memory_recall_episodes

Search episodes via FTS5 (bm25 ranking). Optional task_id scopes the search; k caps results (default 5, max 50).

Server Threadwork tianqbu/threadwork
Category Read
Risk class Low
Parameters 00 required

What memory_recall_episodes does on Threadwork

AI agents call memory_recall_episodes to retrieve information from Threadwork without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Why memory_recall_episodes needs a policy

This tool retrieves and queries stored episode data using full-text search ranking. It has no side effects—it does not create, modify, delete, or execute operations. The optional task_id and k parameters are read-only filters. It belongs in the Read category with low severity because misuse by an AI agent would only cause information disclosure or inefficient queries, not data loss or harmful actions.

From the tool's definition Tool description explicitly states 'Search episodes via FTS5' and uses optional parameters to scope/cap results. The term 'search' and 'recall' indicate data retrieval with no modification. FTS5 is a full-text search mechanism that queries existing data.

Questions about memory_recall_episodes

What does the memory_recall_episodes tool do? +

Search episodes via FTS5 (bm25 ranking). Optional task_id scopes the search; k caps results (default 5, max 50). It is categorised as a Read tool in the Threadwork MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on memory_recall_episodes? +

Register the Threadwork MCP server in PolicyLayer and add a rule for memory_recall_episodes: 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 Threadwork. Nothing to install.

What risk level is memory_recall_episodes? +

memory_recall_episodes is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit memory_recall_episodes? +

Yes. Add a rate_limit block to the memory_recall_episodes 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.

How do I block memory_recall_episodes completely? +

Set action: deny in the PolicyLayer policy for memory_recall_episodes. 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.

What MCP server provides memory_recall_episodes? +

memory_recall_episodes is provided by the Threadwork MCP server (tianqbu/threadwork). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// LOOK UP ANOTHER 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 →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.