splitifi_list_models
List all 28,636 production ML models across every practice vertical — family law, litigation finance, judicial AI, employment, securities, antitrust, healthcare, EDGAR/commercial, and international. Returns category breakdown and counts. Use splitifi_get_model to fetch a single model card.
This record as markdown: /tools/io-github-mysplitifi-splitifi-mcp/splitifi-list-models.md
What splitifi_list_models does on Splitifi Intelligence MCP
AI agents call splitifi_list_models to retrieve information from Splitifi Intelligence MCP 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 |
|---|---|---|---|
page | number | — | Page number for pagination. Default: 1 |
status | string | — | Filter by status: production, experimental, stub |
category | string | — | Filter by LF category (e.g. "antitrust", "patent_ip") |
vertical | string | — | Filter to a specific vertical (optional). Omit to return all. |
Parameters from the server's own tool schema.
Why splitifi_list_models is rated Low
This tool retrieves and queries metadata about available ML models (counts, categories, model cards). It performs no side effects, does not execute code or models, does not modify data, and does not trigger external operations. It is a pure read operation that enumerates assets in the system.
From the tool's definition Tool description states it 'List[s] all 28,636 production ML models' and 'Returns category breakdown and counts.' The verb 'list' is indicative of a retrieval operation with no modification or execution of those models.
Attacks that exploit this kind of access
The rule that runs splitifi_list_models safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Splitifi Intelligence MCP, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For splitifi_list_models, this is the rule to start with:
splitifi_list_models 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 Splitifi Intelligence MCP, apply this rule, and every splitifi_list_models call is checked against it from then on.
Questions about splitifi_list_models
List all 28,636 production ML models across every practice vertical — family law, litigation finance, judicial AI, employment, securities, antitrust, healthcare, EDGAR/commercial, and international. Returns category breakdown and counts. Use splitifi_get_model to fetch a single model card. It is categorised as a Read tool in the Splitifi Intelligence MCP MCP Server, which means it retrieves data without modifying state.
splitifi_list_models accepts 4 parameters: page, status, category, vertical. The full parameter table on this page comes from the server's own tool schema.
Register the Splitifi Intelligence MCP server in PolicyLayer and add a rule for splitifi_list_models: 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 Splitifi Intelligence MCP. Nothing to install.
splitifi_list_models 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 splitifi_list_models 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 splitifi_list_models. 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.
splitifi_list_models is provided by the Splitifi Intelligence MCP server (splitifi-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Splitifi Intelligence, and thousands of servers like it.
This server
Across the catalogue