Prepare a knowledge backfill run for a project. Returns done-flows + existing ADRs + structured instructions that YOU (Claude) must follow to classify and propose knowledge drafts. This is the MCP-first alternative to the keyword heuristic. Workflow: 1. Call this tool → receive flows, existing AD...
AI agents call knowledge_backfill_request 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.
The tool retrieves existing data (done-flows, ADRs, rulesets) and returns them for the AI to process. It does not itself create, modify, or delete anything — the actual knowledge draft creation is a separate subsequent step (knowledge_draft_create). The medium severity reflects that it exposes potentially sensitive project architecture decisions and workflow history to the AI agent.
From the tool's definition Prepare a knowledge backfill run for a project. Returns done-flows + existing ADRs + structured instructions
Attacks that exploit this kind of access
Prepare a knowledge backfill run for a project. Returns done-flows + existing ADRs + structured instructions that YOU (Claude) must follow to classify and propose knowledge drafts. This is the MCP-first alternative to the keyword heuristic. Workflow: 1. Call this tool → receive flows, existing ADRs, and the ruleset 2. Read the flows, decide which qualify as ADR / Pattern / Runbook / Lessons-Learned 3. Skip anything already covered by existing ADRs 4. Group similar flows into ONE draft with multiple sourceFlowIds 5. For each draft: call knowledge_draft_create with the payload Be conservative. Only propose drafts you are confident about. Better few high-quality drafts than many noisy ones. 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_backfill_request: 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_backfill_request 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_backfill_request 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_backfill_request. 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_backfill_request 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 →