textify-mcp
A local stdio shim for the hosted Textify MCP server that converts audio, video, images, documents, and webpages into text or Markdown. Includes tools for YouTube transcripts, audio transcription, OCR, file-to-Markdown, and webpage-to-Markdown extraction.
README
@textifyme/mcp
Local (stdio) shim for the hosted Textify MCP server — turn anything into text from any MCP
client. It bridges a local command-style MCP config to the hosted streamable-HTTP endpoint at
https://mcp.textify.me/mcp, with your API key pre-wired.
Prefer a remote connector? If your client supports remote MCP servers directly (Claude.ai "Add custom connector"), just add
https://mcp.textify.me/mcp— you don't need this package. This shim exists for clients that only accept a local command.
Tools
| Tool | What it does |
|---|---|
youtube_transcript |
Fetch a YouTube video's published captions by URL or ID. |
transcribe_audio |
Transcribe an audio/video file (URL or upload) to timestamped text. |
ocr_image |
Extract text from a photo, screenshot, or scan (incl. handwriting). |
file_to_markdown |
Convert a DOCX / PPTX / XLSX / EPUB to clean Markdown (PDF not supported). |
webpage_to_markdown |
Fetch a public URL and return clean Markdown. |
Every account gets 100 free credits/month. All calls debit the same credit ledger as the Textify REST API and website — one balance, one accounting.
Setup
Get an API key at https://textify.me/docs.
Claude Desktop / Claude Code / Cursor
{
"mcpServers": {
"textify": {
"command": "npx",
"args": ["-y", "@textifyme/mcp"],
"env": { "TEXTIFY_API_KEY": "sk_your_key" }
}
}
}
TEXTIFY_API_KEY is required — tool calls that cost credits authenticate with it as
Authorization: Bearer <key>. Get a free key (100 credits/month) at https://textify.me/account.
Configuration
| Env var | Default | Purpose |
|---|---|---|
TEXTIFY_API_KEY |
— | API key; sent as Authorization: Bearer <key>. Required for credit-costing tools. |
TEXTIFY_MCP_URL |
https://mcp.textify.me/mcp |
Endpoint override. Set to http://localhost:8788/mcp to test against a local wrangler dev. |
Extra CLI args are forwarded to the underlying mcp-remote
bridge (e.g. --debug).
How it works
The shim is a thin wrapper: it resolves the bundled mcp-remote proxy and launches it against the
Textify endpoint with your auth header attached, then pipes MCP over stdio. No Textify credentials
are stored on disk by this package; the key lives only in your client's env.
Local development
# in this package dir
npm install
TEXTIFY_MCP_URL=http://localhost:8788/mcp TEXTIFY_API_KEY=sk_test node bin/textify-mcp.mjs
# (run `pnpm --filter @app/mcp run dev` in the Textify monorepo to serve localhost:8788)
License
MIT — see LICENSE.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.