# SpecStream MCP server

> Search, extract, enrich and monitor structured data from the live web for agents and teams.

- Listing: https://mcp.tc/i/specstream
- Connect: use the server's own URL `https://api.specstream.ai/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: [Search & Web Data](https://mcp.tc/c/search-web)
- Vendor: SpecStream
- Homepage: <https://specstream.ai/>

## About

SpecStream is a live web data platform. Through its MCP endpoint an assistant can search the web, extract text from pages and documents, build structured datasets from plain-language requests, enrich lists, and monitor data for changes.

It runs as a hosted streamable HTTP endpoint at https://api.specstream.ai/mcp. Users sign in from their MCP client, for example by running /mcp in Claude Code after adding the server. OAuth scopes cover specs, finds, projects and account data, including a spend scope.

## What it can do

- Search the live web and get answers in structured form
- Extract main text from up to 20 URLs, including PDF, Word and Excel
- Build structured datasets from plain-language requests
- Enrich lists with missing details
- Monitor saved requests for changes on a schedule

## Example prompts

- "Search the web for recent funding rounds of European robotics startups."
- "Extract the main text from these five URLs."
- "Build a list of dental clinics in Austin with phone numbers and websites."
- "Monitor this pricing page and tell me when values change."

## Install

### Claude Code

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

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

2. Start Claude Code, type `/mcp`, pick **specstream** and choose **Authenticate**. A browser window opens for the SpecStream 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 **SpecStream** and paste this URL:

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

3. Click **Add**, then **Connect**, and sign in when SpecStream 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=SpecStream&connectorUrl=https%3A%2F%2Fapi.specstream.ai%2Fmcp>) (opens connector settings)

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

3. Click **Connect** and sign in when SpecStream 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://api.specstream.ai/mcp` as the server URL, then for authentication choose **OAuth**. ChatGPT sends you to SpecStream 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=specstream&config=eyJ1cmwiOiJodHRwczovL2FwaS5zcGVjc3RyZWFtLmFpL21jcCJ9>) (opens Cursor)

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

`mcp.json`:

```json
{
  "mcpServers": {
    "specstream": {
      "url": "https://api.specstream.ai/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=specstream&config=%7B%22type%22%3A%22http%22%2C%22url%22%3A%22https%3A%2F%2Fapi.specstream.ai%2Fmcp%22%7D>) (opens VS Code)

Or from a terminal:

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

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

`.vscode/mcp.json`:

```json
{
  "servers": {
    "specstream": {
      "type": "http",
      "url": "https://api.specstream.ai/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": {
    "specstream": {
      "serverUrl": "https://api.specstream.ai/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 specstream --url https://api.specstream.ai/mcp
codex mcp login specstream
```

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

`config.toml`:

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

### Gemini CLI

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

Then, inside Gemini CLI, run `/mcp auth specstream` 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": {
    "specstream": {
      "type": "http",
      "url": "https://api.specstream.ai/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://api.specstream.ai/mcp`.

## Details

- Last checked: 2026-11-18 (reachable, asks for credentials)
- Listed: 2026-11-12
- Updated: 2026-11-12

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