MCP server

Sila runs a hosted Model Context Protocol server. Your agent can scrape pages and run crawls with your workspace credits.

https://api.sila.sh/mcp

The server accepts two kinds of credentials:

OAuth. Add the URL to your client and sign in to Sila when the client asks. Sila shows a consent screen that names the app and where access goes. Click Allow to continue.
API key. Send Authorization: Bearer sila_… with every request. Create a key on the API keys page. See Authentication.

There is no anonymous access. Requests without a valid credential return 401.

Set up your client

Claude Code
Cursor
Codex
VS Code
Other clients

claude mcp add --transport http sila https://api.sila.sh/mcp

Run /mcp inside Claude Code and choose sila to sign in. To use an API key instead:

claude mcp add --transport http sila https://api.sila.sh/mcp \
  --header "Authorization: Bearer sila_your_key"

Add this to ~/.cursor/mcp.json, or to .cursor/mcp.json in a project:

{
  "mcpServers": {
    "sila": {
      "url": "https://api.sila.sh/mcp"
    }
  }
}

Cursor opens the sign-in page the first time you use the server. To use an API key, add a headers field:

{
  "mcpServers": {
    "sila": {
      "url": "https://api.sila.sh/mcp",
      "headers": { "Authorization": "Bearer sila_your_key" }
    }
  }
}

Add this to ~/.codex/config.toml:

[mcp_servers.sila]
url = "https://api.sila.sh/mcp"

Then sign in:

codex mcp login sila

To use an API key instead, store it in an environment variable and point Codex at it:

[mcp_servers.sila]
url = "https://api.sila.sh/mcp"
bearer_token_env_var = "SILA_API_KEY"

Add this to .vscode/mcp.json:

{
  "servers": {
    "sila": {
      "type": "http",
      "url": "https://api.sila.sh/mcp"
    }
  }
}

VS Code starts the sign-in flow when you start the server. To use an API key, add a headers field:

{
  "servers": {
    "sila": {
      "type": "http",
      "url": "https://api.sila.sh/mcp",
      "headers": { "Authorization": "Bearer sila_your_key" }
    }
  }
}

Any client that supports remote (streamable HTTP) MCP servers works. Many accept this shape:

{
  "mcpServers": {
    "sila": {
      "url": "https://api.sila.sh/mcp"
    }
  }
}

Run npx -y @sila-sh/cli@latest init --all --browser to log in and install the Sila skills in one step. See CLI.

Tools

Tool	Input	What it does
`sila_scrape`	`url`, `formats` (default `["markdown"]`), `render` (default `auto`)	Scrapes one page. Returns the markdown, the other formats as JSON, and a screenshot as an image.
`sila_crawl`	`url`, `limit`, `respectRobots` (default `true`), `discovery`	Starts a crawl. Returns the crawl `id` and `status`.
`sila_crawl_status`	`id`	Returns the crawl status and stats.
`sila_crawl_pages`	`id`, `cursor` (default `0`)	Returns one batch of stored pages.
`sila_crawl_cancel`	`id`	Stops a queued or running crawl.
`sila_usage`	none	Returns your credits used and remaining this month.

Inputs match the REST API. See Scrape a page and Create a crawl for the formats, render values, and discovery values. A crawl runs in the background. Call sila_crawl_status until it finishes, then read the pages with sila_crawl_pages. Start at cursor 0 and pass nextCursor back as the next cursor.

Credits

MCP calls use the same credits as the REST API.

Page type	Credits
Fetched statically	1
Needed the headless browser, or any `screenshot` format	5

See Credits and plans.

Errors

A failed tool call returns an error result with the API error code and message, for example credits_exhausted: …. See Errors for every code. The server also returns 429 rate_limited when you send too many requests.

Getting started

AI agents

API reference

Guides

Set up your client

Tools

Credits

Errors

​Sign in

​Set up your client

​Tools

​Credits

​Errors

Sign in

Set up your client

Tools

Credits

Errors