hive-mind_memory

Access hive shared memory Use when native Task is wrong because you need queen-led collective intelligence — Byzantine-FT consensus, broadcast across many worker agents, shared memory with bounded conflict. For a single subagent, native Task is fine. Pair with swarm_init first to set topology.

Server Claude Flow claude-flow
Category Read
Risk class Low
Parameters 00 required

What hive-mind_memory does on Claude Flow

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

Why hive-mind_memory needs a policy

The tool is described as 'Access hive shared memory,' which suggests a read operation. However, 'shared memory with bounded conflict' implies possible write/update semantics as well (e.g., consensus-based updates). The description is ambiguous about whether this tool only reads or also writes to shared memory.

From the tool's definition 'Access hive shared memory' — primary action is accessing/reading shared memory; no explicit write, delete, or execute semantics described

Questions about hive-mind_memory

What does the hive-mind_memory tool do? +

Access hive shared memory Use when native Task is wrong because you need queen-led collective intelligence — Byzantine-FT consensus, broadcast across many worker agents, shared memory with bounded conflict. For a single subagent, native Task is fine. Pair with swarm_init first to set topology. It is categorised as a Read tool in the Claude Flow MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on hive-mind_memory? +

Register the Claude Flow MCP server in PolicyLayer and add a rule for hive-mind_memory: 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 Claude Flow. Nothing to install.

What risk level is hive-mind_memory? +

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

Can I rate-limit hive-mind_memory? +

Yes. Add a rate_limit block to the hive-mind_memory 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 hive-mind_memory completely? +

Set action: deny in the PolicyLayer policy for hive-mind_memory. 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 hive-mind_memory? +

hive-mind_memory is provided by the Claude Flow MCP server (claude-flow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// GET IN TOUCH

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

Message sent.

We'll get back to you soon.