# Servana MCP server

> Find local service businesses in US cities, estimate prices and send quote requests to cleaners, trainers, photographers and more.

- Listing: https://mcp.tc/i/servana
- Connect: use the server's own URL `https://servana.ai/api/mcp` (no sign-in); clients connect to it directly. The listing link is a page, not an MCP endpoint.
- Type: remote (Streamable HTTP)
- Auth: none
- Category: [E-commerce](https://mcp.tc/c/ecommerce)
- Vendor: Servana
- Homepage: <https://servana.ai/>

## About

Servana is a US directory of local service businesses: cleaning, laundry, med spa, yoga, personal training, photography and home services. Coverage is strongest in New York City. The server lets an assistant map a request to a category, search businesses by city, read a business profile, get a rough price range, and send quote requests whose replies are emailed to the user.

It runs as a hosted streamable HTTP endpoint at https://servana.ai/api/mcp. No sign-in or API key is needed. Servana does not take payments or confirm bookings; businesses reply to the user directly.

## What it can do

- Map a service request to a Servana category
- Search local businesses by city and service
- View a business profile, rating and pricing
- Get a non-binding price estimate for a service
- Send quote requests to up to 3 businesses at once
- Check whether businesses replied to an enquiry

## Tools (8)

- `search_services`: Map a described local service to a Servana category slug. (read-only)
- `search_vendors`: Find local businesses for a service in a US city. (read-only)
- `get_vendor`: Get one business's services, prices, rating and claim status. (read-only)
- `estimate_service_request`: Get a rough, non-binding price range for a service in a city. (read-only)
- `send_message_to_vendor`: Send an approved enquiry to one or up to three businesses. (can modify or delete data)
- `check_enquiry_replies`: Check replies to enquiries sent earlier in the conversation. (read-only)
- `prepare_quote_request`: Show a pre-filled quote request form for 1 to 3 businesses; sends nothing. (read-only)
- `request_quote`: Send an approved structured quote request to 1 to 3 businesses. (can modify or delete data)

## Example prompts

- "Find house cleaners in Brooklyn, New York"
- "How much does a deep clean cost in Chicago?"
- "Ask three photographers in Miami about availability next Saturday"
- "Did any of the businesses I contacted reply yet?"

## Install

### Claude Code

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

```bash
claude mcp add --transport http servana https://servana.ai/api/mcp
```

2. Start Claude Code and type `/mcp`. **servana** should show as connected.

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 **Servana** and paste this URL:

```url
https://servana.ai/api/mcp
```

3. Click **Add**. Its tools appear in the chat’s tools menu.

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=Servana&connectorUrl=https%3A%2F%2Fservana.ai%2Fapi%2Fmcp>) (opens connector settings)

2. Check that the URL reads `https://servana.ai/api/mcp` and click **Add**.

3. Turn it on in a chat from the tools menu.

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://servana.ai/api/mcp` as the server URL, then for authentication choose **No authentication**.

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=servana&config=eyJ1cmwiOiJodHRwczovL3NlcnZhbmEuYWkvYXBpL21jcCJ9>) (opens Cursor)

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

`mcp.json`:

```json
{
  "mcpServers": {
    "servana": {
      "url": "https://servana.ai/api/mcp"
    }
  }
}
```

### VS Code

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

Or from a terminal:

```bash
code --add-mcp '{"name":"servana","type":"http","url":"https://servana.ai/api/mcp"}'
```

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

`.vscode/mcp.json`:

```json
{
  "servers": {
    "servana": {
      "type": "http",
      "url": "https://servana.ai/api/mcp"
    }
  }
}
```

### 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": {
    "servana": {
      "serverUrl": "https://servana.ai/api/mcp"
    }
  }
}
```

2. Refresh the MCP server list in Cascade.

Devin Desktop is the new name for Windsurf. It reads `serverUrl` (or `url`) for remote servers.

### Codex

```bash
codex mcp add servana --url https://servana.ai/api/mcp
```

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

`config.toml`:

```toml
[mcp_servers.servana]
url = "https://servana.ai/api/mcp"
```

### Gemini CLI

```bash
gemini mcp add --transport http servana https://servana.ai/api/mcp
```

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": {
    "servana": {
      "type": "http",
      "url": "https://servana.ai/api/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://servana.ai/api/mcp`.

## Recent changes

- 2026-11-13 05:26 UTC: Tracking started: 8 tools read. Source: automatic check.

More on the History tab, with descriptions before and after for the newest entries: https://mcp.tc/i/servana#history (Atom feed: https://mcp.tc/i/servana/history.xml). It records what mcp.tc's anonymous checks saw, every 3 hours where the tool list can be read without sign-in; it is not a security review.

## Details

- Server version: 1.0.0
- MCP protocol version: 2025-06-18
- Last checked: 2026-11-18 (reachable)
- Listed: 2026-11-13
- Updated: 2026-11-13

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