splitifi_get_model
Fetch the full model card for a specific model by ID. Returns metadata, performance metrics, training provenance, and jurisdiction. Use splitifi_list_models to discover model IDs.
This record as markdown: /tools/io-github-mysplitifi-splitifi-mcp/splitifi-get-model.md
What splitifi_get_model does on Splitifi Intelligence MCP
AI agents call splitifi_get_model 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 |
|---|---|---|---|
model_id | string | Yes | Model ID (e.g. "settlement_probability_v1", "jd_wl_cacd_v1", "lf_ca1_antitrust_win_v1") |
Parameters from the server's own tool schema.
Why splitifi_get_model is rated Low
This tool retrieves and returns static metadata and model information about a pre-trained ML model by ID. It has no side effects, does not execute code or queries, does not modify state, and does not move money. The blast radius of misuse is minimal—an attacker gaining access would be able to read model documentation and performance data, which poses no direct operational risk. Classification as Read is appropriate.
From the tool's definition Tool performs 'Fetch' operation returning 'metadata, performance metrics, training provenance, and jurisdiction' with no mention of modification, deletion, execution, or financial operations. Description explicitly indicates retrieval-only behavior.
Attacks that exploit this kind of access
The rule that runs splitifi_get_model 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_get_model, this is the rule to start with:
splitifi_get_model 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_get_model call is checked against it from then on.
Questions about splitifi_get_model
Fetch the full model card for a specific model by ID. Returns metadata, performance metrics, training provenance, and jurisdiction. Use splitifi_list_models to discover model IDs. It is categorised as a Read tool in the Splitifi Intelligence MCP MCP Server, which means it retrieves data without modifying state.
splitifi_get_model accepts 1 parameter: model_id. Required: model_id. 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_get_model: 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_get_model 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_get_model 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_get_model. 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_get_model 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