Get memory context for a project
AI agents call get_memory_context to retrieve information from SAM without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries existing memory data for a project without modifying, deleting, or executing any operations. It is a straightforward data retrieval function analogous to 'fetch' or 'get', which falls clearly into the Read category.
From the tool's definition Tool name 'get_memory_context' and description 'Get memory context for a project' indicate a retrieval operation. The verb 'Get' and the operation of retrieving stored memory context is a read-only action with no data modification or side effects.
Documented attack patterns abuse exactly the kind of access get_memory_context gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and SAM, and nothing reaches the server without passing your rules. This is the rule we recommend for get_memory_context:
{
"version": "1",
"default": "deny",
"tools": {
"get_memory_context": {}
}
}get_memory_context 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.
Get memory context for a project. It is categorised as a Read tool in the SAM MCP Server, which means it retrieves data without modifying state.
Register the SAM MCP server in PolicyLayer and add a rule for get_memory_context: 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 SAM. Nothing to install.
get_memory_context 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_context 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_context. 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_context is provided by the SAM MCP server (pigrieco/mcp-memory-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from SAM, 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.
37 SAM tools catalogued and risk-classified — across an index of 43,000+ MCP servers.