AI agents call mcp_get_value to retrieve information from Memcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves stored values from persistent memory without modifying, deleting, or executing operations. The lack of a detailed description lowers confidence slightly, but the naming convention and server purpose strongly suggest a simple read/retrieval function. No side effects or destructive capabilities are indicated.
From the tool's definition Tool name 'mcp_get_value' indicates data retrieval. Server context describes 'storing and retrieving information across conversations using a local SQLite database.' The sibling tool 'mcp_set_value' performs writes, positioning 'mcp_get_value' as the…
Attacks that exploit this kind of access
mcp_get_value. It is categorised as a Read tool in the Memcp MCP Server, which means it retrieves data without modifying state.
Register the Me MCP server in PolicyLayer and add a rule for mcp_get_value: 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 Memcp. Nothing to install.
mcp_get_value 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 mcp_get_value 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 mcp_get_value. 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.
mcp_get_value is provided by the Me MCP server (moshez/memcp). 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 →