neural_compress
Compress neural model or embeddings Use when nothing native trains on your workflow — Claude Code has no learning loop. Use to train SONA/MoE/EWC patterns from successful task outcomes; query via neural_predict before spawning agents. Off-path for one-shot work.
This record as markdown: /tools/io-github-ruvnet-claude-flow/neural-compress.md
What neural_compress does on Claude Flow
AI agents call neural_compress to retrieve information from Claude Flow without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why neural_compress is rated Low
Even though neural_compress only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
The rule that runs neural_compress safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Claude Flow, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For neural_compress, this is the rule to start with:
neural_compress is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Claude Flow, apply this rule, and every neural_compress call is checked against it from then on.
Questions about neural_compress
Compress neural model or embeddings Use when nothing native trains on your workflow — Claude Code has no learning loop. Use to train SONA/MoE/EWC patterns from successful task outcomes; query via neural_predict before spawning agents. Off-path for one-shot work. It is categorised as a Read tool in the Claude Flow MCP Server, which means it retrieves data without modifying state.
Register the Claude Flow MCP server in PolicyLayer and add a rule for neural_compress: 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.
neural_compress 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 neural_compress 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 neural_compress. 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.
neural_compress 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.
More on Claude Flow, and thousands of servers like it.
This server
Across the catalogue