Connect the Context.dev MCP server

Connect your AI agent to Context.dev once, then ask it to scrape, search, extract, parse, enrich, or monitor the web directly from chat.

Hosted MCP URL: https://mcp.context.dev/mcpContext.dev uses OAuth. You sign in through your browser, so you do not need to paste an API key into your MCP configuration.

Connect your client

Choose your client and follow the steps below. Use the exact hosted URL, including /mcp.

Claude, Cowork, and Claude Desktop

Add a custom connector

Open Customize → Connectors, select +, then choose Add custom connector.On Team and Enterprise plans, an organization owner must first add Context.dev from Organization settings → Connectors.

Enter the Context.dev MCP URL

Name the connector Context.dev and enter:

https://mcp.context.dev/mcp

Leave the optional OAuth client ID and client secret fields empty.

Connect your account

Select Add, then Connect. Sign in to Context.dev in the browser window and approve access.

Enable it in a conversation

Select the + button beside the composer, open Connectors, and enable Context.dev.

Claude Code

Add the hosted server for your user:

terminal

claude mcp add --transport http --scope user context https://mcp.context.dev/mcp

Start Claude Code, run /mcp, select context, and complete the browser sign-in.

Open your global MCP configuration at ~/.cursor/mcp.json and add:

~/.cursor/mcp.json

{
  "mcpServers": {
    "context": {
      "url": "https://mcp.context.dev/mcp"
    }
  }
}

Then open Cursor Settings → Tools & MCP:

Find context.
Select Authenticate.
Sign in to Context.dev in the browser window.
Confirm that Cursor shows the server as connected.

Use .cursor/mcp.json instead if you only want Context.dev available in one project.

Add the hosted server:

terminal

codex mcp add context --url https://mcp.context.dev/mcp

Authenticate:

terminal

codex mcp login context

Run codex mcp list to verify the connection. In the Codex CLI, use /mcp to inspect the available Context.dev tools.You can also add the server from Settings → MCP servers in the ChatGPT desktop app or Codex IDE extension. Choose Streamable HTTP, enter the hosted URL, save, restart the client, and select Authenticate.

Open MCP settings

Open the ChatGPT desktop app, go to Settings → MCP servers, and select Add server.

Add Context.dev

Name the server Context.dev, choose Streamable HTTP, and enter:

https://mcp.context.dev/mcp

Restart and authenticate

Save the server, restart the app, and select Authenticate beside Context.dev. Complete the browser sign-in.

Confirm the connection

Enter /mcp in the composer to view the connected server and its tools.

ChatGPT on the web uses workspace plugins for remote MCP tools and does not read the MCP configuration from your computer.

Run MCP: Open User Configuration from the Command Palette, or create .vscode/mcp.json for a project-specific connection:

.vscode/mcp.json

{
  "servers": {
    "context": {
      "type": "http",
      "url": "https://mcp.context.dev/mcp"
    }
  }
}

Start the server from the inline action above its configuration. VS Code opens a browser for OAuth the first time it connects.

Use a remote Streamable HTTP server with OAuth:

mcp.json

{
  "mcpServers": {
    "context": {
      "type": "http",
      "url": "https://mcp.context.dev/mcp"
    }
  }
}

Your client must support remote Streamable HTTP MCP servers and OAuth. When prompted, sign in to Context.dev and approve access.

Verify the connection

Start a new conversation and ask:

Use Context.dev to retrieve the live brand profile for stripe.com. Tell me which Context.dev tool you called.

A working connection calls get-brand or brand-retrieve-unified and returns live data. If the agent answers from memory without making a tool call, confirm that Context.dev is enabled for the conversation.

What your agent can do

The MCP server exposes the callable operations in the public Context.dev API, plus a visual brand card.

Capability	Tools
Parse files	`parse-document`
Scrape pages and sites	`web-scrape-html`, `web-scrape-markdown`, `web-scrape-images`, `web-scrape-sitemap`, `web-crawl`, `web-screenshot`
Search and extract	`web-search`, `web-extract`
Brand intelligence	`get-brand`, `brand-retrieve-unified`, `web-styleguide`, `web-fonts`
Products and classification	`brand-ai-product`, `brand-ai-products`, `web-naics`, `web-sic`
Cache warming	`utility-prefetch`
Monitor management	`list-monitors`, `create-monitor`, `get-monitor`, `update-monitor`, `delete-monitor`
Monitor runs	`run-monitor-now`, `list-monitor-runs`, `get-monitor-run`, `list-account-runs`
Monitor changes and usage	`list-monitor-changes`, `list-changes`, `get-change`, `list-monitor-credit-usage`, `rotate-monitor-webhook-secret`

Prompts to try

Research a website

Scrape the Acme pricing page and summarize every plan, limit, and billing interval.

Extract structured data

Extract all open engineering roles from this careers site as JSON with title, location, and application URL.

Parse a document

Parse this PDF and return its tables as clean Markdown, preserving the section hierarchy.

Monitor a change

Create a daily monitor for this changelog and notify me only about new product releases.

Authentication and permissions

Context.dev uses OAuth 2.0 Authorization Code flow with PKCE. The MCP client receives scoped tokens; it never receives your Context.dev password or API key. The server requests:

api.read for parsing, scraping, searching, extraction, enrichment, and reading monitor data
api.write for creating, updating, deleting, or manually running monitors and rotating webhook secrets

Monitor tools can change persistent account state. Keep tool approvals enabled and review calls to create-monitor, update-monitor, delete-monitor, run-monitor-now, and rotate-monitor-webhook-secret.

MCP calls use your Context.dev account and consume the same credits as the corresponding API operations. See pricing and monitor credit usage.

Troubleshooting

The server does not appear or shows zero tools

Confirm that the URL is exactly https://mcp.context.dev/mcp, including /mcp. Restart or refresh the client after editing its configuration, then make sure Context.dev is enabled for the current conversation.

Authentication loops or returns 401

Clear the saved authentication for Context.dev in your client, reconnect, and complete the browser flow again. Do not add an API key or OAuth secret to the URL.

The agent answers without calling Context.dev

Enable Context.dev for the conversation and name it explicitly in the prompt. In clients with tool controls, confirm that the relevant Context.dev tools are enabled.

Check whether the hosted server is online

Run:

terminal

curl -fsS https://mcp.context.dev/health

A healthy server returns a JSON response with a healthy status. If it is healthy but your client cannot connect, inspect the client’s MCP output log and reconnect.

Next steps

Browse the API

See the endpoints and data available through the MCP tools.

Monitor websites

Learn how monitor targets, schedules, changes, and webhooks work.

Install the skill

Teach your agent when and how to use Context.dev while writing code.

View the source

Inspect the open-source MCP server implementation.

Get Started

Give it to your Agent

What can Context.dev do

Optimizations

No-code Integrations

Connect the Context.dev MCP server

Connect your client

Claude, Cowork, and Claude Desktop

Claude Code

Verify the connection

What your agent can do

Prompts to try

Research a website

Extract structured data

Parse a document

Monitor a change

Authentication and permissions

Troubleshooting

Next steps

Browse the API

Monitor websites

Install the skill

View the source

​Connect your client

​Claude, Cowork, and Claude Desktop

​Claude Code

​Verify the connection

​What your agent can do

​Prompts to try

Research a website

Extract structured data

Parse a document

Monitor a change

​Authentication and permissions

​Troubleshooting

​Next steps

Browse the API

Monitor websites

Install the skill

View the source

Connect your client

Claude, Cowork, and Claude Desktop

Claude Code

Verify the connection

What your agent can do

Prompts to try

Authentication and permissions

Troubleshooting

Next steps