get_990_summary
AI agents call get_990_summary to retrieve information from Kindora-for-ChatGPT MCP server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries publicly available IRS 990 summary information with no side effects. The 'get_*' naming pattern combined with the server's stated purpose of enabling 'grant discovery' from public filings indicates a read-only retrieval operation. Tool description is empty, which slightly reduces confidence, but context from sibling tools and server purpose strongly suggests read classification.
From the tool's definition Tool name 'get_990_summary' indicates retrieval of summary data from IRS Form 990 filings. The server description states it 're-exposes Kindora's public funder and grant tools' focused on 'grant discovery from IRS 990 filings and Grants.gov'.
Attacks that exploit this kind of access
get_990_summary. It is categorised as a Read tool in the Kindora-for-ChatGPT MCP server MCP Server, which means it retrieves data without modifying state.
Register the Kindora-for-ChatGPT MCP server MCP server in PolicyLayer and add a rule for get_990_summary: 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 Kindora-for-ChatGPT MCP server. Nothing to install.
get_990_summary 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 get_990_summary 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 get_990_summary. 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.
get_990_summary is provided by the Kindora-for-ChatGPT MCP server MCP server (wayanvota/kindora-chatgpt-mcp). 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 →