Read one experiment record by (proposal_id, run_timestamp).
AI agents call read_experiment to retrieve information from Ebony Enriching without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves a single experiment record identified by proposal_id and run_timestamp. The verb 'read' and the retrieval-only semantics indicate no state changes, no code execution, and no destructive operations. The append-only semantics of the server reinforce that read operations are safe.
From the tool's definition Tool name is 'read_experiment' and description states 'Read one experiment record' — explicitly a retrieval operation with no modification or side effects.
Attacks that exploit this kind of access
Read one experiment record by (proposal_id, run_timestamp). It is categorised as a Read tool in the Ebony Enriching MCP Server, which means it retrieves data without modifying state.
Register the Ebony Enriching MCP server in PolicyLayer and add a rule for read_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.
read_experiment 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 read_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 read_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.
read_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 →