Run a knowledge check on a flow: spot drift against existing ADRs and identify missing knowledge (topics without an asset). Returns flow text + ADR snapshots + instructions. YOU return the analysis — no draft creation in this tool. Use before submitting a flow to review.
AI agents call knowledge_check_flow to retrieve information from DevFlow MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns information about flows and Architecture Decision Records (ADRs) for analysis purposes. It retrieves data, compares it against existing records, and reports findings without modifying any state, executing commands, or triggering side effects. The explicit exclusion of draft creation confirms it is purely informational and read-only in nature.
From the tool's definition The tool 'run a knowledge check on a flow' and 'Returns flow text + ADR snapshots + instructions' indicates retrieval and analysis of existing data.
Attacks that exploit this kind of access
Run a knowledge check on a flow: spot drift against existing ADRs and identify missing knowledge (topics without an asset). Returns flow text + ADR snapshots + instructions. YOU return the analysis — no draft creation in this tool. Use before submitting a flow to review. It is categorised as a Read tool in the DevFlow MCP Server MCP Server, which means it retrieves data without modifying state.
Register the DevFlow MCP Server MCP server in PolicyLayer and add a rule for knowledge_check_flow: 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 DevFlow MCP Server. Nothing to install.
knowledge_check_flow 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 knowledge_check_flow 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 knowledge_check_flow. 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.
knowledge_check_flow is provided by the DevFlow MCP Server MCP server (klausfreiberufler/devflow-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →