Redact sensitive information from provided text.
AI agents use redact to create or update resources in Pangea MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Pangea MCP Server environment.
The tool modifies input text by removing or masking sensitive information and returns the modified version. This is a reversible transformation (the original text can be preserved elsewhere), making it a Write operation rather than Destructive. Misuse could result in over-redaction of important data or under-redaction of sensitive data, but it does not delete stored records or execute code.
From the tool's definition "Redact sensitive information from provided text"
Attacks that exploit this kind of access
Redact sensitive information from provided text. It is categorised as a Write tool in the Pangea MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Pangea MCP Server MCP server in PolicyLayer and add a rule for redact: 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 Pangea MCP Server. Nothing to install.
redact 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 redact 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 redact. 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.
redact is provided by the Pangea MCP Server MCP server (pangeacyber/pangea-mcp-server). 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 →