Decode a percent-encoded string.
AI agents call url_decode to retrieve information from Nexus Core without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
URL decoding is a reversible, read-only operation that transforms data format without creating, modifying, deleting, or executing anything. The tool has no blast radius if misused by an AI agent—at worst it produces incorrect plaintext from malformed input. It belongs in the Read category as a data retrieval/transformation tool.
From the tool's definition Tool name is 'url_decode' and description states 'Decode a percent-encoded string.' This is a pure data transformation utility that decodes URL-encoded input into plaintext without any side effects, state changes, or external operations.
Attacks that exploit this kind of access
Decode a percent-encoded string. It is categorised as a Read tool in the Nexus Core MCP Server, which means it retrieves data without modifying state.
Register the Nexus Core MCP server in PolicyLayer and add a rule for url_decode: 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 Nexus Core. Nothing to install.
url_decode is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the url_decode 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 url_decode. 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.
url_decode is provided by the Nexus Core MCP server (noumenon-ai/nexus-core). 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 →