Kindora Funder Discovery

Maximum number of funders to return (1-50)

Optional 2-letter state or "City, ST". Only biases peer discovery under org_description; never filters funders.

Minimum single-grant size in USD (default 5000)

Short cause phrase for the nonprofit (fallback). Example: "youth mental health". Adding words narrows the match.

Names or EINs of peer / aspirational organizations. Example: ["Greater Chicago Food Depository", "Feeding America"].

Maximum number of funders to return (1-50)

Minimum single-grant size in USD (default 1000)

EIN of the RECIPIENT nonprofit whose funders you want.

Name of the recipient nonprofit (resolved via the IRS BMF registry when recipient_ein is not given).

Foundation EIN (9 digits). Can include hyphens (e.g., "94-3136777") or be provided as digits only (e.g., "943136777").

Number of years of filing data to return (1-10)

Foundation EIN (9 digits, hyphens OK). Required for US 990 path. Optional if ``funder_id`` is supplied for a non-990 funder.

Optional non-990 funder id. Accepts a bare UUID or prefixed id like ``n9f:<uuid>`` / ``non990:<uuid>``. Use this for European funders, US community foundations, DAFs, and other funders that don't file IRS 990-PF. You can get it from search_funders or get_funder_profile.

Maximum number of grants to return (1-50)

Optional NTEE code to filter recipient organizations. Example: "B41" (Higher Education), "E" (Health). Use get_ntee_codes to browse available codes.

Optional case-insensitive substring to match against the grant_purpose field. Useful for narrowing to a topic when recipient NTEE code is too coarse — e.g., purpose_keyword="vaccine" surfaces Gates grants whose purpose text mentions vaccines, even when the recipient is classified outside health (universities, think tanks, etc.).

Optional recipient country filter. Use ISO 3166-1 alpha-2 codes (e.g., "CH" Switzerland, "ZA" South Africa, "NG" Nigeria, "IN" India). A code that is valid ISO is always read as ISO ("NG" is Nigeria, never Niger; "SN" is Senegal, never Singapore); legacy FIPS 10-4 codes match only when they are not ISO codes at all ("UK", "SF"). Output codes are emitted in ISO 3166.

Optional 2-letter US state code to filter by recipient state (e.g., "CA", "NY").

Optional year to filter by (filing_year for 990, grant_year for discovered). If not provided, returns all available years.

Foundation EIN (9 digits) for US 990 funders. Can include hyphens (e.g., "94-3136777") or be provided as digits only (e.g., "943136777"). Optional if ``funder_id`` is supplied for a non-990 funder.

Optional non-990 funder id. Accepts a bare UUID or ``n9f:<uuid>`` / ``non990:<uuid>``. The ``usf:<ein>`` prefix is also accepted and routes back to the EIN path.

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.

Optional non-990 funder id (bare UUID / ``n9f:<uuid>``).

Single letter (A-Z) to browse codes in a major category. Example: "A" for Arts, Culture & Humanities "B" for Education "E" for Health Care "P" for Human Services

Search term to find codes by description (case-insensitive). Example: "education", "youth", "environment"

Optional name of a specific tool to get detailed help for. Example: "search_funders", "get_funder_profile"

One of the 8 philanthropy categories above.

Funder HQ country — ISO 3166-1 alpha-2 ("US", "GB", "DE") or a recognized name ("United Kingdom", "Germany"). Filters by where the FOUNDATION is headquartered; the corpus spans European funders, not just US. Independent of `state` (US foundations are the only ones with state-level location data).

full-time | part-time | contract | internship | fellowship | temporary.

Categories to hide. Default is no category exclusions; the public jobs board includes operations roles. Pass specific category names to suppress them.

Restrict to one funder by EIN (9 digits, optional prefixes/dashes accepted).

Restrict to a LIST of funder EINs (up to 100). The recommended compositional pattern is search_funders → search_funder_jobs(funder_eins=[...]) for cause-area searches (climate, racial equity, youth, etc.) where the cause isn't captured by the 8 role-family categories.

Maximum number of results to return (1-50)

Recency window in days (0-730). Set 0 to disable.

Keyword search on job title (case-insensitive substring). Examples: "program officer", "grants manager", "CEO", "communications director".

remote | hybrid | on-site.

Experience level: internship_fellowship | entry_level | mid | senior | executive. Comma-separate for multi-select — 'entry_level,internship_fellowship' is the early-career shelf (new grads, students). Rows not yet leveled by the classifier are excluded when set.

Result ordering. 'funder_giving' (default) ranks by the foundation's annual average giving so the biggest funders surface first. 'recent' sorts by posted_at desc.

2-letter US state code (e.g., "CA", "NY"). Uses a broad SQL prefilter plus an exact token-aware post-filter against the location field.

City name to filter by (case-insensitive). Example: "San Francisco", "New York"

Optional HQ country name (or list of names) to restrict to funders headquartered in those countries (e.g., "Germany", ["United States", "Canada"]). Distinct from `grantee_country_codes` (where the funder's grants land) and from `state` (US state of HQ). Use when the user asks for funders based in a specific country — e.g. "European-headquartered foundations" → country=["Germany","Spain","United Kingdom", "Switzerland","Netherlands","France"]. US foundations are included only when "United States" (or "USA") is in the list, or when the param is omitted.

Optional list of canonical funder_type codes to exclude from results. NOTE: this search ALREADY excludes the operating-entity types by default — private_operating (pharma patient-assistance foundations) and operating_nonprofit (hospital / university group returns) post large "annual_grants" but aren't grantmakers you can apply to. Use this for ADDITIONAL categories; to opt an operating type back in, name it in funder_type instead.

Optional canonical funder_type to include. Examples: "community_foundation", "family_foundation", "corporate_foundation", "private_operating", "operating_nonprofit", "independent_foundation". Use this to narrow to a specific kind of grantmaker. NOTE: operating entities (private_operating, operating_nonprofit) are EXCLUDED BY DEFAULT — name one here to include it (e.g. to look up a specific hospital or patient-assistance foundation).

Optional list of FIPS 10-4 country codes (e.g., "UK" for United Kingdom, "IN" for India, "KE" for Kenya, "SF" for South Africa) to restrict to funders whose grantees are located in those countries. Use this when the user is asking for funders that move money into a specific non-US geography. Country here is the grantee's HQ country, derived from foundation_grants. When set, the search is forced through the hybrid path; the ILIKE-only name-match path cannot filter by country. Distinct from `state`, which filters by the funder's own US HQ.

Filter to foundations that make expenditure responsibility grants (grants to non-501(c)(3) entities like PBCs, for-profits, and foreign orgs). Set to True to find only ER-active funders.

Filter to foundations with known program-related investment activity. Set true when looking for PRI-active capital providers.

Maximum number of results to return (1-50)

Maximum total assets filter in dollars. Example: 100000000 (foundations with up to $100M assets)

Colloquial metro / region name for sub-state geography a single city can't capture — "Bay Area", "NYC", "the DMV", "Greater Boston", "Los Angeles", "Chicago", "Seattle". Resolved to its MSA/CBSA code set and applied as an HQ pre-filter. PREFER this over `city` whenever the user names a metro/region rather than one municipality (e.g. "Bay Area funders that fund drug rehab" → query="drug rehab addiction", metro="Bay Area"). Accepts a single name or a list. City names resolve too ('Cleveland', 'Knoxville', 'Portland, OR'). An unrecognized name does NOT error: the search runs without that metro filter and the result carries `geo_notice` saying so (with a did-you-mean when one is close). Example: "Bay Area", ["NYC", "Greater Boston"]

Minimum total assets filter in dollars. Example: 10000000 (foundations with $10M+ assets)

Explicit MSA/CBSA codes when you already know them (e.g. ["41860", "41940"]); unioned with whatever `metro` resolves to. Most callers should use `metro`.

NTEE classification code to filter by. Example: "A20" (Arts Organizations), "B" (Education), "E" (Health)

Search term for a funder name or cause-area phrase. Example: "Ford Foundation", "global health", "community foundation" Topic searches work best with 2+ words.

Two-letter US state code to filter by funder HQ location. Example: "CA", "NY", "TX"

Only IRS-active orgs (default True).

Case-insensitive exact city name.

Maximum number of results (1-50)

Maximum total received.

Colloquial metro/region ("Bay Area", "NYC", "Chicago", "Greater Boston") or a city name ("Cleveland", "Portland, OR") → resolved to its MSA codes. Prefer over city for metro-area intent. An unrecognized name does not error: the search runs without the metro filter and the result carries `geo_notice`.

Minimum employee count.

Minimum distinct funders.

Minimum total grant dollars RECEIVED (the key grantee-benchmarking filter — "received over $1M").

Explicit CBSA codes if you already know them.

NTEE classification PREFIXES (e.g. ["K31"] food banks, ["E"] health, ["B20"] schools). Prefix match, so "K" = all food/agriculture, "K31" = food banks specifically.

Case-insensitive substring match on the organization name.

received (default) | revenue | funders | name.

2-letter US state code (e.g. "IL").

Filter government grants by agency name (case-insensitive). Example: "Department of Education", "NSF", "NIH"

Where the applicant works — a country name or a region. Returns funders scoped to that place PLUS regional and global funders, with place-specific ones ranked first (a Kenyan applicant also sees "Sub-Saharan Africa" and worldwide funders). Native names work ("Deutschland", "Espana"). OMIT when the user has not named a place: "Global"/"International" is accepted but simply means no geographic restriction, so it is never needed. An unrecognised value broadens the search rather than emptying it. Use this instead of state for international queries — passing "India" via state would error because state requires a US code. Mixing state with a non-US country is rejected. Example: "India", "Kenya", "Southeast Asia", "Deutschland"

Deadline lookahead window in days (1-365)

Filter foundation programs by focus area (matches values in focus_areas array). Example: "Education", "Health", "Environment"

Set TRUE when the applicant is a FOR-PROFIT entity (social enterprise, public benefit corporation, B Corp, L3C, CDFI). Routes foundation-program search to the for-profit capital pool: loans, program-related investments, revenue-based financing, patient equity, guarantees — capital a company can actually take. Default False = the 501(c)(3) grant pool, which deliberately excludes those instruments.

Maximum number of results to return (1-50)

Maximum grant size filter in dollars. Example: 500000 (grants up to $500K)

Minimum grant size filter in dollars. Example: 50000 (grants of $50K+)

GOVERNMENT-grants applicant filter only. Omit for the entity-aware default: true for nonprofits and false for for-profit applicants. Does not open the foundation pool — use for_profit_applicant.

Natural language search query. Searches across program names, descriptions, focus areas, beneficiary types, and geographic focus. Supports quoted phrases for exact matching and -term for exclusion. Example: "youth outdoor education", "affordable housing", "STEM education for girls", "food bank hunger", "climate change environment", "domestic violence women"

Filter by grant source type. Options: "foundation" (private foundation programs only), "government" (federal + state government grants only), or omit for both sources combined. PREFER omitting this — the foundation corpus is much larger, and filtering to government-only often returns few or zero results.

Two-letter US state code to filter by geographic relevance. Returns programs focused on that state plus nationally available programs. Example: "CA", "NY", "TX"

Alias for query. The tool description says 'by TOPIC', so many MCP clients send topic= (32 rejected calls by 2026-07-11) — accept both; query wins when both are set.