Classify every Dependency node by license risk: copyleft (GPL/AGPL/SSPL/EUPL/CPAL/OSL/RPL), proprietary, unknown. Returns tier=BLOCK if any copyleft or proprietary dep, WARN if only unknowns, OK otherwise. Note: until per-ecosystem license detection lands, most Dependency nodes carry license=
AI agents call license_audit to retrieve information from OpenCodeHub MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and analyzes license metadata on existing dependencies to produce risk classifications. It has no side effects—it does not install, remove, modify, or execute code. It is a pure information retrieval and analysis operation typical of Read category tools. The low severity reflects that misuse would only expose license compliance information without enabling destructive or risky actions.
From the tool's definition Tool classifies and returns license risk tiers (BLOCK/WARN/OK) based on existing Dependency node data; performs auditing and categorization without modifying repositories, dependencies, or configurations.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Classify every Dependency node by license risk: copyleft (GPL/AGPL/SSPL/EUPL/CPAL/OSL/RPL), proprietary, unknown. Returns tier=BLOCK if any copyleft or proprietary dep, WARN if only unknowns, OK otherwise. Note: until per-ecosystem license detection lands, most Dependency nodes carry license=. It is categorised as a Read tool in the OpenCodeHub MCP Server MCP Server, which means it retrieves data without modifying state.
Register the OpenCodeHub MCP Server MCP server in PolicyLayer and add a rule for license_audit: 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 OpenCodeHub MCP Server. Nothing to install.
license_audit 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 license_audit 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 license_audit. 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.
license_audit is provided by the OpenCodeHub MCP Server MCP server (theagenticguy/opencodehub). 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 →