# Flowra MCP server

> Discover and run tools across 1,000+ connected apps, with approval gates and a run ledger for AI agents and workflows.

- Listing: https://mcp.tc/i/flowra
- Connect: use the server's own URL `https://mcp.flowra.dev/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: [Automation & Integrations](https://mcp.tc/c/automation)
- Vendor: Flowra
- Homepage: <https://flowra.dev/>

## About

Flowra is a hosted platform for building AI agents and workflows from a one-sentence description. The MCP server gives assistants access to Flowra's app integrations and custom tools, with approval gates for risky steps and a ledger of each run.

It runs as a hosted streamable HTTP endpoint at https://mcp.flowra.dev/mcp. Users sign in to Flowra in the browser on first use, and app accounts are connected through OAuth. No API key header is needed in the client configuration.

## What it can do

- Discover tools across connected app integrations
- Connect app accounts through OAuth
- Run tools from connected apps
- Use custom tools hosted by Flowra
- Gate risky steps behind human approval
- Review runs in a ledger of inputs, outputs and credits

## Example prompts

- "Find a Flowra tool that posts a message to Slack"
- "Connect my GitHub account in Flowra and triage new issues"
- "Create a workflow that sends a weekly competitor brief"
- "Run my Flowra agent and show the run ledger"

## Install

### Claude Code

1. Run this in a terminal, in your project folder:

```bash
claude mcp add --transport http flowra https://mcp.flowra.dev/mcp
```

2. Start Claude Code, type `/mcp`, pick **flowra** and choose **Authenticate**. A browser window opens for the Flowra sign-in.

Add `--scope user` to make it available in every project, not just this one.

### Claude Desktop

1. Open **Customize → Connectors**, click **+ Add**, then **Add custom connector**.

2. Name it **Flowra** and paste this URL:

```url
https://mcp.flowra.dev/mcp
```

3. Click **Add**, then **Connect**, and sign in when Flowra 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](<https://claude.ai/customize/connectors?modal=add-custom-connector&connectorName=Flowra&connectorUrl=https%3A%2F%2Fmcp.flowra.dev%2Fmcp>) (opens connector settings)

2. Check that the URL reads `https://mcp.flowra.dev/mcp` and click **Add**.

3. Click **Connect** and sign in when Flowra 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, go to **Plugins**, select **+**, then **Add custom MCP server**.

2. Enter a name for the server.

3. Under **Connection**, paste `https://mcp.flowra.dev/mcp` as the server URL, then for authentication choose **OAuth**. ChatGPT sends you to Flowra to sign in.

4. Check **I understand and want to continue**, then select **Create as a plugin**.

Whether you can add a custom MCP server depends on your ChatGPT plan and your workspace permissions (in Business workspaces, admins and owners can).

### Cursor

[Add to Cursor](<https://cursor.com/install-mcp?name=flowra&config=eyJ1cmwiOiJodHRwczovL21jcC5mbG93cmEuZGV2L21jcCJ9>) (opens Cursor)

Or add it by hand to `~/.cursor/mcp.json` (all projects) or `.cursor/mcp.json` (this project):

`mcp.json`:

```json
{
  "mcpServers": {
    "flowra": {
      "url": "https://mcp.flowra.dev/mcp"
    }
  }
}
```

Cursor shows **Needs authentication** next to the server. Click the button beside it to sign in.

### VS Code

[Install in VS Code](<https://vscode.dev/redirect/mcp/install?name=flowra&config=%7B%22type%22%3A%22http%22%2C%22url%22%3A%22https%3A%2F%2Fmcp.flowra.dev%2Fmcp%22%7D>) (opens VS Code)

Or from a terminal:

```bash
code --add-mcp '{"name":"flowra","type":"http","url":"https://mcp.flowra.dev/mcp"}'
```

Or commit it to the repo in `.vscode/mcp.json`:

`.vscode/mcp.json`:

```json
{
  "servers": {
    "flowra": {
      "type": "http",
      "url": "https://mcp.flowra.dev/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": {
    "flowra": {
      "serverUrl": "https://mcp.flowra.dev/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 flowra --url https://mcp.flowra.dev/mcp
codex mcp login flowra
```

Or edit `~/.codex/config.toml` directly:

`config.toml`:

```toml
[mcp_servers.flowra]
url = "https://mcp.flowra.dev/mcp"
```

### Gemini CLI

```bash
gemini mcp add --transport http flowra https://mcp.flowra.dev/mcp
```

Then, inside Gemini CLI, run `/mcp auth flowra` 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": {
    "flowra": {
      "type": "http",
      "url": "https://mcp.flowra.dev/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://mcp.flowra.dev/mcp`.

## Details

- Last checked: 2026-11-17 (reachable, asks for credentials)
- Listed: 2026-10-27
- Updated: 2026-10-27

---
Source: https://mcp.tc/i/flowra (mcp.tc is an independent directory, not affiliated with this server's publisher). Corrections: https://mcp.tc/report
