New Your team’s decisions, in one playbook every coding agent works from. Never answer your agent twice

metaharness_drift_from_history

iter 53 — one-command drift detection. Composes audit-list + oia-audit + audit-trend: finds the most recent record in

SERVERClaude Flow SOURCEclaude-flow
Low RISK CLASS
Category Read
Parameters 00 required
Recommended Allowedsee the rule below
Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/io-github-ruvnet-claude-flow/metaharness-drift-from-history.md

What metaharness_drift_from_history does on Claude Flow

AI agents call metaharness_drift_from_history 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 metaharness_drift_from_history is rated Low

The tool retrieves and analyzes historical audit records to detect drift—a diagnostic/observational operation with no modification or execution of external commands. However, confidence is moderate (0.72) because the description is incomplete ('finds the most recent record in' trails off), and the broader context of a 'hive-mind swarm' orchestration platform with many tools suggests potential for complex side…

From the tool's definition Tool name contains 'drift_from_history' and description states 'drift detection' that 'Composes audit-list + oia-audit + audit-trend: finds the most recent record'. These are query/analysis operations over audit and historical data.

Questions about metaharness_drift_from_history

What does the metaharness_drift_from_history tool do? +

iter 53 — one-command drift detection. Composes audit-list + oia-audit + audit-trend: finds the most recent record in. 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 metaharness_drift_from_history? +

Register the Claude Flow MCP server in PolicyLayer and add a rule for metaharness_drift_from_history: 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 metaharness_drift_from_history? +

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

Can I rate-limit metaharness_drift_from_history? +

Yes. Add a rate_limit block to the metaharness_drift_from_history 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 metaharness_drift_from_history completely? +

Set action: deny in the PolicyLayer policy for metaharness_drift_from_history. 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 metaharness_drift_from_history? +

metaharness_drift_from_history 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.

// THE MCP REGISTRY

PolicyLayer tracks 44,603 MCP servers and 515,000+ tools.

Every server has a live record: who publishes it, whether it answers without auth, its risk grade, every tool classified, the recommended policy. This page is one line of Claude Flow's. Pull the full record:

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.