skills/chaoschild/appflowy-mcp/appflowy)
Your own site
<a href="https://agentmods.dev/skills/chaoschild/appflowy-mcp/appflowy"><img src="https://agentmods.dev/badge/skills/chaoschild/appflowy-mcp/appflowy/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 appflowy

Your own site · 80×15
<a href="https://agentmods.dev/skills/chaoschild/appflowy-mcp/appflowy"><img src="https://agentmods.dev/badge/skills/chaoschild/appflowy-mcp/appflowy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,381 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00055 $0.01381
Opus 5 $0.00028 $0.00691
Sonnet 5 $0.00011 $0.00276
Haiku 4.5 $0.00006 $0.00138

Measured 8d ago against content hash 42dc792d4814, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

appflowy 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.

skills/appflowy/SKILL.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Working with AppFlowy

The appflowy MCP server exposes 22 tools over AppFlowy Cloud. Every call needs a workspace_id, and most need a page_id or database_id on top of that. You never know these IDs up front. Resolve them first.

Auth is automatic. Do not call get_auth_token unless a tool returns HTTP 401 twice in a row, or the user explicitly asks to mint a refresh token.

Always resolve IDs before acting

Work down this chain, and do not guess or reuse an ID from an earlier conversation:

  1. get_workspace_list gives workspace UUIDs. If there is more than one and the user did not say which, ask.
  2. get_workspace_folder(workspace_id, depth=3) gives the page tree. Match the user's page by name here.
  3. get_databases(workspace_id) gives database IDs, which are distinct from page IDs.

get_workspace_folder defaults to depth=1, which shows only top-level items. Use depth=3 or higher when hunting for a nested page, or pass root_view_id to expand one branch instead of pulling the whole tree.

To create a page at the top level of a workspace, pass the workspace_id itself as parent_view_id.

Errors

Tools do not raise. They return {"error": "...", "details": ...}. Check for error in the result before you use it, and never treat a failed call as a success. Report the details payload to the user rather than paraphrasing it.

Writing documents

Three tools write document content. Picking the wrong one destroys the page's identity.

Goal Tool Effect
New page create_document_from_markdown Creates under parent_view_id.
Add to an existing page append_markdown_to_page Appends blocks. Keeps view_id and history.
Rewrite an existing page replace_page_document Recreates the page. New view_id, links break, history lost.

Default to append_markdown_to_page. replace_page_document cannot edit in place; AppFlowy Cloud has no such endpoint, so it creates a replacement page and trashes the original. Before calling it, tell the user the page will get a new ID and that any links to it will break. If they only want to add a section, append instead. If they want to edit one paragraph in the middle, say plainly that this server cannot do a surgical edit, and offer append or full replace.

Read the full file on GitHub · 99 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 · 99 lines · 55 tokens per session scan A 42dc792d4814

Subscribe to this mod's changes

appflowy is a skill published in the GitHub repository ChaosChild/appflowy-mcp (0 stars, last pushed 29d ago), licensed MIT. It adds 55 tokens to every session and 1,381 once invoked, about $0.0003 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.