This record as markdown: /tools/ruflo/metaharness-mcp-scan.md
What metaharness_mcp_scan does on Ruflo
AI agents call metaharness_mcp_scan to retrieve information from Ruflo without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why metaharness_mcp_scan is rated Low
Static security scans are read-only operations that examine code or configurations to identify vulnerabilities without making changes. No data is modified, deleted, or executed as a side effect. The incomplete description ('scan of' without completion) prevents higher confidence, but the word 'scan' combined with 'static' strongly suggests a non-destructive inspection tool.
From the tool's definition Tool name 'metaharness_mcp_scan' and description fragment 'static security scan of' indicate a scanning/analysis operation that retrieves or queries security information without modifying systems.
Attacks that exploit this kind of access
The rule that runs metaharness_mcp_scan safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Ruflo, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For metaharness_mcp_scan, this is the rule to start with:
metaharness_mcp_scan 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 Ruflo, apply this rule, and every metaharness_mcp_scan call is checked against it from then on.
Questions about metaharness_mcp_scan
ADR-150 — static security scan of. It is categorised as a Read tool in the Ruflo MCP Server, which means it retrieves data without modifying state.
Register the Ruflo MCP server in PolicyLayer and add a rule for metaharness_mcp_scan: 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 Ruflo. Nothing to install.
metaharness_mcp_scan 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 metaharness_mcp_scan 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 metaharness_mcp_scan. 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.
metaharness_mcp_scan is provided by the Ruflo MCP server (ruvnet/ruflo). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Ruflo, and thousands of servers like it.
This server
Across the catalogue