AI agents call get_memory to retrieve information from AGI-MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves/queries stored memory entries across different layers (goals, observations, thoughts, commands, hypotheses, assessments) from persistent SQLite storage. It has no side effects, does not execute operations, modify data, delete records, or commit financial actions.
From the tool's definition Tool name is 'get_memory' with description 'Retrieve memory entries by layer' — uses retrieval verb 'Retrieve' indicating data query only, with no modification or execution capability mentioned.
Attacks that exploit this kind of access
Retrieve memory entries by layer (goals, observations, thoughts, commands, hypotheses, assessments). It is categorised as a Read tool in the AGI-MCP MCP Server, which means it retrieves data without modifying state.
Register the AGI- MCP server in PolicyLayer and add a rule for get_memory: 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 AGI-MCP. Nothing to install.
get_memory 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 get_memory 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 get_memory. 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.
get_memory is provided by the AGI- MCP server (muah1987/agi-mcp). 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 →