@rymi/mcp
OfficialAllows configuring Deepgram as a speech-to-text (STT) and text-to-speech (TTS) provider for voice agents, including model selection and fallback settings.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@@rymi/mcpCreate a new AI voice agent for customer support"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
@rymi/mcp
The Rymi MCP server — create and manage AI voice agents from any MCP-capable client.
Point Claude Desktop, Claude Code, Cursor, or a Rymi voice agent at this server and manage your entire voice-agent fleet — agents, calls, numbers, knowledge, and usage — without writing a line of HTTP code.
Documentation · Dashboard · Node SDK · Python SDK
🚀 Two ways to run it
☁️ Hosted — no install, no API key
Add https://mcp.rymi.live/mcp as a custom connector and sign in. In Claude:
Settings → Connectors → Add custom connector. Paste the URL exactly — no
trailing slash, since OAuth identifies the server by that string.
Signing in grants the connector everything you can do in Rymi, acting as you. Revoke any time from Settings.
Clients without OAuth (and CI) can pass a secret key against the same host instead:
{
"mcpServers": {
"rymi": {
"type": "http",
"url": "https://mcp.rymi.live/",
"headers": {
"Authorization": "Bearer rymi_your_secret_key"
}
}
}
}💻 Local — via npx
Run the server on your own machine — it speaks stdio by default and talks to the Rymi REST API directly. The key is read from the RYMI_API_KEY environment variable.
{
"mcpServers": {
"rymi": {
"command": "npx",
"args": ["-y", "@rymi/mcp"],
"env": {
"RYMI_API_KEY": "rymi_your_secret_key"
}
}
}
}Options:
RYMI_MCP_READONLY=1hides every mutating tool (includingcreate_call,batch_call,publish_agent).This package speaks stdio only.
--transport httpwas removed in 2.0.0 — use the hosted endpoint above, which the local server could never match on auth (it has no OAuth, and no per-key tool gating).
Related MCP server: Mistral Agent Manager
🧰 Tools
⚠️ Gated tools
create_call and batch_call place real, billable outbound calls; publish_agent flips an agent live to end users.
What restrains them depends on which server you're talking to.
Hosted
mcp.rymi.live— tools are filtered by your tenant role, on both OAuth and API keys. Anowner/adminsees everything; amembergets agent-scoped tools only, with account-scoped writes (billing, keys, numbers, DNC) never registered.RYMI_MCP_READONLYdoes not apply there.Local
@rymi/mcp— no role filtering. Full write surface unless you start it withRYMI_MCP_READONLY=1, which hides every mutating tool at once. That flag is set by whoever starts the server, so it guards a local run you configure, not a key you hand out.
Either way, role filtering bounds the tool surface, not the credential: a key or token stays valid against the REST API directly. Treat MCP access as equivalent to handing over your own account access.
Carrier connect/disconnect and publishable-key creation/revocation are intentionally not exposed over MCP (they enter credentials and change standing configuration) — do those from the dashboard.
⚙️ Configuring an agent
create_agent and update_agent accept the full agent configuration surface. Always call list_llm_options first to get valid model and voice IDs.
Agents created over MCP are custom agents — you choose the model stack and they're billed at component cost + a flat $0.02/min platform fee. (Managed "Rymi-Curated" SKUs are picked from the dashboard.)
Multi-language / bilingual — set
supported_languagesto every BCP-47 tag the agent should handle, e.g.["hi-IN","en-US"]. The primarylanguageis merged in automatically. The server resolves the per-language model stack for you; some languages may fall back to a different provider.Model stack — pin
llm_provider+llm_model, and optionallystt_provider/stt_modelandtts_provider/tts_model. Realtime LLMs (and Deepgram TTS) carry their own voice, so leavevoiceempty for those.Fallbacks —
llm_fallback_*,stt_fallback_*,tts_fallback_*set a secondary provider/model per channel. Passnullto clear.Self-hosted endpoints (Enterprise) —
custom_llm_url,custom_voice_url(+custom_voice_mode),custom_transcriber_url.https://orwss://only;nullclears.persona— note thatcallerPersonasentries are objects of shape{ type, approach, detectedWhen }, not plain strings.
provider_config is server-derived (recomputed from the resolved stack + supported languages on every write) and is not accepted as an input.
📖 Documentation
Full reference and guides: docs.rymi.live/api/mcp
📄 License
MIT © Rymi
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/rymi-live/rymi-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server