Retrieve memories based on query with rich contextual information
AI agents call recall_memories to retrieve information from Heimdall MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves stored memory data without modifying, deleting, or executing any operations. It functions as a lookup/search mechanism for codebase context, documentation, and git history that was previously stored. No side effects or state changes occur from invoking this tool.
From the tool's definition Tool name 'recall_memories' and description 'Retrieve memories based on query with rich contextual information' indicate data retrieval only.
Attacks that exploit this kind of access
Retrieve memories based on query with rich contextual information. It is categorised as a Read tool in the Heimdall MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Heimdall MCP Server MCP server in PolicyLayer and add a rule for recall_memories: 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 Heimdall MCP Server. Nothing to install.
recall_memories 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 recall_memories 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 recall_memories. 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.
recall_memories is provided by the Heimdall MCP Server MCP server (lcbcfoo/heimdall-mcp-server). 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 →