Establishes a TCP connection to a running Debug Adapter Protocol (DAP) server.
AI agents invoke connect_dap to trigger actions in Debugging 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.
Connecting to a DAP server initiates an active debugging session over a network connection, which triggers external operations and enables control of a running process. This goes beyond read/write into executing/controlling an external system. Misuse could allow an agent to attach to arbitrary processes or services on the network, with significant blast radius.
From the tool's definition Establishes a TCP connection to a running Debug Adapter Protocol (DAP) server
Attacks that exploit this kind of access
Establishes a TCP connection to a running Debug Adapter Protocol (DAP) server. It is categorised as a Execute tool in the Debugging MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Debugging MCP Server MCP server in PolicyLayer and add a rule for connect_dap: 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 Debugging MCP Server. Nothing to install.
connect_dap 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 connect_dap 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 connect_dap. 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.
connect_dap is provided by the Debugging MCP Server MCP server (luischang07/debugging-mcp). 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 →