upsell_hunter
Chasseur d'upsell — Gapup agent-payable C-suite expertise (CRO). Returns a structured, audited deliverable. Reference case: Gapup Hub — Upsell 8 comptes · €127k potentiel · Top 3 : Alan+Qonto+Pennylane · Playbook 5 étapes. Inputs are validated server-side — send the documented case fields.
This record as markdown: /tools/io-github-getgapup-mcp-knowledge/upsell-hunter.md
What upsell_hunter does on Mcp Knowledge
AI agents call upsell_hunter to retrieve information from Mcp Knowledge without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
async | boolean | — | If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client ti |
company | object | Yes | |
horizon | string | — | |
product | object | Yes | |
accounts | array | Yes | |
targetUpsellEur | number | — |
Parameters from the server's own tool schema.
Why upsell_hunter is rated Low
The tool appears to perform analysis and return structured intelligence/recommendations about upsell opportunities (account analysis, potential revenue identification, playbook). This is primarily a read/query-style analytical tool that retrieves expert business analysis. However, the description is partially in French and somewhat opaque about whether it triggers any external write or financial actions.
From the tool's definition 'Chasseur d'upsell' — returns a structured, audited deliverable; reference case shows analysis of accounts and upsell potential (€127k potentiel)
Risk signalsHigh parameter count (21 properties)
Attacks that exploit this kind of access
The rule that runs upsell_hunter safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Mcp Knowledge, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For upsell_hunter, this is the rule to start with:
upsell_hunter 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 Mcp Knowledge, apply this rule, and every upsell_hunter call is checked against it from then on.
Questions about upsell_hunter
Chasseur d'upsell — Gapup agent-payable C-suite expertise (CRO). Returns a structured, audited deliverable. Reference case: Gapup Hub — Upsell 8 comptes · €127k potentiel · Top 3 : Alan+Qonto+Pennylane · Playbook 5 étapes. Inputs are validated server-side — send the documented case fields. It is categorised as a Read tool in the Mcp Knowledge MCP Server, which means it retrieves data without modifying state.
upsell_hunter accepts 6 parameters: async, company, horizon, product, accounts, targetUpsellEur. Required: company, product, accounts. The full parameter table on this page comes from the server's own tool schema.
Register the Mcp Knowledge MCP server in PolicyLayer and add a rule for upsell_hunter: 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 Mcp Knowledge. Nothing to install.
upsell_hunter 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 upsell_hunter 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 upsell_hunter. 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.
upsell_hunter is provided by the Mcp Knowledge MCP server (https://mcp.gapup.io). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Mcp Knowledge, and thousands of servers like it.
This server
Across the catalogue