Get comprehensive giving statistics for a funder. This tool calculates aggregate statistics about a funder's grantmaking from IRS 990-PF data, web-extracted grant records, 360Giving rows, and CRA T3010 rows. It provides lifetime totals, focus areas, geographic distribution, and year-over-year tre...
Part of the Foundation Discovery server.
Free to start. No card required.
AI agents call get_funder_stats to retrieve information from Foundation Discovery without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though get_funder_stats only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
{
"version": "1",
"default": "deny",
"tools": {
"get_funder_stats": {}
}
}See the full Foundation Discovery policy for all 10 tools.
These attack patterns abuse exactly the kind of access get_funder_stats gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Get comprehensive giving statistics for a funder. This tool calculates aggregate statistics about a funder's grantmaking from IRS 990-PF data, web-extracted grant records, 360Giving rows, and CRA T3010 rows. It provides lifetime totals, focus areas, geographic distribution, and year-over-year trends. Pass ein for US 990 foundations, or funder_id (bare UUID / n9f:<uuid>) for non-990 funders. Args: ein: Foundation EIN (9 digits). Can include hyphens (e.g., "94-3136777") or be provided as digits only (e.g., "943136777"). Optional when funder_id is supplied. funder_id: Optional non-990 funder id (bare UUID / n9f:<uuid>). Returns: Dictionary containing: - ein: The normalized 9-digit EIN - foundation_name: Foundation name if found - giving_stats: Aggregate giving statistics: - total_grants: Total number of grants made - total_amount: Total grant amount when a single currency is present - total_amount_by_currency: Per-currency totals for mixed-currency data - average_grant: Mean grant size (raw and formatted) - median_grant: Median grant size (raw and formatted) - min_grant/max_grant: Range of grant sizes - focus_areas: NTEE code distribution showing: - top_ntee_codes: Top 10 categories funded with counts and amounts - total_ntee_codes_funded: Number of unique categories - geographic_distribution: Where grants went: - states: Top 10 US states by grant count. Each entry includes grant_count, total_amount, and avg_grant_amount (per-grant mean within that state). - countries: Top 10 recipient-HQ countries by grant count, keyed by ISO 3166-1 alpha-2 code (e.g. "CH" Switzerland, "ZA" South Africa, "NG" Nigeria). Each entry includes grant_count, total_amount, and avg_grant_amount — the per-country mean is prospect-targeting signal: a country with markedly higher avg than the US recipient bucket often indicates a different funding pattern (large global health intermediaries, multi-year capacity grants, etc.). Reflects recipient HQ, NOT implementation geography — many globally operating grantees are HQ'd in the US. - regions: Summary by US Census region (Northeast, Midwest, South, West) - non_us_recipient_pct: Percentage of grants (with country populated) that went to non-US-headquartered recipients - total_states_funded: Number of unique states - total_countries_funded: Number of unique recipient-HQ countries - yearly_breakdown: Year-by-year giving history: - Each year shows grant count, total amount, and average grant - year_over_year_trends: Trend analysis: - trend_direction: "increasing", "decreasing", or "stable" - yoy_changes: Detailed changes between consecutive years - data_quality: Information about data completeness: - years_of_data: How many years of grant data exist - year_range: Earliest and latest years in data - completeness: Percentage of grants with amounts, NTEE codes, states, and countries Examples: get_funder_stats(ein="943136777") get_funder_stats(ein="94-3136777") get_funder_stats(funder_id="n9f:34563780-0b99-463e-89e6-7e7b634634fd") Related tools: - get_funder_profile: Get foundation profile information - get_990_summary: Get financial trends (assets, revenue) - get_foundation_grants: See individual grants - get_ntee_codes: Look up what NTEE codes mean. It is categorised as a Read tool in the Foundation Discovery MCP Server, which means it retrieves data without modifying state.
Register the Foundation Discovery MCP server in PolicyLayer and add a rule for get_funder_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 Foundation Discovery. Nothing to install.
get_funder_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 get_funder_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 get_funder_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.
get_funder_stats is provided by the Foundation Discovery MCP server (https://kindora-mcp.azurewebsites.net/mcp/). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 10 Foundation Discovery tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.