mcp server

live

Use the SHRP MCP server directly inside Claude Desktop, Cursor, Windsurf, and any MCP-compatible AI agent. Add SHRP once to your Model Context Protocol config and your agent can pull YouTube transcripts and generate speech natively. Speech-to-text is live today through the SHRP REST API while the MCP transcribe tool is being scoped separately.

// what is mcp

model context protocol

the model context protocol lets ai tools like claude desktop, cursor, and windsurf call external capabilities as native tools.

tools, not endpoints

instead of writing fetch() calls, your ai agent calls shrp mcp tools directly. youtube_transcript and text_to_speech behave like built-in functions.

one config, everywhere

add your shrp api key to your mcp config once. every project that uses that config gets access to shrp automatically.

// mcp tools

youtube_transcriptlive

Extract a transcript from any YouTube video URL. Returns plain text or SRT.

url: stringformat?: "text" | "srt"
text_to_speechlive

Convert text to speech using Google Neural voices. Returns base64 MP3 audio.

text: stringvoiceName: stringlanguageCode: stringspeed?: number
/api/v1/transcriberest live

upload audio or video through the live rest api for speech-to-text. the mcp transcribe tool is not exposed yet because file upload semantics need a separate mcp design.

view rest api docs →

// setup

add shrp to your mcp config with your api key. the server url and auth header are the same regardless of which client you use.

mcp config (any client)
{
  "mcpServers": {
    "shrp": {
      "url": "https://shrp.app/api/mcp",
      "headers": {
        "Authorization": "Bearer shrp_live_..."
      }
    }
  }
}
Claude Desktop
claude_desktop_config.json
~/Library/Application Support/Claude/
Cursor
.cursor/mcp.json
project root or ~/.cursor/
Windsurf
.codeiumrc
project root
Any MCP client
mcp config
per-client docs

// how it works in practice

1
generate an api key

go to /dashboard/api-keys and generate a shrp_live_ key. free accounts get 2 keys.

2
add to your mcp config

paste the config snippet above into your claude desktop, cursor, or windsurf mcp settings with your key.

3
use it naturally

tell your ai agent "get me the transcript of this video" or "convert this to speech" — it calls shrp automatically.

// why mcp over the rest api

no glue code

the rest api requires you to write fetch calls and handle responses. mcp tools are called directly by the ai — zero boilerplate.

works mid-conversation

your ai agent can pull a youtube transcript or generate audio mid-task, without leaving the conversation or switching tools.

composable

chain tools together. pull a youtube transcript → summarise → convert summary to speech. all in one ai agent flow.

same auth, same quota

uses your existing api key and plan. no new accounts, no separate billing.

// mcp faq

Is the SHRP MCP server live?

Yes. The SHRP MCP server is live for youtube_transcript and text_to_speech tools. Speech-to-text is currently available through the REST API.

Can I use SHRP MCP with Claude Desktop?

Yes. Add the SHRP MCP server URL and your SHRP API key to Claude Desktop using the MCP config shown on this page.

Does SHRP MCP work with Cursor and Windsurf?

Yes. SHRP uses the Model Context Protocol, so it can be configured in Cursor, Windsurf, Claude Desktop, and other MCP-compatible clients.

Does the MCP server include speech-to-text?

Not yet as an MCP tool. The speech-to-text API is live at POST /api/v1/transcribe, while MCP file upload support is being scoped separately.

// start using shrp mcp

get api key →rest api docs