Manually triggers a reconnection attempt to the Node.js debugger
AI agents invoke retry_connect to trigger actions in MCP NodeJS Debugger. 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 actively triggers an external operation (reconnection to the Node.js debugger process), which constitutes executing an action rather than merely reading data or writing state. Misuse could disrupt an active debugging session or cause repeated connection attempts, but blast radius is moderate since it only affects the debug connection.
From the tool's definition Manually triggers a reconnection attempt to the Node.js debugger
Documented attack patterns abuse exactly the kind of access retry_connect gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP NodeJS Debugger, and nothing reaches the server without passing your rules. This is the rule we recommend for retry_connect:
{
"version": "1",
"default": "deny",
"tools": {
"retry_connect": {
"limits": [
{
"counter": "retry_connect_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}retry_connect stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Manually triggers a reconnection attempt to the Node.js debugger. It is categorised as a Execute tool in the MCP NodeJS Debugger MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCP NodeJS Debugger MCP server in PolicyLayer and add a rule for retry_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 MCP NodeJS Debugger. Nothing to install.
retry_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 retry_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 retry_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.
retry_connect is provided by the MCP NodeJS Debugger MCP server (workbackai/mcp-nodejs-debugger). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 13 MCP NodeJS Debugger tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
13 MCP NodeJS Debugger tools catalogued and risk-classified — across an index of 42,500+ MCP servers.