aidefence_analyze
Deep analysis of input for specific threat types with similar pattern search and mitigation recommendations. Use when nothing native exists — Claude Code does not have a PII / prompt-injection / adversarial-text scanner. Pair with any tool that ingests untrusted input (browser scrape, federation ...
This record as markdown: /tools/io-github-ruvnet-claude-flow/aidefence-analyze.md
What aidefence_analyze does on Claude Flow
AI agents call aidefence_analyze 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 aidefence_analyze is rated Low
This is a defensive analysis tool that reads and examines data to detect security threats without modifying, executing, or destructively altering anything. It retrieves threat intelligence patterns and returns recommendations. The pairing suggestion with 'any tool that ingests untrusted input' further confirms its role as a passive security scanner rather than an active intervention tool.
From the tool's definition The tool performs 'deep analysis' and 'pattern search' on input data with 'mitigation recommendations.' The description emphasizes it is a scanner for threat detection (PII, prompt-injection, adversarial-text), not an executor or modifier of data.
Attacks that exploit this kind of access
The rule that runs aidefence_analyze 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 aidefence_analyze, this is the rule to start with:
aidefence_analyze 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 aidefence_analyze call is checked against it from then on.
Questions about aidefence_analyze
Deep analysis of input for specific threat types with similar pattern search and mitigation recommendations. Use when nothing native exists — Claude Code does not have a PII / prompt-injection / adversarial-text scanner. Pair with any tool that ingests untrusted input (browser scrape, federation envelope, memory_import_claude). 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 aidefence_analyze: 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.
aidefence_analyze 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 aidefence_analyze 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 aidefence_analyze. 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.
aidefence_analyze 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