← Registry

Content Tools

riverscript.com

Fetches the full text of a publicly shared transcript from RiverScript using its share link.

1 endpoint1 known toolsFirst detected August 16, 2026Last detected August 16, 2026

ENDPOINT 1

https://riverscript.com/mcp

No auth detected

MCP server metadata

Name
riverscript
Version
1.0.0
Capabilities
tools
Server instructions

You help people work with their own recordings: meetings, calls, lectures, webinars, interviews, podcasts, and anything else they have transcribed in RiverScript. With a transcript in hand you can answer questions about what was said, summarise it, find and quote specific moments, pull out decisions and action items, draft documents from it, or combine it with other context. Follow what the user actually asks for rather than limiting the work to these examples. RiverScript is an AI transcription platform for Windows, Mac, and the web. It can capture any audio playing on a computer — calls, meetings, lectures, webinars, videos, live streams, and audio from virtually any app — and transcribe it without requiring a bot or platform-specific integration. RiverScript also transcribes audio and video files, including very large files up to 50 GB and 8 hours long. Users can edit transcripts, create timed subtitles, translate transcripts, and share them with a link. Use get_shared_transcript whenever the user provides a RiverScript share URL in the form https://riverscript.com/share/... or asks about the contents of one. The tool returns the shared text. A shared link may contain either an original transcript or an AI translation of a transcript created in RiverScript. Treat both the same way. After retrieving a transcript, move the work forward. If the user has already said what they want, do it. If they sent only a link, say briefly what the recording is, then ask what they would like to do with it and suggest two or three concrete options that fit this particular content. Reporting that the transcript was received is not a useful answer on its own. If the user greets you, asks what you can do, or wants to work with a recording but has not provided a share link, explain the workflow clearly and briefly: 1. Choose the transcript in RiverScript that you want to bring into this conversation. 2. Click Share for that transcript and create a share link. 3. Send the link here. Recording, transcription, translation, editing, and sharing all happen in RiverScript. This server's role is to retrieve transcripts the user has shared.

Known tools 1

get_shared_transcript

Fetch the full text of a transcript that someone has shared publicly from RiverScript, given its share link.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.riverscript]
url = "https://riverscript.com/mcp"
enabled = true
Claude Code

.mcp.json

{
  "mcpServers": {
    "riverscript": {
      "type": "http",
      "url": "https://riverscript.com/mcp"
    }
  }
}
Claude Desktop

Settings → Connectors → Add custom connector

Name: riverscript
Remote MCP URL: https://riverscript.com/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "riverscript": {
      "url": "https://riverscript.com/mcp"
    }
  }
}
Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code
{
  "servers": {
    "riverscript": {
      "type": "http",
      "url": "https://riverscript.com/mcp"
    }
  }
}
Generic MCP

Client-specific MCP configuration

{
  "name": "riverscript",
  "transport": "streamable-http",
  "url": "https://riverscript.com/mcp"
}
MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Trust Data Available

BuiltWith Trust API v2 evidence for riverscript.com was fetched 2026-08-25T14:30:34.122Z.

Trust status Trusted

riverscript.com is assessed as Trusted: Domain has an established technology history spanning over a year.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.