# Speakeasy Platform MCP (MCP server)

> Speakeasy Platform MCP is an MCP server that adds cloud and DevOps tools to AI assistants such as Claude Code, Cursor and VS Code. Secure and manage MCP servers through the Speakeasy AI Control Plane from your agent. It has 275 GitHub stars, is released under the AGPL-3.0 license and runs as a remote server at https://ai.speakeasy.com/platform-mcp.

Securely scale AI usage across your organization. Built for humans and agents. Documentation · Running locally · Tech Stack · Contributing · Login · Roadmap

## Key facts

| Fact | Value |
|---|---|
| Repository | https://github.com/speakeasy-api/gram |
| GitHub stars | 275 |
| License | AGPL-3.0 |
| Language | Go |
| Transport | streamable-http |
| Packages | none (remote only) |
| Remote URL | https://ai.speakeasy.com/platform-mcp |
| Needs API key | no |
| Official | yes |
| Works with | Claude Code, Cursor, VS Code, Claude.ai, ChatGPT |
| Category | Cloud & DevOps |
| Latest release | tunnel@0.2.0 (Oct 22, 2026) |
| Last commit | Oct 26, 2026 |
| MCP registry name | com.speakeasy.ai/platform |

## Install

### Claude Desktop

```
Settings > Connectors > Add custom connector
URL: https://ai.speakeasy.com/platform-mcp
```

Remote servers are added as a custom connector, not in claude_desktop_config.json.

### Claude Code

```sh
claude mcp add --transport http speakeasy-platform-mcp "https://ai.speakeasy.com/platform-mcp"
```

### Cursor (.cursor/mcp.json)

```json
{
  "mcpServers": {
    "speakeasy-platform-mcp": {
      "url": "https://ai.speakeasy.com/platform-mcp"
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "speakeasy-platform-mcp": {
      "type": "http",
      "url": "https://ai.speakeasy.com/platform-mcp"
    }
  }
}
```

Config formats checked against the official docs on 2026-10-07.

## Similar MCP servers

- [Homebutler](https://appsgit.com/mcp-servers/homebutler): Tells an agent what changed on a server since it last looked - status, Docker, backups, Proxmox. (307 stars, MIT)
- [Stata MCP](https://appsgit.com/mcp-servers/stata-mcp): Let LLM help you achieve your regression analysis with Stata. (270 stars, AGPL-3.0)
- [Unifi MCP Server](https://appsgit.com/mcp-servers/unifi-mcp-server): An MCP server that leverages official UniFi API. (309 stars, Apache-2.0, needs API key)
- [MCP Maigret](https://appsgit.com/mcp-servers/mcp-maigret): MCP server that lets AI agents run maigret, an OSINT tool that searches a username across thousands of sites. (268 stars, MIT)
- [Ucsandman MCP Server](https://appsgit.com/mcp-servers/ucsandman-mcp-server): Policy checks, approvals, records, and governed HTTP capabilities for unattended agents. (313 stars, MIT, needs API key)
- [three.ws Alerts](https://appsgit.com/mcp-servers/three-ws-alerts): Create, update, and delete pump.fun alert rules and read fired-alert history across channels. (250 stars, Apache-2.0, needs API key)

---

Canonical page: https://appsgit.com/mcp-servers/speakeasy-platform-mcp
Source: appsgit (https://appsgit.com), the app store for github. Data from the GitHub API, refreshed daily.
Machine access: JSON API https://appsgit.com/api/v1/apps (OpenAPI: https://appsgit.com/openapi.json), MCP server https://mcp.appsgit.com/mcp, full index https://appsgit.com/llms-full.txt.