mcp-pandoc-ts: A Document Conversion MCP Server (TypeScript/Host Service Version)

Created By
mystique920a year ago
MCP-Server that can control pandoc on host from docker environment using a local pandoc host service
Overview

What is mcp-pandoc-ts?

mcp-pandoc-ts is a TypeScript-based MCP server that facilitates document conversion using the pandoc tool from a Docker environment, allowing users to convert documents between various formats such as Markdown, HTML, PDF, DOCX, and TXT.

How to use mcp-pandoc-ts?

To use mcp-pandoc-ts, set up the pandoc-host-service on your host machine, configure the PANDOC_HOST_URL, and run the mcp-pandoc-ts server in a container. You can then send conversion requests to the server.

Key features of mcp-pandoc-ts?

  • Converts documents between multiple formats using pandoc.
  • Runs in a Docker container while leveraging a host service for pandoc execution.
  • Supports various input and output formats, including Markdown, HTML, PDF, and DOCX.

Use cases of mcp-pandoc-ts?

  1. Converting Markdown documents to PDF for printing.
  2. Transforming HTML content into DOCX for word processing.
  3. Automating document format conversions in a CI/CD pipeline.

FAQ from mcp-pandoc-ts?

  • What formats does mcp-pandoc-ts support?

It supports Markdown, HTML, PDF, DOCX, and TXT formats, with LaTeX and EPUB being untested.

  • Do I need to install pandoc on the container?

No, pandoc must be installed on the host machine, and the container communicates with it via the host service.

  • Is there a way to run the service in the background?

Yes, you can use tools like nohup, screen, or tmux to run the host service in the background.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
mystique920
Star
0
Language
TypeScript
License
MIT license

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

a day ago