Get SBIR/STTR statistics - count of firms or awards by criteria
AI agents call sbir_stats to retrieve information from SBA MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns statistical counts and data summaries from a read-only data source (SBA federal R&D funding database). It performs no writes, deletive operations, code execution, or financial transactions. The blast radius of misuse is minimal—incorrect statistics queries return only informational data without side effects.
From the tool's definition Tool description explicitly states 'Get SBIR/STTR statistics' and 'count of firms or awards by criteria' — these are retrieval and aggregation operations with no mutation, deletion, or execution of external commands.
Attacks that exploit this kind of access
Get SBIR/STTR statistics - count of firms or awards by criteria. It is categorised as a Read tool in the SBA MCP Server MCP Server, which means it retrieves data without modifying state.
Register the SBA MCP Server MCP server in PolicyLayer and add a rule for sbir_stats: 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 SBA MCP Server. Nothing to install.
sbir_stats 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 sbir_stats 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 sbir_stats. 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.
sbir_stats is provided by the SBA MCP Server MCP server (shawndrake2/mcp-sba). 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 →