Get configuration value Use when native settings.json edits are wrong because the values need to be read by the Ruflo runtime (daemon, MCP server, neural router) — those load via the config_* path, not by re-reading settings.json. For .gitignore / .editorconfig style files, native Edit is fine.
AI agents call config_get 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.
This tool retrieves configuration values from the Ruflo runtime without modifying, deleting, or executing operations. It is a pure read operation that queries existing settings. The low severity reflects that configuration retrieval alone poses minimal risk—configuration values themselves are typically non-sensitive in enterprise contexts, and reading them has no side effects or destructive capability.
From the tool's definition Tool name is 'config_get' with description stating 'Get configuration value'. The verb 'Get' and the retrieval-only purpose indicate data querying without modification.
Attacks that exploit this kind of access
Get configuration value Use when native settings.json edits are wrong because the values need to be read by the Ruflo runtime (daemon, MCP server, neural router) — those load via the config_* path, not by re-reading settings.json. For .gitignore / .editorconfig style files, native Edit is fine. 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 config_get: 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.
config_get 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 config_get 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 config_get. 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.
config_get 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.