bva_screen
Screen a veterans claim issue type at the Board of Veterans' Appeals. Returns allowance rate, denial rate, remand rate, and docket type distribution for the matched issue.
This record as markdown: /tools/io-github-mysplitifi-splitifi-mcp/bva-screen.md
What bva_screen does on Splitifi Intelligence MCP
AI agents call bva_screen 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 |
|---|---|---|---|
issue_type | string | Yes | Veterans claim issue type (e.g. PTSD, hearing_loss, TBI, back_pain) |
Parameters from the server's own tool schema.
Why bva_screen is rated Low
This tool retrieves outcome predictions and judge profile data from a trained ML model based on historical veterans' appeals records. It performs a lookup/query operation with no side effects, no data modification, no code execution, and no financial transactions. It is purely informational for users researching veterans' claim outcomes.
From the tool's definition Tool returns statistics and predictive information ('allowance rate, denial rate, remand rate, and docket type distribution') from historical court records without modifying, deleting, or executing any actions. The verb 'screen' means retrieve/query data.
Attacks that exploit this kind of access
The rule that runs bva_screen 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 bva_screen, this is the rule to start with:
bva_screen 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 bva_screen call is checked against it from then on.
Questions about bva_screen
Screen a veterans claim issue type at the Board of Veterans' Appeals. Returns allowance rate, denial rate, remand rate, and docket type distribution for the matched issue. It is categorised as a Read tool in the Splitifi Intelligence MCP MCP Server, which means it retrieves data without modifying state.
bva_screen accepts 1 parameter: issue_type. Required: issue_type. 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 bva_screen: 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.
bva_screen 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 bva_screen 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 bva_screen. 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.
bva_screen 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