Record one run of a proposal
AI agents use write_experiment 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 or appends new experiment records to a lab notebook system. It modifies state by recording data but does not delete, execute arbitrary code, move money, or trigger external operations beyond the notebook domain itself. The append-only design means changes are reversible through logical operations (superseding proposals).
From the tool's definition Tool name 'write_experiment' and description 'Record one run of a proposal' indicate creation/modification of experiment records. The server uses 'append-only semantics' confirming data is added reversibly without deletion.
Attacks that exploit this kind of access
Record one run of a proposal. 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 write_experiment: 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.
write_experiment 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 write_experiment 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 write_experiment. 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.
write_experiment 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 →