Snapshot of open work across the project. Returns four buckets: - inFlightFlows: flows currently in planning / in_progress / review - openIntents: forward-intent doc-pages with status !=
AI agents call pending_work 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 retrieves and queries existing data (workflow status, work items, intent documents) without creating, modifying, deleting, or executing operations. It is purely informational and read-only, making it a Read category risk with low severity since misuse would only expose information already within the project system.
From the tool's definition Tool returns a 'snapshot of open work' and 'returns four buckets' of data with no mention of modification, deletion, or side effects. The description indicates it queries project status and retrieves documentation pages.
Attacks that exploit this kind of access
Snapshot of open work across the project. Returns four buckets: - inFlightFlows: flows currently in planning / in_progress / review - openIntents: forward-intent doc-pages with status !=. 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 pending_work: 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.
pending_work 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 pending_work 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 pending_work. 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.
pending_work 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.
pending_work is one line of DevFlow MCP Server's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →