Read a memory bank file for a specific project
AI agents call memory_bank_read to retrieve information from Memory Bank without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves data from a memory bank file without modifying, executing, or destructing any information. It is a straightforward read operation that queries existing data, making it low-severity. The context of project memory management and the presence of sibling tools (memory_bank_update, memory_bank_write) that handle modifications further confirms this tool's read-only nature.
From the tool's definition Tool name is 'memory_bank_read' and description explicitly states 'Read a memory bank file'. The verb 'read' combined with the retrieval-only nature of the operation (no mention of modification, deletion, or execution) clearly indicates a query operation with…
Attacks that exploit this kind of access
Read a memory bank file for a specific project. It is categorised as a Read tool in the Memory Bank MCP Server, which means it retrieves data without modifying state.
Register the Memory Bank MCP server in PolicyLayer and add a rule for memory_bank_read: 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 Memory Bank. Nothing to install.
memory_bank_read 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 memory_bank_read 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 memory_bank_read. 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.
memory_bank_read is provided by the Memory Bank MCP server (@allpepper/memory-bank-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 →