Find which skill was used for similar past tasks. Skip the skill-selection decision for common task patterns.
AI agents call recall_skill_choice to retrieve information from GraphHub without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries persistent session memory to retrieve information about past skill usage. It has no side effects, does not modify or delete data, and does not execute code or trigger external operations. It is purely informational, enabling an agent to make faster decisions by looking up previous patterns rather than deciding from scratch. Classification as Read is appropriate.
From the tool's definition Tool description states 'Find which skill was used' — a retrieval/query operation that searches historical session memory for similar task patterns. No modification, deletion, or execution of external code is described.
Documented attack patterns abuse exactly the kind of access recall_skill_choice gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and GraphHub, and nothing reaches the server without passing your rules. This is the rule we recommend for recall_skill_choice:
{
"version": "1",
"default": "deny",
"tools": {
"recall_skill_choice": {}
}
}recall_skill_choice is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Find which skill was used for similar past tasks. Skip the skill-selection decision for common task patterns. It is categorised as a Read tool in the GraphHub MCP Server, which means it retrieves data without modifying state.
Register the GraphHub MCP server in PolicyLayer and add a rule for recall_skill_choice: 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 GraphHub. Nothing to install.
recall_skill_choice 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 recall_skill_choice 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 recall_skill_choice. 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.
recall_skill_choice is provided by the GraphHub MCP server (slnquangtran/graph-hub). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from GraphHub, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
32 GraphHub tools catalogued and risk-classified — across an index of 43,000+ MCP servers.