nb_start_agent

Start a new agent conversation with an optional initial message.

SERVERNodebench SOURCEnodebench-mcp

High RISK CLASS

Category Execute

Parameters 00 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/io-github-homenshum-nodebench/nb-start-agent.md

WHAT IT DOES

What nb_start_agent does on Nodebench

AI agents invoke nb_start_agent to trigger actions in Nodebench. 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.

RISK

Why nb_start_agent is rated High

Starting an agent is an Execute action because it triggers an external computational process whose side effects are not predetermined and depend on arguments (the initial message). While not as severe as running arbitrary shell commands, it initiates autonomous decision-making that could perform reads, writes, or other operations.

From the tool's definition Tool name 'nb_start_agent' and description 'Start a new agent conversation with an optional initial message' indicates launching an autonomous agent process.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs nb_start_agent safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Nodebench, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For nb_start_agent, this is the rule to start with:

nb_start_agent Rate-limited

nb_start_agent 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "nb_start_agent": {
      "limits": [
        {
          "counter": "nb_start_agent_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Nodebench, apply this rule, and every nb_start_agent call is checked against it from then on.

FAQ

Questions about nb_start_agent

What does the nb_start_agent tool do? +

Start a new agent conversation with an optional initial message. It is categorised as a Execute tool in the Nodebench MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on nb_start_agent? +

Register the Nodebench MCP server in PolicyLayer and add a rule for nb_start_agent: 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 Nodebench. Nothing to install.

What risk level is nb_start_agent? +

nb_start_agent is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit nb_start_agent? +

Yes. Add a rate_limit block to the nb_start_agent 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.

How do I block nb_start_agent completely? +

Set action: deny in the PolicyLayer policy for nb_start_agent. 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.

What MCP server provides nb_start_agent? +

nb_start_agent is provided by the Nodebench MCP server (nodebench-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Nodebench, and thousands of servers like it.

This server

All 824 Nodebench tools → High-risk tools on this server →

Across the catalogue

start_devtools_monitoring on Percepta MCP Server →team_manager_start_room on Team Manager MCP →start_etw_trace on Procmon → All high-risk MCP tools → The MCP Attack Database →

Guides

Govern code and CI agents →Agent sandbox →Least privilege for MCP →