create_task_bank
Create or add to a fixed task bank for controlled agent evaluation. Each task defines: initial state (repo snapshot, config), success criteria (deterministic checks), forbidden behaviors, category (bugfix/refactor/integration/UI), and difficulty. The task bank is the foundation for ablation exper...
This record as markdown: /tools/io-github-homenshum-nodebench/create-task-bank.md
What create_task_bank does on Nodebench
AI agents use create_task_bank to create or update resources in Nodebench, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Nodebench environment.
Why create_task_bank is rated Medium
This tool creates or modifies task definitions and metadata (initial state, success criteria, forbidden behaviors, category, difficulty) in a task bank repository. These are reversible write operations - tasks can be edited or removed. The severity is medium because misuse could corrupt evaluation datasets or introduce biased tasks that affect agent benchmarking, but does not delete data irreversibly or execute code.
From the tool's definition Tool description explicitly states 'Create or add to a fixed task bank' - the verbs 'create' and 'add' indicate data creation/modification operations. The tool modifies a persistent task bank used for evaluation experiments.
Attacks that exploit this kind of access
The rule that runs create_task_bank 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 create_task_bank, this is the rule to start with:
create_task_bank stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Nodebench, apply this rule, and every create_task_bank call is checked against it from then on.
Questions about create_task_bank
Create or add to a fixed task bank for controlled agent evaluation. Each task defines: initial state (repo snapshot, config), success criteria (deterministic checks), forbidden behaviors, category (bugfix/refactor/integration/UI), and difficulty. The task bank is the foundation for ablation experiments comparing bare vs NodeBench-augmented agents. Based on Anthropic. It is categorised as a Write tool in the Nodebench MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Nodebench MCP server in PolicyLayer and add a rule for create_task_bank: 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.
create_task_bank is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the create_task_bank 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 create_task_bank. 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.
create_task_bank 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.
More on Nodebench, and thousands of servers like it.
This server
Across the catalogue