Omnidim Mcp Server

io.github.OmnidimPublished by GitHub account Omnidimv0.8.0Updated Oct 24, 2026

Official MCP server for OmniDimension. Drive voice agents, dispatch calls, and run bulk campaigns.

Overview

AI-generated overview

Official OmniDimension MCP server that lets an assistant create and manage voice agents, dispatch calls and bulk campaigns, and handle knowledge bases and phone

What you can do
Create, update, list, get and delete voice agents, and list available LLM, voice, STT and TTS providers to configure them with. Dispatch individual calls and review call logs. Create, fetch, act on, cancel and monitor bulk calling campaigns. List, upload, attach, detach and delete knowledge base material. List, attach, detach and import phone numbers from Twilio, Exotel or SIP. Manage child organizations, users and credits for reseller accounts.
When to use it
Useful when you want to build or adjust OmniDimension voice agents, place or review calls, run bulk calling campaigns, or manage knowledge bases and phone numbers from an MCP client such as Claude, Cursor or Windsurf.
Requirements
Either the hosted remote endpoint with OAuth, or the local npm package run through npx with Node.js. An OmniDimension API key is required, supplied as the OMNIDIM_API_KEY environment variable for the local server. Network access to OmniDimension services. A setup command can detect and configure supported MCP clients.
Before you install
The API key is a secret; the setup command stores it in a local credentials file. Tools can create, update and delete agents, knowledge base entries and phone number links, and can dispatch real calls and bulk campaigns, which may incur charges. The package sends anonymous telemetry (version, OS family, tool names, error categories) unless disabled.

Installation

In SourceWeft

  1. Open Omnidim Mcp Server in the dashboard and add it to a workspace.
  2. Connect the required credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.Omnidim%2Fomnidim-mcp-server/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config. The client completes OAuth sign-in on first connect.

{
  "mcpServers": {
    "omnidim": {
      "type": "http",
      "url": "https://mcp.omnidim.io/mcp"
    }
  }
}

README

@omnidim-ai/mcp-server

Local stdio Model Context Protocol server for OmniDimension. Drive voice agents, dispatch calls, and manage knowledge bases from Claude, Cursor, Windsurf, or any MCP-compatible client.

Looking for the hosted OAuth variant? Use https://mcp.omnidim.io/mcp instead. The hosted server is the recommended path for Claude Desktop, Claude.ai, and any client that supports HTTP MCP.

Quick start

bash
npx -y @omnidim-ai/mcp-server setup

Reuses a saved API key from ~/.config/omnidim/credentials if one exists, otherwise prompts for a new one and validates it. Then installs the server in any detected MCP client (Claude Code, Claude Desktop, Cursor, Windsurf). Get an API key at omnidim.io/api-management.

Manual install

Claude Code

bash
claude mcp add omnidim -- npx -y @omnidim-ai/mcp-server

Claude Desktop, Cursor, Windsurf

Add this block to your MCP client config:

json
{  "mcpServers": {    "omnidim": {      "command": "npx",      "args": ["-y", "@omnidim-ai/mcp-server"],      "env": {        "OMNIDIM_API_KEY": "your_api_key_here"      }    }  }}

Get your API key from omnidim.io/api-management.

Config file locations:

ClientPath
Claude Desktop (macOS)~/Library/Application Support/Claude/claude_desktop_config.json
Claude Desktop (Windows)%APPDATA%\Claude\claude_desktop_config.json
Cursor~/.cursor/mcp.json
Windsurf~/.codeium/windsurf/mcp_config.json

Tools

SurfaceTools
Agentscreate, update, list, get, delete
Callsdispatch, list logs, get log
Bulk callscreate, fetch, get, actions, cancel, live status
Knowledge baselist, upload, attach, detach, delete
Phone numberslist, attach, detach, import (Twilio, Exotel, SIP)
Providerslist LLMs, list voices, list STT, list TTS
Resellerchild orgs, users, credits (reseller accounts only)

Full API reference: docs.omnidim.io.

Local development

bash
git clone https://github.com/Omnidim/omnidim-mcp-servercd omnidim-mcp-servernpm installnpm run buildOMNIDIM_API_KEY=sk_... npm start

Inspect tools and call them interactively:

bash
OMNIDIM_API_KEY=sk_... npx @modelcontextprotocol/inspector node build/index.js

Telemetry

Anonymous usage data is sent to help us improve the package: package version, Node version, OS family, install count, session boots, tool names, and setup or crash outcomes as short error categories (e.g. config_write_error, http_500). No API keys, no tool inputs/outputs, no error messages, no file paths, no personal info.

Disable with:

bash
npx -y @omnidim-ai/mcp-server telemetry disable

Full field-by-field breakdown and other opt-out options in TELEMETRY.md.

Troubleshooting

Run the diagnostics command to see versions, detected clients, backend reachability, and recent errors:

bash
npx -y @omnidim-ai/mcp-server doctor

It never prints your API key. A local log of errors is kept at ~/.config/omnidim/logs/mcp.log (stays on your machine, never sent).

Reporting issues

See ISSUES.md for how to file bug reports, request features, or get help. Paste the doctor output into your report.

License

MIT

Source: README.md at commit de20781

Tools

0
This server asks you to sign in, so SourceWeft could not read its tools without an account and has not indexed them. What a connected account sees can depend on that account and its permissions.

Version history

1
  1. v0.8.0LatestSep 16, 2026

Score

85% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts