AI agents use lexicon_update_track to create or update resources in Lexicon — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Lexicon environment.
This tool modifies track data (tags, metadata, cuepoints, incoming flag) within a DJ library. These are reversible changes—metadata and tags can be updated again or reverted. There is no deletion or destruction of data, no code execution, and no financial impact.
From the tool's definition Tool description states 'Update one track (tags, metadata, cuepoints, incoming flag)'. The verbs 'update' and 'metadata' modification are characteristic of Write operations.
Attacks that exploit this kind of access
Update one track (tags, metadata, cuepoints, incoming flag). Requires LEXICON_MCP_ALLOW_WRITES=1. It is categorised as a Write tool in the Lexicon MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Lexicon MCP server in PolicyLayer and add a rule for lexicon_update_track: 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 Lexicon. Nothing to install.
lexicon_update_track 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 lexicon_update_track 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 lexicon_update_track. 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.
lexicon_update_track is provided by the Lexicon MCP server (turbotailz/lexicon-mcp). 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 →