Productivity · Remote MCP server
Ray notifications
Send email, push, Slack, Discord, Telegram and webhook notifications and manage templates with Ray.
What the MCP Registry states
The entry as published to the official MCP Registry (read 2026-10-04), latest version.
- Registry name
io.github.gege-mn/ray-mcp- Version
- 0.1.0
- Status
- Active
- Category
- productivity
- Transport
- Streamable HTTP, stdio (local process)
- Package
- npm
- Published
- 2026-09-14
- Updated
- 2026-09-14
- Publisher
- gege-mn (GitHub)
- Website
- ray.gege.mn/docs
- Repository
- github.com/gege-mn/ray-mcp
- Source
- Registry API entry
Remote endpoints
| Transport | URL | Headers declared |
|---|---|---|
| Streamable HTTP | https://ray-api.gege.mn/mcp | Authorization (required, secret) |
Packages
| Registry | Package | Version | Transport |
|---|---|---|---|
| npmruntime: npx | @gege-mn/ray-mcp | 0.1.0 | stdio |
How to connect Ray notifications
Ray notifications is a remote MCP server: there is nothing to install. Its endpoint is https://ray-api.gege.mn/mcp, served over Streamable HTTP. In an assistant that accepts remote MCP servers (often under a setting named connectors, integrations or tools), add a new server and give it this URL; in a client configured by file, add it as a remote (HTTP) server with the same URL.
The registry entry declares an HTTP header for the connection: Authorization (required, secret). A secret header usually carries an API key or token issued by the service; clients that accept custom headers set it with the server's URL.
It can also run locally from a Node.js package published to the npm registry: @gege-mn/ray-mcp version 0.1.0. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Node.js; clients usually start it with npx — the usual command is npx -y @gege-mn/ray-mcp@0.1.0. It reads these environment variables: RAY_API_KEY (required, secret) and RAY_MCP_URL; set them in the client's configuration for this server.
In the mcpServers JSON format that many desktop and editor MCP clients read, the entry looks like this (placeholders in angle brackets):
{
"mcpServers": {
"ray-mcp": {
"command": "npx",
"args": [
"-y",
"@gege-mn/ray-mcp@0.1.0"
],
"env": {
"RAY_API_KEY": "<secret>",
"RAY_MCP_URL": "<value>"
}
}
}
}Derived from the registry entry, not tested here. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect
More productivity servers
| Server | Runs |
|---|---|
| RallyTools for Go-to-market teams creating sales materials, product demos, and deal rooms for customers. | Remote · HTTP |
| Ramp KitLATAM fiat ramps on Stellar for AI agents: live quotes, sandbox orders, PIX/SPEI simulation, docs. | Local · stdio |
| RapportscoreConversational AI Coaching from calls; permissioned Team Dynamics reports in a limited U.S. pilot. | Remote · HTTP |
| Ratatosk MCPCNCF release intelligence: typed changes from release notes; check_stack compares versions locally. | Local · stdio |
| Raza SORRaza Rizwan's record: ask how much of your workflow AI can automate; governed, cited answers. | Remote · HTTP |
| Razi Document ToolsDocument processing over MCP: merge, split and compress PDFs, run OCR, extract document text. | Remote · HTTP |
| Razi Text GenerationText generation over MCP: prose, emails, blog outlines, SQL, humanizing, text diffs, fake data. | Remote · HTTP |
| RCLLSelf-hosted shared memory for a team of AI agents. Rooms, L0-L3 depth, no LLM on the read path. | Local · stdio |