Connect to a Chromium instance (discovers running instance or launches one)
AI agents invoke cdp_connect to trigger actions in CDP-MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool either attaches to an existing browser process or spawns a new one. Launching or attaching to a browser process is an external operation with significant blast radius — once connected, an AI agent gains access to the full CDP surface (arbitrary JS execution, network interception, DOM manipulation, credential access, etc.).
From the tool's definition Connect to a Chromium instance (discovers running instance or launches one)
Attacks that exploit this kind of access
Connect to a Chromium instance (discovers running instance or launches one). It is categorised as a Execute tool in the CDP-MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the CDP-MCP Server MCP server in PolicyLayer and add a rule for cdp_connect: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches CDP-MCP Server. Nothing to install.
cdp_connect is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the cdp_connect rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for cdp_connect. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
cdp_connect is provided by the CDP-MCP Server MCP server (jekyll-001/cdp-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →