mcpField
S
scribe

scribe

Local
scribe.writulos.comDeveloper Tools0Updated 2w ago
RepositoryVisit website

About scribe

scribe is an MCP server for generating Markdown documentation from source code, for users of Writulos Scribe and MCP-compatible clients. It documents one file or batches of up to 20, returning the generated text in the client chat.

Key features

  1. 01Generate Markdown for one code file
  2. 02Document batches of up to 20 files
  3. 03Accept filenames and extra context
  4. 04Return generated docs in client chat
  5. 05Record runs in a log file

Use cases

  1. 01Document a source file while coding
  2. 02Generate docs for a group of files
  3. 03Add context to file documentation

MCP support

The server exposes `generate_docs` and `generate_docs_batch` to MCP clients. It requires a Writulos Scribe API key for generation.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "com-writulos-scribe": {
      "command": "npx",
      "args": [
        "-y",
        "writulos-mcp"
      ],
      "env": {
        "WRITULOS_API_KEY": "<WRITULOS_API_KEY>",
        "WRITULOS_OUTPUT_DIR": "<WRITULOS_OUTPUT_DIR>",
        "WRITULOS_PROJECT_ROOT": "<WRITULOS_PROJECT_ROOT>",
        "WRITULOS_API_URL": "<WRITULOS_API_URL>"
      }
    }
  }
}
Run commandnpx -y writulos-mcp
Environment variables to set
WRITULOS_API_KEYSecretYour Writulos Scribe API key, from https://scribe.writulos.com/dashboard/api-keys
WRITULOS_OUTPUT_DIRDirectory for the run log (writulos.log). Defaults to "docs", relative to the project root.
WRITULOS_PROJECT_ROOTProject root the run log is written under. Defaults to the working directory.
WRITULOS_API_URLOverride the API base URL, for testing against another deployment. Defaults to https://scribe.writulos.com/api

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmwritulos-mcp1.0.3

Tools

2

Saved tool list · updated 1w ago

ParameterTypeRequiredDescription
codestringYesThe source code to document.
contextstringNoOptional extra context about the file or project.
filenamestringNoThe filename, e.g. auth.js

Details

From the project README

writulos-mcp

Official MCP server for Writulos Scribe — generate markdown documentation for your code inside Cursor, Claude Desktop, and any MCP-compatible AI agent.

Installation

No install needed. Run directly with npx:

npx writulos-mcp

Or install globally:

npm install -g writulos-mcp

Setup in Cursor

Add this to .cursor/mcp.json in your project root:

{
  "mcpServers": {
    "writulos": {
      "command": "npx",
      "args": ["-y", "writulos-mcp"],
      "env": {
        "WRITULOS_API_KEY": "writ_YOUR_API_KEY"
      }
    }
  }
}

Restart Cursor. Then in the AI chat, ask:

Document all the files in this project using writulos

The generated docs come back in the chat — ask Cursor to save them wherever you keep documentation. The server itself only writes a run log to docs/writulos.log (set WRITULOS_OUTPUT_DIR to move it), recording each run and how many generations you have left this month.

Setup in Claude Code, Claude Desktop and other clients

Use the same command, args and env as the Cursor config above. Whichever way the client adds the server, give it WRITULOS_API_KEY: without the key the server still starts, and every tool call answers with where to get one.

Usage and limits

Each file documented uses one generation from your Writulos plan's monthly allowance, the same allowance the dashboard and the GitHub Action draw on. When it runs out, the tools say so and when it resets.

Tools

generate_docs

Generate markdown documentation for a single code file.

Inputs:

  • code (required) — the source code
  • filename (optional) — e.g. auth.js
  • context (optional) — extra context about the file
generate_docs_batch

Generate markdown documentation for up to 20 files in one request.

Inputs:

  • files (required) — array of { code, filename?, context? } objects

Requirements

Source and issues

This repository is a copy of the server, updated on every release. Report bugs and ask questions in its issues.

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.