This record as markdown: /tools/delego-dev-delego/delego-pending.md
What delego_pending does on Pypi:delego
AI agents call delego_pending to retrieve information from Pypi:delego without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why delego_pending is rated Low
The tool name suggests listing pending items (proposed actions awaiting resolution) in a policy/audit firewall system. This is consistent with a read/query operation. However, the description is empty, lowering confidence. No evidence of write, execute, or destructive behavior.
From the tool's definition Tool name 'delego_pending' and empty description. Based on sibling tools (audit_tail, propose_action, resolve_action, show_policy), 'pending' most likely lists pending/unresolved proposed actions awaiting authorization.
Attacks that exploit this kind of access
The rule that runs delego_pending safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Pypi:delego, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For delego_pending, this is the rule to start with:
delego_pending 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 Pypi:delego, apply this rule, and every delego_pending call is checked against it from then on.
Questions about delego_pending
delego_pending is a read tool on the Pypi:delego MCP server. It is categorised as a Read tool in the Pypi:delego MCP Server, which means it retrieves data without modifying state.
Register the Pypi:delego MCP server in PolicyLayer and add a rule for delego_pending: 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 Pypi:delego. Nothing to install.
delego_pending 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 delego_pending 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 delego_pending. 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.
delego_pending is provided by the Pypi:delego MCP server (pypi:delego). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Pypi:delego, and thousands of servers like it.
This server
Across the catalogue