MCP server for nonprofit financials via ProPublica — IRS Form 990 data for 1.8M+ nonprofits.
Scored across 3 tools
Each tool serves a distinct, non-overlapping purpose: search for organizations, retrieve an organization's profile, and retrieve its filings. There is no ambiguity about which tool to use for a given task.
All tools follow the same 'nonprofit_<action>' pattern with verbs indicating the operation (search, get_filings, get_organization). The naming is clean, predictable, and consistent.
With only three tools, the set is tightly scoped to the server's purpose of exploring nonprofit data. Each tool is essential and there is no bloat or redundancy, making the count appropriate.
The tool surface covers the entire workflow: search to find entities, get details for a single entity, and retrieve historical filings for analysis. No obvious gaps exist for the stated purpose of exploring nonprofit data.
All Form 990 filings for a tax-exempt org by EIN: year-by-year revenue, expenses, assets, liabilities, net assets, revenue breakdown, executive compensation, and source PDF links. Use for trend analysis, due diligence, and accessing primary 990 documents. The filing year (tax_prd_yr) is the fiscal year of the return — data lags 1–2 years; always cite the year. An organization that resolves but has filed no 990 returns an empty filings array with a notice, not an error. Also returns filings_pdf_only — older filings with a PDF but no extracted financial data. Data from ProPublica Nonprofit Explorer, sourced from IRS Form 990 filings.
| Name | Required | Description | Default |
|---|---|---|---|
| ein | Yes | Employer Identification Number. Use nonprofit_search to resolve an org name to its EIN. |
| Name | Required | Description |
|---|---|---|
| ein | No | Employer Identification Number as integer. |
| name | No | Legal org name per IRS. |
| error | No | Present when the call failed. Absent on success. |
| notice | No | Present when the organization resolved but Nonprofit Explorer holds no filing of any kind for it — names the org and why the filing history is empty. An empty filings array without this notice means the org has filings that carry a PDF but no extracted data; read filings_pdf_only. |
| filings | No | Filings with extracted financial data, sorted newest first. |
| data_source | No | ProPublica + IRS attribution text. |
| propublica_url | No | ProPublica Nonprofit Explorer URL for this org. |
| filings_pdf_only | No | Older filings with a PDF but no extracted financial data. |
| total_filings_pdf_only | No | Count of PDF-only filings (no extracted data). |
| total_filings_with_data | No | Count of filings with extracted financial data. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and idempotentHint=true, so safety is covered. The description adds valuable behavioral context: data lag of 1–2 years, the empty-filings edge case (returns notice, not error), the existence of filings_pdf_only, and the data source. These details extend beyond annotations and help the agent predict behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description front-loads the primary purpose and use cases, then appends crucial caveats (data lag, empty array, pdf-only). It is information-dense but not overly verbose; every sentence contributes meaningful guidance. Slightly long for a single paragraph, but well-structured with a logical flow.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (multiple return variations, data lag, edge cases) and the existence of an output schema, the description covers all essential operational details: what data is returned, how to interpret the year, error handling for no filings, and the source. No missing information prevents correct invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema covers the ein parameter exhaustively (both integer and string forms, leading-zero handling, and a pointer to nonprofit_search). Schema coverage is 100%, so the description does not need to add parameter semantics. It adds a note about fiscal year (tax_prd_yr) but that is not a parameter; thus baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb ('Get') and the resource: all Form 990 filings for a tax-exempt org by EIN. It enumerates the specific data provided (revenue, expenses, assets, etc.) and includes distinct output variations (filings_pdf_only), making its purpose unambiguous and distinct from sibling tools like nonprofit_get_organization (org details) and nonprofit_search (EIN resolution).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives explicit use cases ('trend analysis, due diligence, accessing primary 990 documents') and clarifies the filing year lag, but it does not explicitly name when to use an alternative tool. The schema description does mention using nonprofit_search for name-to-EIN resolution, but the main description lacks direct sibling exclusions. Clear context with no exclusions warrants a 4.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Full profile for a single tax-exempt org by EIN: legal name, address, NTEE classification, 501(c) type, IRS ruling date, and a financial snapshot from the most recent Form 990 filing (revenue, expenses, assets, net assets, and the source PDF link). Also returns the IRS Business Master File standing — whether contributions are deductible, exemption status, and public-charity vs. private-foundation classification. Use nonprofit_search first if you only have an org name — this tool requires an EIN. Data lags 1–2 years; the tax year is shown prominently. Data from ProPublica Nonprofit Explorer, sourced from IRS Form 990 filings.
| Name | Required | Description | Default |
|---|---|---|---|
| ein | Yes | Employer Identification Number. Accepts integer (530196605) or string with optional hyphen ("53-0196605"). Obtain from nonprofit_search results. |
| Name | Required | Description |
|---|---|---|
| ein | No | Employer Identification Number as integer. |
| city | No | City. Null when not on record. |
| name | No | Legal org name per IRS. |
| error | No | Present when the call failed. Absent on success. |
| state | No | Two-letter state abbreviation. Null when not on record. |
| strein | No | EIN in "XX-XXXXXXX" format. |
| address | No | Street address. Null when not on record. |
| zipcode | No | ZIP code. Null when not on record. |
| ntee_code | No | Full NTEE code (e.g., "E210" = hospital). Null when unclassified. |
| sort_name | No | IRS Business Master File secondary name line (SORT_NAME) — an internal sort key such as a division or service-center label, not an alternate organization name. Null for most orgs. |
| deductible | No | Whether contributions to this org are tax-deductible, as "<IRS code> — <meaning>". Three states, not two: code 1 deductible, code 2 not deductible, code 4 deductible by treaty (foreign orgs). Null when the IRS Business Master File records no deductibility code. |
| data_source | No | ProPublica + IRS attribution text. |
| ruling_date | No | ISO date of IRS recognition (e.g., "1946-07"). Null when not on record. |
| asset_amount | No | Most recent IRS BMF total assets in USD. Null when not on record. |
| filing_count | No | Total filings with extracted data on record. |
| exempt_status | No | IRS exemption status as "<IRS code> — <meaning>"; code 1 is an unconditional exemption. This records what the IRS granted, not whether the exemption is still in force — the Business Master File is a lagging snapshot and automatic revocations are published separately. Null when the Business Master File records no status code. |
| income_amount | No | Most recent IRS BMF total income in USD. Null when not on record. |
| latest_filing | No | Financial snapshot from the most recent Form 990. Null if no filings_with_data are available. |
| bmf_tax_period | No | Tax period of the latest return recorded in the IRS Business Master File (e.g. "2025-06-01"). Often more recent than latest_filing.tax_prd_yr, which reflects the newest 990 ProPublica has extracted. Null when not on record. |
| propublica_url | No | ProPublica Nonprofit Explorer URL for this org. |
| revenue_amount | No | Most recent IRS BMF total revenue in USD. Null when not on record. |
| foundation_type | No | IRS foundation classification as "<IRS code> — <meaning>", separating public charities (codes 10–25) from private foundations (codes 2–4). Codes 0 (all organizations except 501(c)(3)) and 9 (suspense) fall outside both groups. Null when the IRS Business Master File records no foundation code. |
| subsection_code | No | 501(c) subsection number (e.g., 3 = charitable organization, covering both public charities and private foundations — see foundation_type to tell them apart). Null when not classified. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations declare readOnlyHint=true and idempotentHint=true, so the safety profile is already covered. The description adds valuable context beyond that: the data freshness caveat ('lags 1–2 years'), the source attribution ('ProPublica Nonprofit Explorer, sourced from IRS Form 990 filings'), and the note that the tax year is displayed prominently to avoid misreading stale data. This behavior — returning potentially dated financials that require interpretation — is exactly the kind of nuance annotations cannot convey.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is dense but every sentence earns its place: the first sentence inventories the return payload, the second covers the standing/classification fields, the third routes to the sibling, and the fourth handles data lag and provenance. The most decision-relevant line ('use nonprofit_search first... requires an EIN') is placed third but the leading payload inventory is front-loaded appropriately. No filler or redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Complete for a single-parameter read tool. An output schema exists, so return-value documentation is handled structurally. The description covers the data source, freshness caveat, sibling routing, and required parameter format. The only thing an agent might want — average field-level detail for every return value — is available in the output schema. Nothing needed for correct invocation or result interpretation is missing.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the schema fully documents the ein format (integer with leading-zero caveat, or string with optional hyphen). The description adds meaning beyond the schema by specifying where the EIN comes from ('Obtain from nonprofit_search results'), which tells the agent the provenance of the parameter and reinforces the tool-routing decision. It also explains what the parameter is used for (keying into the full profile), which the raw schema's 'Employer Identification Number' label does not.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb ('returns a full profile') and resource ('single tax-exempt org by EIN'), enumerating the exact fields delivered (legal name, address, NTEE, 501(c) type, ruling date, financials, BMF standing). This cleanly distinguishes it from siblings: it is the rich single-record getter, while nonprofit_get_filings covers filings and nonprofit_search is the discovery tool. No ambiguity survives.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly tells the agent when to use this tool vs. the sibling: 'Use nonprofit_search first if you only have an org name — this tool requires an EIN.' It also sets expectations about data recency ('Data lags 1–2 years'), which is a usage constraint the agent needs to decide whether the tool fits the user's needs. Both conditions for correct use are stated directly.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search 1.8M+ IRS-recognized tax-exempt organizations by name, keyword, city, or phrase. Optionally narrow by US state, NTEE major sector (1–10), or 501(c) subsection type. Returns EINs — pass them to nonprofit_get_organization or nonprofit_get_filings for details. Results are paginated at 25 per page; use the page parameter and num_pages to paginate. Total results cap at 10,000 in the API; if total_results === 10000 the actual count may be higher. A zero-match query and a page past the last one both return an empty organizations array with a notice rather than an error; only a page whose offset reaches that 10,000 cap is refused. Supports quoted phrases ("Red Cross"), required terms (+evanston), excluded terms (-dental). Data from ProPublica Nonprofit Explorer, sourced from IRS Form 990 filings.
| Name | Required | Description | Default |
|---|---|---|---|
| page | No | Zero-indexed page number. 25 results per page. Total pages is in num_pages. Increment to paginate large result sets. | |
| query | Yes | Keyword search string. Searched against org name, the secondary name line, and city in order of relevance. Supports: quoted phrases ("Red Cross"), required terms (+evanston), excluded terms (-dental). Empty string returns all orgs within the active filters. | |
| state | No | Two-letter US state, territory, or military postal code (e.g., "WA", "NY", "PR"). Case-insensitive — normalized to uppercase before filtering. A code outside that set is rejected rather than silently returning national results. Restricts results to orgs headquartered in that state. "ZZ" (foreign address) is accepted, but no organization in the index currently carries it. | |
| ntee_category | No | NTEE (National Taxonomy of Exempt Entities) major group integer (1–10). 1=Arts/Culture/Humanities, 2=Education, 3=Environment/Animals, 4=Health, 5=Human Services, 6=International/Foreign Affairs, 7=Public/Societal Benefit, 8=Religion Related, 9=Mutual/Membership Benefit, 10=Unknown/Unclassified. | |
| subsection_code | No | 501(c) subsection code. "3" = charitable/religious/educational organization (most common — includes both public charities and private foundations; nonprofit_get_organization returns foundation_type to tell them apart), "4" = social welfare org, "6" = business league/trade association, "92" = 4947(a)(1) nonexempt charitable trust. Filters by tax status, not sector. |
| Name | Required | Description |
|---|---|---|
| error | No | Present when the call failed. Absent on success. |
| notice | No | Present when the response needs a caveat the domain fields cannot carry: a page that returned no organizations (distinguishing a zero-match query from a page past the end of the result set, and naming the next call), a total_results sitting on the API result ceiling rather than counting matches, or both at once in one string. Absent when the page is populated and the total is an exact count. |
| cur_page | No | Current page (zero-indexed). |
| per_page | No | Results per page applied by the API (25). |
| num_pages | No | Total pages available (total_results / 25, ceiling). The last valid page is num_pages - 1. |
| data_source | No | ProPublica + IRS attribution text. |
| page_offset | No | Zero-indexed offset of the first result on this page. Requests are refused once this reaches 10,000. |
| organizations | No | Matching organizations for the current page. |
| total_results | No | Total matching orgs (up to 10,000 — the API ceiling). If 10000, actual count may be higher. |
| active_filters | No | Active filters echoed back for verification. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the readOnlyHint annotation, the description discloses significant behavioral traits: pagination at 25 per page, a 10,000 total-result cap with the meaning of total_results === 10000, the exact behavior for zero-match and past-last-page queries (empty array with notice rather than error), the specific cap refusal, supported search syntax (quoted phrases, + and -), and the data source. This is far more than annotations provide and is highly informative.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is dense but every sentence adds value. It is structured logically: purpose, return value and usage, pagination mechanics, edge-case behavior, search syntax, and data source. Nothing is redundant; the length is justified by the tool's complexity and the need to communicate all these caveats. Front-loading the core purpose and the return-value pointer to siblings is well done.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (filters, pagination, caps, error handling, search syntax), the description covers all essential aspects an agent needs to call it correctly. It also has an output schema for return values, so no need to explain them. There are no gaps for a reasonable agent to trip over.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Even though the schema descriptions cover 100% of parameters, the tool description adds valuable semantic context beyond them: it explains how pagination works (page and num_pages), clarifies the meaning of an empty query, and hints at the parameter roles in the search. It explicitly discusses the NTEE category and subsection codes while also providing a rationale for using them. This goes well beyond the baseline.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Search' and the resource '1.8M+ IRS-recognized tax-exempt organizations', specifying the search fields (name, keyword, city, phrase) and optional filters (state, NTEE sector, subsection code). It also distinguishes this tool from its siblings by stating that it returns EINs to be passed to nonprofit_get_organization or nonprofit_get_filings for details.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly instructs to use this tool for searching and then pass the resulting EINs to the two sibling tools for details, making the when-to-use clear. It also provides detailed pagination instructions (page and num_pages) and mentions that empty queries return all orgs within active filters, giving actionable guidance for actual usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
nonprofit_get_filings6 fields changedInput schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"Input schema / additionalPropertiesAdded value: +falseOutput schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"Output schema / anyOfAdded value: +[
+ {
+ "not": {
+ "required": [
+ "error"
+ ]
+ },
+ "required": [
+ "ein",
+ "name",
+ "filings",
+ "filings_pdf_only",
+ "total_filings_with_data",
+ "total_filings_pdf_only",
+ "data_source",
+ "propublica_url"
+ ]
+ },
+ {
+ "required": [
+ "error"
+ ]
+ }
+]Output schema / properties / errorAdded value: +{
+ "additionalProperties": {},
+ "description": "Present when the call failed. Absent on success.",
+ "properties": {
+ "code": {
+ "description": "JSON-RPC error code for this failure.",
+ "maximum": 9007199254740991,
+ "minimum": -9007199254740991,
+ "type": "integer"
+ },
+ "data": {
+ "additionalProperties": {},
+ "properties": {
+ "reason": {
+ "description": "Machine-readable failure mode. Declared by this tool: `not_found`: The EIN does not correspond to a known organization in the Nonprofit Explorer database `upstream_error`: ProPublica API returns a non-JSON body or network error Other values are possible when a failure originates below the handler.",
+ "examples": [
+ "not_found",
+ "upstream_error"
+ ],
+ "type": "string"
+ },
+ "recovery": {
+ "additionalProperties": {},
+ "description": "Actionable next step for the caller.",
+ "properties": {
+ "hint": {
+ "type": "string"
+ }
+ },
+ "required": [
+ "hint"
+ ],
+ "type": "object"
+ },
+ "retryable": {
+ "description": "Whether retrying may succeed.",
+ "type": "boolean"
+ }
+ },
+ "type": "object"
+ },
+ "message": {
+ "description": "Human-readable description of what went wrong.",
+ "type": "string"
+ }
+ },
+ "required": [
+ "code",
+ "message"
+ ],
+ "type": "object"
+}Output schema / requiredRemoved value: -[
- "ein",
- "name",
- "filings",
- "filings_pdf_only",
- "total_filings_with_data",
- "total_filings_pdf_only",
- "data_source",
- "propublica_url"
-]nonprofit_get_organization6 fields changedInput schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"Input schema / additionalPropertiesAdded value: +falseOutput schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"Output schema / anyOfAdded value: +[
+ {
+ "not": {
+ "required": [
+ "error"
+ ]
+ },
+ "required": [
+ "ein",
+ "strein",
+ "name",
+ "sort_name",
+ "address",
+ "city",
+ "state",
+ "zipcode",
+ "ntee_code",
+ "subsection_code",
+ "ruling_date",
+ "asset_amount",
+ "income_amount",
+ "revenue_amount",
+ "deductible",
+ "exempt_status",
+ "foundation_type",
+ "bmf_tax_period",
+ "latest_filing",
+ "filing_count",
+ "data_source",
+ "propublica_url"
+ ]
+ },
+ {
+ "required": [
+ "error"
+ ]
+ }
+]Output schema / properties / errorAdded value: +{
+ "additionalProperties": {},
+ "description": "Present when the call failed. Absent on success.",
+ "properties": {
+ "code": {
+ "description": "JSON-RPC error code for this failure.",
+ "maximum": 9007199254740991,
+ "minimum": -9007199254740991,
+ "type": "integer"
+ },
+ "data": {
+ "additionalProperties": {},
+ "properties": {
+ "reason": {
+ "description": "Machine-readable failure mode. Declared by this tool: `not_found`: The EIN does not correspond to a known organization in the Nonprofit Explorer database `upstream_error`: ProPublica API returns a non-JSON body (HTML 500) or network error Other values are possible when a failure originates below the handler.",
+ "examples": [
+ "not_found",
+ "upstream_error"
+ ],
+ "type": "string"
+ },
+ "recovery": {
+ "additionalProperties": {},
+ "description": "Actionable next step for the caller.",
+ "properties": {
+ "hint": {
+ "type": "string"
+ }
+ },
+ "required": [
+ "hint"
+ ],
+ "type": "object"
+ },
+ "retryable": {
+ "description": "Whether retrying may succeed.",
+ "type": "boolean"
+ }
+ },
+ "type": "object"
+ },
+ "message": {
+ "description": "Human-readable description of what went wrong.",
+ "type": "string"
+ }
+ },
+ "required": [
+ "code",
+ "message"
+ ],
+ "type": "object"
+}Output schema / requiredRemoved value: -[
- "ein",
- "strein",
- "name",
- "sort_name",
- "address",
- "city",
- "state",
- "zipcode",
- "ntee_code",
- "subsection_code",
- "ruling_date",
- "asset_amount",
- "income_amount",
- "revenue_amount",
- "deductible",
- "exempt_status",
- "foundation_type",
- "bmf_tax_period",
- "latest_filing",
- "filing_count",
- "data_source",
- "propublica_url"
-]nonprofit_search6 fields changedInput schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"Input schema / additionalPropertiesAdded value: +falseOutput schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"Output schema / anyOfAdded value: +[
+ {
+ "not": {
+ "required": [
+ "error"
+ ]
+ },
+ "required": [
+ "total_results",
+ "num_pages",
+ "cur_page",
+ "per_page",
+ "page_offset",
+ "organizations",
+ "active_filters",
+ "data_source"
+ ]
+ },
+ {
+ "required": [
+ "error"
+ ]
+ }
+]Output schema / properties / errorAdded value: +{
+ "additionalProperties": {},
+ "description": "Present when the call failed. Absent on success.",
+ "properties": {
+ "code": {
+ "description": "JSON-RPC error code for this failure.",
+ "maximum": 9007199254740991,
+ "minimum": -9007199254740991,
+ "type": "integer"
+ },
+ "data": {
+ "additionalProperties": {},
+ "properties": {
+ "reason": {
+ "description": "Machine-readable failure mode. Declared by this tool: `invalid_state`: The state filter is not a US state, territory, or military postal code (or ZZ for foreign entities) `pagination_ceiling`: The requested page is at or beyond ProPublica's 10,000-result offset ceiling `upstream_error`: ProPublica API returns a 500 or network error Other values are possible when a failure originates below the handler.",
+ "examples": [
+ "invalid_state",
+ "pagination_ceiling",
+ "upstream_error"
+ ],
+ "type": "string"
+ },
+ "recovery": {
+ "additionalProperties": {},
+ "description": "Actionable next step for the caller.",
+ "properties": {
+ "hint": {
+ "type": "string"
+ }
+ },
+ "required": [
+ "hint"
+ ],
+ "type": "object"
+ },
+ "retryable": {
+ "description": "Whether retrying may succeed.",
+ "type": "boolean"
+ }
+ },
+ "type": "object"
+ },
+ "message": {
+ "description": "Human-readable description of what went wrong.",
+ "type": "string"
+ }
+ },
+ "required": [
+ "code",
+ "message"
+ ],
+ "type": "object"
+}Output schema / requiredRemoved value: -[
- "total_results",
- "num_pages",
- "cur_page",
- "per_page",
- "page_offset",
- "organizations",
- "active_filters",
- "data_source"
-]nonprofit_get_filings5 fields changedOutput schema / properties / filings / items / properties / executive_compensation / additionalPropertiesAdded value: +falseOutput schema / properties / filings / items / properties / executive_compensation / anyOfRemoved value: -[
- {
- "additionalProperties": false,
- "properties": {
- "amount": {
- "anyOf": [
- {
- "type": "number"
- },
- {
- "type": "null"
- }
- ],
- "description": "Total executive compensation in USD. Null when not reported."
- },
- "field_name": {
- "description": "Source API field name for transparency (compnsatncurrofcr or compofficers).",
- "type": "string"
- },
- "form_type": {
- "description": "Form type this compensation field is sourced from.",
- "type": "string"
- },
- "note": {
- "description": "Plain-English description of what this field covers and where to find per-officer detail.",
- "type": "string"
- }
- },
- "required": [
- "amount",
- "field_name",
- "form_type",
- "note"
- ],
- "type": "object"
- },
- {
- "type": "null"
- }
-]Output schema / properties / filings / items / properties / executive_compensation / propertiesAdded value: +{
+ "amount": {
+ "anyOf": [
+ {
+ "type": "number"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "description": "Total executive compensation in USD. Null when not reported."
+ },
+ "field_name": {
+ "description": "Source API field the amount was read from — compnsatncurrofcr on 990 and 990-EZ, compofficers on 990-PF.",
+ "enum": [
+ "compnsatncurrofcr",
+ "compofficers"
+ ],
+ "type": "string"
+ },
+ "form_type": {
+ "description": "Form type this compensation field is sourced from.",
+ "enum": [
+ "990",
+ "990-EZ",
+ "990-PF"
+ ],
+ "type": "string"
+ },
+ "note": {
+ "description": "Plain-English description of what this field covers and where to find per-officer detail.",
+ "type": "string"
+ }
+}Output schema / properties / filings / items / properties / executive_compensation / requiredAdded value: +[
+ "amount",
+ "field_name",
+ "form_type",
+ "note"
+]Output schema / properties / filings / items / properties / executive_compensation / typeAdded value: +"object"nonprofit_get_filings3 fields changedOutput schema / properties / filings / items / properties / program_expense_ratio / anyOfPrevious value: -[
- {
- "additionalProperties": false,
- "properties": {
- "fundraising_expenses": {
- "anyOf": [
- {
- "type": "number"
- },
- {
- "type": "null"
- }
- ],
- "description": "Professional fundraising fees (profndraising) in USD. Null when not reported."
- },
- "management_compensation": {
- "anyOf": [
- {
- "type": "number"
- },
- {
- "type": "null"
- }
- ],
- "description": "Officer/director/trustee compensation (compnsatncurrofcr) in USD. Null when not reported."
- },
- "note": {
- "description": "Methodology note explaining the computation and its limitations.",
- "type": "string"
- },
- "other_salaries": {
- "anyOf": [
- {
- "type": "number"
- },
- {
- "type": "null"
- }
- ],
- "description": "Other salaries and wages (othrsalwages) in USD. Null when not reported."
- },
- "program_expenses": {
- "anyOf": [
- {
- "type": "number"
- },
- {
- "type": "null"
- }
- ],
- "description": "Computed program expenses (total − officer comp − other wages − fundraising) in USD."
- },
- "ratio": {
- "anyOf": [
- {
- "type": "number"
- },
- {
- "type": "null"
- }
- ],
- "description": "Program expense ratio as decimal 0.0–1.0. Null if inputs insufficient."
- },
- "total_expenses": {
- "anyOf": [
- {
- "type": "number"
- },
- {
- "type": "null"
- }
- ],
- "description": "Total functional expenses (denominator) in USD. From totfuncexpns."
- }
- },
- "required": [
- "ratio",
- "program_expenses",
- "total_expenses",
- "management_compensation",
- "other_salaries",
- "fundraising_expenses",
- "note"
- ],
- "type": "object"
- },
- {
- "type": "null"
- }
-]New value: +[
+ {
+ "additionalProperties": false,
+ "properties": {
+ "fundraising_expenses": {
+ "anyOf": [
+ {
+ "type": "number"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "description": "Professional fundraising fees (profndraising) in USD. Null when not reported."
+ },
+ "management_compensation": {
+ "anyOf": [
+ {
+ "type": "number"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "description": "Officer/director/trustee compensation (compnsatncurrofcr) in USD. Null when not reported."
+ },
+ "note": {
+ "description": "Methodology note naming the source of the functional allocation.",
+ "type": "string"
+ },
+ "other_salaries": {
+ "anyOf": [
+ {
+ "type": "number"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "description": "Other salaries and wages (othrsalwages) in USD. Null when not reported."
+ },
+ "program_expenses": {
+ "anyOf": [
+ {
+ "type": "number"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "description": "Program-service expenses in USD — Form 990 Part IX column (B), line 25."
+ },
+ "ratio": {
+ "anyOf": [
+ {
+ "type": "number"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "description": "Program-service expenses divided by total functional expenses, as a decimal 0.0–1.0. Always null against the current data source, which reports no program-service expense total."
+ },
+ "total_expenses": {
+ "anyOf": [
+ {
+ "type": "number"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "description": "Total functional expenses in USD — Form 990 Part IX column (A). From totfuncexpns."
+ }
+ },
+ "required": [
+ "ratio",
+ "program_expenses",
+ "total_expenses",
+ "management_compensation",
+ "other_salaries",
+ "fundraising_expenses",
+ "note"
+ ],
+ "type": "object"
+ },
+ {
+ "type": "null"
+ }
+]Output schema / properties / filings / items / properties / program_expense_ratio / descriptionPrevious value: -"Program-expense ratio with inputs. Null for 990-PF (different field set). Approximation — consult the source PDF for the full expense schedule."New value: +"Always null against the current data source. ProPublica returns no Form 990 Part IX column (B) program-service expense total, and the functional allocation across program, management, and fundraising cannot be reconstructed from the fields it does return. Read Part IX of the filing at pdf_url for the split."Output schema / properties / noticeAdded value: +{
+ "description": "Present when the organization resolved but Nonprofit Explorer holds no filing of any kind for it — names the org and why the filing history is empty. An empty filings array without this notice means the org has filings that carry a PDF but no extracted data; read filings_pdf_only.",
+ "type": "string"
+}nonprofit_get_organization10 fields changedOutput schema / properties / asset_amount / descriptionPrevious value: -"Most recent IRS BMF total assets in USD. Null when not reported."New value: +"Most recent IRS BMF total assets in USD. Null when not on record."Output schema / properties / bmf_tax_periodAdded value: +{
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "description": "Tax period of the latest return recorded in the IRS Business Master File (e.g. \"2025-06-01\"). Often more recent than latest_filing.tax_prd_yr, which reflects the newest 990 ProPublica has extracted. Null when not on record."
+}Output schema / properties / deductibleAdded value: +{
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "description": "Whether contributions to this org are tax-deductible, as \"<IRS code> — <meaning>\". Three states, not two: code 1 deductible, code 2 not deductible, code 4 deductible by treaty (foreign orgs). Null when the IRS Business Master File records no deductibility code."
+}Output schema / properties / exempt_statusAdded value: +{
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "description": "IRS exemption status as \"<IRS code> — <meaning>\"; code 1 is an unconditional exemption. This records what the IRS granted, not whether the exemption is still in force — the Business Master File is a lagging snapshot and automatic revocations are published separately. Null when the Business Master File records no status code."
+}Output schema / properties / foundation_typeAdded value: +{
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "description": "IRS foundation classification as \"<IRS code> — <meaning>\", separating public charities (codes 10–25) from private foundations (codes 2–4). Codes 0 (all organizations except 501(c)(3)) and 9 (suspense) fall outside both groups. Null when the IRS Business Master File records no foundation code."
+}Output schema / properties / income_amount / descriptionPrevious value: -"Most recent IRS BMF total income in USD. Null when not reported."New value: +"Most recent IRS BMF total income in USD. Null when not on record."Output schema / properties / revenue_amount / descriptionPrevious value: -"Most recent IRS BMF total revenue in USD. Null when not reported."New value: +"Most recent IRS BMF total revenue in USD. Null when not on record."Output schema / properties / sort_name / descriptionPrevious value: -"Alternate or subtitle name from the org record. Null when absent."New value: +"IRS Business Master File secondary name line (SORT_NAME) — an internal sort key such as a division or service-center label, not an alternate organization name. Null for most orgs."Output schema / properties / subsection_code / descriptionPrevious value: -"501(c) subsection number (e.g., 3 = public charity). Null when not classified."New value: +"501(c) subsection number (e.g., 3 = charitable organization, covering both public charities and private foundations — see foundation_type to tell them apart). Null when not classified."Output schema / requiredPrevious value: -[
- "ein",
- "strein",
- "name",
- "sort_name",
- "address",
- "city",
- "state",
- "zipcode",
- "ntee_code",
- "subsection_code",
- "ruling_date",
- "asset_amount",
- "income_amount",
- "revenue_amount",
- "latest_filing",
- "filing_count",
- "data_source",
- "propublica_url"
-]New value: +[
+ "ein",
+ "strein",
+ "name",
+ "sort_name",
+ "address",
+ "city",
+ "state",
+ "zipcode",
+ "ntee_code",
+ "subsection_code",
+ "ruling_date",
+ "asset_amount",
+ "income_amount",
+ "revenue_amount",
+ "deductible",
+ "exempt_status",
+ "foundation_type",
+ "bmf_tax_period",
+ "latest_filing",
+ "filing_count",
+ "data_source",
+ "propublica_url"
+]nonprofit_search5 fields changedInput schema / properties / query / descriptionPrevious value: -"Keyword search string. Searched against org name, alternate name, and city in order of relevance. Supports: quoted phrases (\"Red Cross\"), required terms (+evanston), excluded terms (-dental). Empty string returns all orgs within the active filters."New value: +"Keyword search string. Searched against org name, the secondary name line, and city in order of relevance. Supports: quoted phrases (\"Red Cross\"), required terms (+evanston), excluded terms (-dental). Empty string returns all orgs within the active filters."Input schema / properties / subsection_code / descriptionPrevious value: -"501(c) subsection code. \"3\" = public charity (most common — donations tax-deductible), \"4\" = social welfare org, \"6\" = business league/trade association, \"92\" = 4947(a)(1) nonexempt charitable trust. Filters by tax status, not sector."New value: +"501(c) subsection code. \"3\" = charitable/religious/educational organization (most common — includes both public charities and private foundations; nonprofit_get_organization returns foundation_type to tell them apart), \"4\" = social welfare org, \"6\" = business league/trade association, \"92\" = 4947(a)(1) nonexempt charitable trust. Filters by tax status, not sector."Output schema / properties / notice / descriptionPrevious value: -"Present when the page carried no organizations — distinguishes a zero-match query from a page past the end of the result set, and names the next call."New value: +"Present when the response needs a caveat the domain fields cannot carry: a page that returned no organizations (distinguishing a zero-match query from a page past the end of the result set, and naming the next call), a total_results sitting on the API result ceiling rather than counting matches, or both at once in one string. Absent when the page is populated and the total is an exact count."Output schema / properties / organizations / items / properties / sub_name / descriptionPrevious value: -"Alternate or subtitle name, or chapter identifier. Null when absent."New value: +"The legal name with the IRS Business Master File secondary name line appended — a division, service-center, or chapter identifier, not a separate trade name the org operates under. Null when the org has no secondary name line."Output schema / properties / organizations / items / properties / subseccd / descriptionPrevious value: -"501(c) subsection code (e.g., 3 = public charity). Null when not classified."New value: +"501(c) subsection code (e.g., 3 = charitable organization). Null when not classified."nonprofit_search6 fields changedInput schema / properties / state / descriptionPrevious value: -"Two-letter US state abbreviation (e.g., \"WA\", \"NY\"). Use \"ZZ\" for foreign entities. Restricts results to orgs headquartered in that state."New value: +"Two-letter US state, territory, or military postal code (e.g., \"WA\", \"NY\", \"PR\"). Case-insensitive — normalized to uppercase before filtering. A code outside that set is rejected rather than silently returning national results. Restricts results to orgs headquartered in that state. \"ZZ\" (foreign address) is accepted, but no organization in the index currently carries it."Output schema / properties / noticeAdded value: +{
+ "description": "Present when the page carried no organizations — distinguishes a zero-match query from a page past the end of the result set, and names the next call.",
+ "type": "string"
+}Output schema / properties / num_pages / descriptionPrevious value: -"Total pages available (total_results / 25, ceiling)."New value: +"Total pages available (total_results / 25, ceiling). The last valid page is num_pages - 1."Output schema / properties / page_offsetAdded value: +{
+ "description": "Zero-indexed offset of the first result on this page. Requests are refused once this reaches 10,000.",
+ "type": "number"
+}Output schema / properties / per_pageAdded value: +{
+ "description": "Results per page applied by the API (25).",
+ "type": "number"
+}Output schema / requiredPrevious value: -[
- "total_results",
- "num_pages",
- "cur_page",
- "organizations",
- "active_filters",
- "data_source"
-]New value: +[
+ "total_results",
+ "num_pages",
+ "cur_page",
+ "per_page",
+ "page_offset",
+ "organizations",
+ "active_filters",
+ "data_source"
+]nonprofit_get_filingsnonprofit_get_organizationnonprofit_searchProPublica Nonprofit MCP — ProPublica Nonprofit Explorer API (free, no auth)
Nonprofit lookup and IRS 990 filing data: revenue, assets, and compensation via ProPublica
MCP server for US nursing facility search and ownership lookup (NursingHomeDatabase).
Agent-native MCP server over 49M+ US public and government records, privacy-first, always current.
Add one secure layer between your agents and this server.
