AI agents call ad4m_recall to retrieve information from Mcp Ad4m without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a pure data retrieval tool that searches and returns semantic graph links with metadata. It has no capacity to modify, delete, or execute operations. The omission of fields for matching is a standard filter pattern in query tools. Even though it accesses persistent memory, the operation is non-destructive and read-only, making it the safest category with minimal blast radius if misused.
From the tool's definition Tool description states 'Query links from a Perspective' and 'Returns author DID + timestamp for each match' with no mention of modifications, deletions, or side effects.
Attacks that exploit this kind of access
Query links from a Perspective by source, predicate, or target. Omit any field to match all. Returns author DID + timestamp for each match. It is categorised as a Read tool in the Mcp Ad4m MCP Server, which means it retrieves data without modifying state.
Register the Mcp Ad4m MCP server in PolicyLayer and add a rule for ad4m_recall: 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 Mcp Ad4m. Nothing to install.
ad4m_recall 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 ad4m_recall 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 ad4m_recall. 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.
ad4m_recall is provided by the Mcp Ad4m MCP server (thefranceway/mcp-ad4m). 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 →