# Cloudflare AI Gateway MCP server
> Search AI Gateway logs and inspect prompts, responses and gateway usage in your Cloudflare account.
- Listing: https://mcp.tc/i/cloudflare-ai-gateway
- Connect: use the server's own URL `https://ai-gateway.mcp.cloudflare.com/mcp` (OAuth sign-in at the server); clients connect to it directly. The listing link is a page, not an MCP endpoint.
- Type: remote (Streamable HTTP)
- Auth: OAuth sign-in
- Category: [AI & Machine Learning](https://mcp.tc/c/ai-ml)
- Vendor: Cloudflare
- Verified: yes, mcp.tc checked that this is the official server (https://mcp.tc/verify). It says who runs the server, not that it is safe.
- Homepage:
- Repository:
## About
Connects to the Cloudflare AI Gateway API so an assistant can list the gateways in an account, search their logs with filters, and read the request and response bodies of individual log entries. It is useful for debugging failed or unexpected model calls.
The server is hosted by Cloudflare at https://ai-gateway.mcp.cloudflare.com/mcp and uses streamable HTTP. Users sign in through the Cloudflare OAuth flow in the browser. Tools are scoped to an account; if your credentials reach several accounts, pass account\_id or set a cf-account-id header.
## What it can do
- List AI Gateways in a Cloudflare account
- Filter gateway logs by date, model, provider, status and feedback
- Fetch details for a specific log entry
- Read the request body of a logged call
- Read the response body of a logged call
## Example prompts
- "List all my AI Gateways."
- "Show logs for gateway 'gateway-001' between January 1 and January 31, 2023."
- "Fetch the latest errors from gateway-001 and work out what went wrong."
- "Show the request and response body for this log ID."
## Install
### Claude Code
1. Run this in a terminal, in your project folder:
```bash
claude mcp add --transport http cloudflare-ai-gateway https://ai-gateway.mcp.cloudflare.com/mcp
```
2. Start Claude Code, type `/mcp`, pick **cloudflare-ai-gateway** and choose **Authenticate**. A browser window opens for the Cloudflare sign-in.
Add `--scope user` to make it available in every project, not just this one.
### Claude Desktop
1. Open **Settings → Connectors** and click **Add custom connector**.
2. Name it **Cloudflare AI Gateway** and paste this URL:
```url
https://ai-gateway.mcp.cloudflare.com/mcp
```
3. Click **Add**, then **Connect**, and sign in when Cloudflare asks.
Claude Desktop’s JSON config file only starts local servers. Remote servers go through Connectors, and connectors you add on claude.ai show up here too.
### claude.ai
1. Open the connector form on claude.ai. This button fills in the name and URL for you:
[Add to claude.ai]() (opens connector settings)
2. Check that the URL reads `https://ai-gateway.mcp.cloudflare.com/mcp` and click **Add**.
3. Click **Connect** and sign in when Cloudflare asks.
Free plans allow one custom connector. On Team and Enterprise plans an owner adds it under **Organization settings → Connectors**.
### ChatGPT
1. On chatgpt.com, open **Settings → Security and login** and turn on **Developer mode**.
2. Go to `chatgpt.com/plugins` and click **+** to create an app for a remote MCP server.
3. Paste `https://ai-gateway.mcp.cloudflare.com/mcp` as the server URL and choose **OAuth**. ChatGPT sends you to Cloudflare to sign in.
Developer mode is available on the web for Plus, Pro, Business, Enterprise and Education accounts.
### Cursor
[Add to Cursor]() (opens Cursor)
Or add it by hand to `~/.cursor/mcp.json` (all projects) or `.cursor/mcp.json` (this project):
`mcp.json`:
```json
{
"mcpServers": {
"cloudflare-ai-gateway": {
"url": "https://ai-gateway.mcp.cloudflare.com/mcp"
}
}
}
```
Cursor shows **Needs login** next to the server. Click it to sign in.
### VS Code
[Install in VS Code]() (opens VS Code)
Or from a terminal:
```bash
code --add-mcp '{"name":"cloudflare-ai-gateway","type":"http","url":"https://ai-gateway.mcp.cloudflare.com/mcp"}'
```
Or commit it to the repo in `.vscode/mcp.json`:
`.vscode/mcp.json`:
```json
{
"servers": {
"cloudflare-ai-gateway": {
"type": "http",
"url": "https://ai-gateway.mcp.cloudflare.com/mcp"
}
}
}
```
VS Code asks you to sign in the first time the server starts.
### Devin Desktop
1. Add it to `~/.config/devin/mcp_config.json` (macOS and Linux) or `%APPDATA%\devin\mcp_config.json` (Windows):
`mcp_config.json`:
```json
{
"mcpServers": {
"cloudflare-ai-gateway": {
"serverUrl": "https://ai-gateway.mcp.cloudflare.com/mcp"
}
}
}
```
2. Refresh the MCP server list in Cascade and sign in when asked.
Devin Desktop is the new name for Windsurf. It reads `serverUrl` (or `url`) for remote servers.
### Codex
```bash
codex mcp add cloudflare-ai-gateway --url https://ai-gateway.mcp.cloudflare.com/mcp
codex mcp login cloudflare-ai-gateway
```
Or edit `~/.codex/config.toml` directly:
`config.toml`:
```toml
[mcp_servers.cloudflare-ai-gateway]
url = "https://ai-gateway.mcp.cloudflare.com/mcp"
```
### Gemini CLI
```bash
gemini mcp add --transport http cloudflare-ai-gateway https://ai-gateway.mcp.cloudflare.com/mcp
```
Then, inside Gemini CLI, run `/mcp auth cloudflare-ai-gateway` to sign in.
This adds it to the current project. Add `-s user` to use it everywhere.
### Any client
Most clients accept this shape. Some name the URL field differently: `serverUrl` in Devin Desktop, `httpUrl` in Gemini CLI’s settings file.
```json
{
"mcpServers": {
"cloudflare-ai-gateway": {
"type": "http",
"url": "https://ai-gateway.mcp.cloudflare.com/mcp"
}
}
}
```
Zed puts servers under `context_servers` in its settings. Cline needs `"type": "streamableHttp"`, or it assumes SSE.
Client only starts local servers? Bridge it with `npx -y mcp-remote https://ai-gateway.mcp.cloudflare.com/mcp`.
## Details
- Last checked: 2026-10-03 (reachable, asks for credentials)
- Listed: 2026-10-03
- Updated: 2026-10-03
---
Source: https://mcp.tc/i/cloudflare-ai-gateway (mcp.tc is an independent directory, not affiliated with this server's publisher). Corrections: https://mcp.tc/report