Papapyrus
A rich text editor that speaks markdown to your AI agents

A skill library for your team

Centralize organizational knowledge in rich text

Control access, comment inline, and connect your AI agents via MCP

Sign in to your orgSee what's inside

Rich text editing · SSR-rendered · Built on Next.js 16 + Postgres

Make your organization smarter

Compose in a rich text editor. Your team reviews and refines company knowledge.

Your agents (Claude, ChatGPT, Cursor, etc.) share the same source of truth.

  • MCP server, ready out of the box

    Expose your skill library to Claude, ChatGPT, Cursor, or any MCP-aware agent. Tool calls return clean markdown so models can reason over your team's institutional knowledge in real time.

  • Robust user access controls

    Grant access at the folder or file level. Per-skill grants override folder-level access, so sensitive playbooks never leak — and every viewer is listed transparently on the page.

  • Tiered permission system

    Admins manage members and ownership; members read, write, and refine. Roles compose with per-folder grants, giving you flexibility without confusion.

  • Inline commenting and resolution

    Highlight any passage, leave a comment, resolve when it's handled. Comments anchor to the text itself, so they stay put as the document evolves.

  • A rich text editor, not raw markdown

    Format with a toolbar, slash commands, and keyboard shortcuts — headings, tables, code blocks, and lists, no markdown syntax required. Everything you write is stored and shipped to agents as clean markdown underneath.

  • Folders the way you'd expect

    Self-referencing folder tree per organization, with breadcrumbs, drag-friendly URLs, and an explorer view that scales from a handful of skills to thousands.

From scratch pad to source of truth

A clear loop from authoring to agent-readable output.

  1. 01

    Write in a rich text editor

    Capture how your team runs payroll, ships releases, or handles support — anything you'd otherwise lose to Slack history. No markdown syntax required.

  2. 02

    Review and refine together

    Comment on tricky passages, resolve threads, and let access controls keep sensitive material in the right hands.

  3. 03

    Ship it to your agents

    Plug the MCP server into Claude or Cursor and let your agents read the same source of truth your humans already trust.

Ask in plain English

Just ask Papapyrus.

No commands, no syntax, no digging through wikis. Anyone on your team can ask a question the way they'd ask a coworker — and get an answer drawn straight from your skill library, with a link back to the source.

  • Answers come from your own vetted documents
  • Every reply points back to the skill it came from
  • People only see answers from skills they're allowed to read
Your Organization's Chatbot
Ask Papapyrus, what’s our vacation policy?

Full-time employees get 20 paid days off per year, accrued monthly. You can carry up to 5 unused days into the next year. Request time off at least 2 weeks ahead through your manager.

People Ops · Time-off policy

What’s our high level Go To Market strategy?

We lead with a product-led motion — free self-serve signup to drive adoption inside teams — then layer sales-assisted expansion once an account hits 10+ active seats. Primary segment is mid-market companies with existing AI agent initiatives, reached through developer communities and partnerships.

Strategy · GTM overview

Write a message…
Model Context Protocol

Your agents should know how your org works.

Two tool calls — that's it. get_all_skills lists every skill the caller can see, organized by folder. get_skill returns one skill's full markdown — the same raw markdown your rich text edits compile down to. The MCP server respects your access controls, so agents see exactly what their human counterpart would.

  • Honors per-folder and per-file access grants
  • Sends raw markdown — no HTML cleanup needed on the agent side
  • Scoped to a single organization per session
claude · mcp · papapyrus
> Tools available
  • get_all_skills()
  • get_skill(id)

> get_all_skills()
{
  "folders": [
    {
      "name": "Engineering",
      "skills": [
        { "id": "skl_82h", "name": "Cutting a release" },
        { "id": "skl_91k", "name": "Triaging on-call pages" }
      ]
    },
    {
      "name": "Sales",
      "skills": [
        { "id": "skl_55a", "name": "Discovery call playbook" }
      ]
    }
  ]
}

> get_skill("skl_82h")
# Cutting a release
1. Open the release dashboard…

Give your org and your agents one source of truth

Stop pasting Slack threads into prompts. Stand up a skill library your humans maintain and your agents read.

Sign in to get started