Record an unanswered query as a bullet in gaps.md.
AI agents use add_gap to create or update resources in Ebony Enriching — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Ebony Enriching environment.
This tool creates new entries in a research notebook by appending to a gaps file. It is a Write operation because it adds data to a file in a reversible manner (entries can be removed via `remove_gap`).
From the tool's definition Tool description states it will 'Record an unanswered query as a bullet in `gaps.md`', which creates new data by appending to a file. The server uses 'append-only semantics', confirming that this modifies data reversibly without deletion or overwrite.
Attacks that exploit this kind of access
Record an unanswered query as a bullet in gaps.md. It is categorised as a Write tool in the Ebony Enriching MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Ebony Enriching MCP server in PolicyLayer and add a rule for add_gap: 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 Ebony Enriching. Nothing to install.
add_gap 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 add_gap 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 add_gap. 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.
add_gap is provided by the Ebony Enriching MCP server (parkviewlab/ebony-enriching). 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 →