remove_ai_signatures
Detect and remove AI-generated writing signatures from academic text. First runs pattern matching for known AI vocabulary (leverage, delve, tapestry, mechanical connectors), then uses LLM to rewrite flagged sections naturally. Returns cleaned text and a list of AI patterns found.
This record as markdown: /tools/io-github-homenshum-nodebench/remove-ai-signatures.md
What remove_ai_signatures does on Nodebench
AI agents use remove_ai_signatures 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 remove_ai_signatures is rated Medium
The tool modifies text by detecting and rewriting sections, which is a reversible write/transform operation. It rewrites academic text in-place, which could alter meaning or academic integrity, but it does not irreversibly destroy data and the original can be retained. The academic context raises the severity to medium due to potential misuse for academic dishonesty.
From the tool's definition Detect and remove AI-generated writing signatures... rewrite flagged sections naturally. Returns cleaned text
Attacks that exploit this kind of access
The rule that runs remove_ai_signatures 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 remove_ai_signatures, this is the rule to start with:
remove_ai_signatures 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 remove_ai_signatures call is checked against it from then on.
Questions about remove_ai_signatures
Detect and remove AI-generated writing signatures from academic text. First runs pattern matching for known AI vocabulary (leverage, delve, tapestry, mechanical connectors), then uses LLM to rewrite flagged sections naturally. Returns cleaned text and a list of AI patterns found. 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 remove_ai_signatures: 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.
remove_ai_signatures 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 remove_ai_signatures 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 remove_ai_signatures. 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.
remove_ai_signatures 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