Skip to main content
The official Context.dev plugin gives OpenClaw native web search and scraping, plus dedicated context_search and context_scrape tools. An optional OAuth MCP connection adds crawling, extraction, document parsing, brand intelligence, screenshots, monitors, and batches.

Install Context.dev from ClawHub

Review the current package, compatibility, and source before installing.

Choose an access level

You can use either path or enable both.

Install the plugin

1

Install from ClawHub

2

Configure the API key

Create a secret key in the Context.dev dashboard, then set it as CONTEXT_API_KEY in the environment that starts the OpenClaw Gateway.For a Gateway started from the same shell:
If OpenClaw runs as a background service, container, or process manager, set the variable in that service’s environment and restart it there. A shell-only export will not update an already-running Gateway.
3

Test native search and scraping

Send the agent a read-only request:
For a known page, ask it to use context_scrape instead.

Connect the full MCP catalog

The plugin’s native tools cover search and single-page scraping. Add the hosted MCP server when the agent also needs extraction, parsing, brand data, monitors, screenshots, or batches.
Complete the Context.dev authorization flow in the browser. No API key is required for this MCP connection. Verify the connection and list its tools:

Use the integration

Creating, updating, running, or deleting monitors and batches changes persistent account state. Ask for those operations explicitly and review the proposed action before it runs.

Troubleshooting

Reference

Plugin source

README, package metadata, manifest, and release source.

OpenClaw documentation

Gateway, plugins, environment, and MCP configuration.

Context.dev MCP guide

Hosted MCP capabilities and OAuth behavior.

Context.dev dashboard

Create an API key and review usage.