Rank a set of OPEN DEALS the user brings (from their CRM, a CSV, a warehouse query) by expected value (amount x win%) with a velocity penalty for stalled deals, and bucket them into Work now / Soon / Watch with reasons and risk flags (past close date, no next step, stalled in stage). Accepts loos...
AI agents call prioritize_pipeline to retrieve information from StackSwap without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
deals | array | Yes | Open deals as loose records. Recognized fields (with aliases): amount/value/acv, stage/dealstage, winProb/probability, closeDate/closeInDays, daysInStage, nextS |
quota | number | — | Optional quota/target to compute weighted coverage against. |
config | object | — | Optional tuning. |
Parameters from the server's own tool schema.
The tool takes deal records as input and returns a ranked, bucketed analysis with risk flags. It is described as read-only (server description states '8 read-only tools') and performs computation/inference on user-supplied data without writing back to any system.
From the tool's definition 'Rank a set of OPEN DEALS', 'bucket them into Work now / Soon / Watch with reasons and risk flags', 'win% is inferred from the stage name when absent' — the tool analyzes and ranks deal data provided by the user, producing a prioritized view with no stated…
Attacks that exploit this kind of access
Rank a set of OPEN DEALS the user brings (from their CRM, a CSV, a warehouse query) by expected value (amount x win%) with a velocity penalty for stalled deals, and bucket them into Work now / Soon / Watch with reasons and risk flags (past close date, no next step, stalled in stage). Accepts loosely-typed deal records — common field aliases (amount/value/acv, stage/dealstage, probability/winProb, closeDate/closeInDays, daysInStage, nextStep) are normalized automatically; win% is inferred from the stage name when absent. Optional quota adds a weighted-coverage line; optional config.stageProbabilities overrides the stage->win% map. Operates only on supplied deals — it never returns net-new prospects. Use when the user asks 'which deals should my reps work first', 'prioritize my pipeline', or pastes a deal list. It is categorised as a Read tool in the StackSwap MCP Server, which means it retrieves data without modifying state.
prioritize_pipeline accepts 3 parameters: deals, quota, config. Required: deals. The full parameter table on this page comes from the server's own tool schema.
Register the StackSwap MCP server in PolicyLayer and add a rule for prioritize_pipeline: 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 StackSwap. Nothing to install.
prioritize_pipeline 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 prioritize_pipeline 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 prioritize_pipeline. 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.
prioritize_pipeline is provided by the StackSwap MCP server (StonesofCreation/stackswap-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 →