# PacketStream

The PacketStream MCP server for Claude Code searches the web and retrieves page text as Markdown. The agent calls its search or fetch tool in response to a request.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 1 repo stars
- Author: packetstream
- License: Apache-2.0 · policy=link-only · description only; the file stays with the author
- Source: https://github.com/packetstream/packetstream-mcp
- Updated: 2026-11-04
- Security check: automated, 2026-11-17 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/mcp/packetstream

## What it does

PacketStream gives an agent two tools: live web search and retrieval of a single page. Search results come back as Markdown and JSON; page retrieval returns the page text in Markdown rather than a summary. Requests go through PacketStream’s hosted server.

Page retrieval reads static HTML only. Pages that depend on JavaScript return an error. Each successful call costs $0.0025 and draws from a prepaid balance. Account-based sign-in requires a PacketStream account with funds; API-key access requires a key created in the PacketStream dashboard.

## Requirements
- Remote server: `https://api.packetstream.io/v1/mcp`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http packetstream https://api.packetstream.io/v1/mcp
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add packetstream --url https://api.packetstream.io/v1/mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "packetstream": {
            "url": "https://api.packetstream.io/v1/mcp"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "packetstream": {
            "type": "http",
            "url": "https://api.packetstream.io/v1/mcp"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http packetstream https://api.packetstream.io/v1/mcp
```

## When to use it
- find current web pages on a topic
- return search results as Markdown and JSON
- retrieve static page text in Markdown

## Example prompts
- Search the web for current guides to MCP server setup.
- Find pages on the topic and return the results as Markdown and JSON.
- Fetch this page and give me its text as Markdown.

## Similar
- [Exa Search](https://affpapa.org/en/nevibecode/mcp/exa-search.md) — MCP server · 9181 installs
- [Ghostrouter](https://affpapa.org/en/nevibecode/mcp/ghostrouter.md) — MCP server · 5398 installs
- [Keenable Web Search](https://affpapa.org/en/nevibecode/mcp/keenable-web-search.md) — MCP server · 2498 installs
- [AnySearch](https://affpapa.org/en/nevibecode/mcp/anysearch.md) — MCP server · 841 installs
- [searxNcrawl](https://affpapa.org/en/nevibecode/mcp/searxncrawl.md) — MCP server · ★ 194 repo stars
- [FATSEARCH](https://affpapa.org/en/nevibecode/mcp/fatsearch.md) — MCP server · ★ 164 repo stars

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
