Distributed Risk desk is an MCP server published by com.distributedrisk, hosted at www.distributedrisk.com. When last checked on 2026-11-22 it was working: it answers and lists its tools. It declares 16 tools, including list_notes, search_notes, get_note, search_screening_lists, list_ofac_actions.
Read the Distributed Risk desk notes and the official US record they cite.
665 connections through 4 shared values. Tap any node.
Inferred from the host name and headers: what a server runs on, not who runs it.
Published desk notes, newest first: entry number, date (the day of the official action), published (the day the desk published the note), title, status, topic (cyber or sanctions), readers, source class, a one-line summary, and the note's URL. Pages with limit and offset; total is the count that matches, next_offset the offset of the next page. Filter by topic or reader as on the desk page.
| Parameter | Type | Description |
|---|---|---|
| limit | integer | How many notes to return. |
| since | string | Only notes dated on or after this day (YYYY-MM-DD). |
| topic | string | cyber (exploited vulnerabilities, advisories, incident filings, the AI stack) or sanctions (everything else). |
| offset | integer | How many matching notes to skip, for the next page. |
| reader |
None yet. Changes appear after a server's second daily check.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
| string |
| Only notes written for this reader: sanctions-trade-finance-committee (Sanctions or trade-finance committee), owner-operating-executive (Owner or operating executive), platform-ai-stack-owner (Platform or AI-stack owner), deal-team (Deal team), credit-committee (Credit committee), cyber-underwriter … |
{
"name": "list_notes",
"title": "List desk notes",
"description": "Published desk notes, newest first: entry number, date (the day of the official action), published (the day the desk published the note), title, status, topic (cyber or sanctions), readers, source class, a one-line summary, and the note's URL. Pages with limit and offset; total is the count that matches, next_offset the offset of the next page. Filter by topic or reader as on the desk page.",
"inputSchema": {
"type": "object",
"properties": {
"limit": {
"type": "integer",
"default": 20,
"maximum": 100,
"minimum": 1,
"description": "How many notes to return."
},
"since": {
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$",
"description": "Only notes dated on or after this day (YYYY-MM-DD)."
},
"topic": {
"enum": [
"cyber",
"sanctions"
],
"type": "string",
"description": "cyber (exploited vulnerabilities, advisories, incident filings, the AI stack) or sanctions (everything else)."
},
"offset": {
"type": "integer",
"default": 0,
"maximum": 10000,
"minimum": 0,
"description": "How many matching notes to skip, for the next page."
},
"reader": {
"enum": [
"sanctions-trade-finance-committee",
"owner-operating-executive",
"platform-ai-stack-owner",
"deal-team",
"credit-committee",
"cyber-underwriter"
],
"type": "string",
"description": "Only notes written for this reader: sanctions-trade-finance-committee (Sanctions or trade-finance committee), owner-operating-executive (Owner or operating executive), platform-ai-stack-owner (Platform or AI-stack owner), deal-team (Deal team), credit-committee (Credit committee), cyber-underwriter (Cyber underwriter)."
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Find published notes that mention every word of the query (a name, a list, a country, a program, a date) in the title, summary, sources or body.
| Parameter | Type | Description |
|---|---|---|
| limit | integer | |
| query * | string | Words to find, for example "Venezuela general license". |
{
"name": "search_notes",
"title": "Search desk notes",
"description": "Find published notes that mention every word of the query (a name, a list, a country, a program, a date) in the title, summary, sources or body.",
"inputSchema": {
"type": "object",
"required": [
"query"
],
"properties": {
"limit": {
"type": "integer",
"default": 5,
"maximum": 20,
"minimum": 1
},
"query": {
"type": "string",
"maxLength": 200,
"minLength": 1,
"description": "Words to find, for example \"Venezuela general license\"."
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}One published note in full (Markdown), with its numbered sources and links to the official record.
| Parameter | Type | Description |
|---|---|---|
| slug * | string | The note's slug, from list_notes or search_notes. |
{
"name": "get_note",
"title": "Read a desk note",
"description": "One published note in full (Markdown), with its numbered sources and links to the official record.",
"inputSchema": {
"type": "object",
"required": [
"slug"
],
"properties": {
"slug": {
"type": "string",
"maxLength": 200,
"minLength": 1,
"description": "The note's slug, from list_notes or search_notes."
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Search the Consolidated Screening List (OFAC SDN and other Treasury lists; BIS Entity, Denied Persons, Unverified and Military End User lists; State ITAR-debarred and nonproliferation lists) by name, alias or identifier (IMO, SWIFT/BIC, registration number). Close spellings match. Each result gives the list, programs, addresses, IDs, remarks and the official list link; the answer says when each list last changed.
| Parameter | Type | Description |
|---|---|---|
| type | string | one of ["Individual","Entity","Vessel","Aircraft"] |
| limit | integer | |
| lists | array | Only these lists, for example ["SDN", "EL"]. |
| query * | string | A name (person, company, vessel, aircraft) or an identifier. |
| country | string | Only entries with an address in this country (two-letter code). |
| min_score | number | How close a name must be. 1 is exact; lower allows more spelling variation. |
{
"name": "search_screening_lists",
"title": "Search the US screening lists",
"description": "Search the Consolidated Screening List (OFAC SDN and other Treasury lists; BIS Entity, Denied Persons, Unverified and Military End User lists; State ITAR-debarred and nonproliferation lists) by name, alias or identifier (IMO, SWIFT/BIC, registration number). Close spellings match. Each result gives the list, programs, addresses, IDs, remarks and the official list link; the answer says when each list last changed.",
"inputSchema": {
"type": "object",
"required": [
"query"
],
"properties": {
"type": {
"enum": [
"Individual",
"Entity",
"Vessel",
"Aircraft"
],
"type": "string"
},
"limit": {
"type": "integer",
"default": 10,
"maximum": 25,
"minimum": 1
},
"lists": {
"type": "array",
"items": {
"enum": [
"SDN",
"SSI",
"FSE",
"NS-MBS",
"CMIC",
"PLC",
"CAP",
"EL",
"DPL",
"UVL",
"MEU",
"DTC",
"ISN"
],
"type": "string"
},
"description": "Only these lists, for example [\"SDN\", \"EL\"]."
},
"query": {
"type": "string",
"maxLength": 200,
"minLength": 2,
"description": "A name (person, company, vessel, aircraft) or an identifier."
},
"country": {
"type": "string",
"pattern": "^[A-Za-z]{2}$",
"description": "Only entries with an address in this country (two-letter code)."
},
"min_score": {
"type": "number",
"default": 0.9,
"maximum": 1,
"minimum": 0.88,
"description": "How close a name must be. 1 is exact; lower allows more spelling variation."
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}OFAC's recent actions, newest first: designations and removals, general licenses, FAQs, regulations and settlements, each with its date, categories and the official page. Filter by date or words in the title.
| Parameter | Type | Description |
|---|---|---|
| limit | integer | |
| query | string | Words in the title or category, for example "Iran general license". |
| since | string | Only actions on or after this day (YYYY-MM-DD). Reaches back about 30 actions. |
{
"name": "list_ofac_actions",
"title": "OFAC recent actions",
"description": "OFAC's recent actions, newest first: designations and removals, general licenses, FAQs, regulations and settlements, each with its date, categories and the official page. Filter by date or words in the title.",
"inputSchema": {
"type": "object",
"properties": {
"limit": {
"type": "integer",
"default": 10,
"maximum": 30,
"minimum": 1
},
"query": {
"type": "string",
"maxLength": 200,
"description": "Words in the title or category, for example \"Iran general license\"."
},
"since": {
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$",
"description": "Only actions on or after this day (YYYY-MM-DD). Reaches back about 30 actions."
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}CISA's Known Exploited Vulnerabilities catalog, newest first: CVE, vendor, product, date added, federal due date, known ransomware use, the required action, FIRST's EPSS estimate, and whether it sits in the AI and agent software stack. Look up one CVE, search vendor or product words, list what was added since a date, or only the AI stack. For one CVE in full, use get_cve.
| Parameter | Type | Description |
|---|---|---|
| cve | string | One CVE, for example CVE-2025-62593. |
| limit | integer | |
| query | string | Vendor, product or vulnerability words, for example "fortinet fortios". |
| since | string | Only entries added on or after this day (YYYY-MM-DD). |
| ai_stack | boolean | true: only AI and agent software (agent frameworks, MCP, model serving, ML platforms, GPU infrastructure, AI assistants). |
| ransomware | boolean | true: only entries CISA marks as used in ransomware campaigns. |
{
"name": "search_kev",
"title": "Search CISA's KEV catalog",
"description": "CISA's Known Exploited Vulnerabilities catalog, newest first: CVE, vendor, product, date added, federal due date, known ransomware use, the required action, FIRST's EPSS estimate, and whether it sits in the AI and agent software stack. Look up one CVE, search vendor or product words, list what was added since a date, or only the AI stack. For one CVE in full, use get_cve.",
"inputSchema": {
"type": "object",
"properties": {
"cve": {
"type": "string",
"pattern": "^[Cc][Vv][Ee]-\\d{4}-\\d{4,}$",
"description": "One CVE, for example CVE-2025-62593."
},
"limit": {
"type": "integer",
"default": 10,
"maximum": 50,
"minimum": 1
},
"query": {
"type": "string",
"maxLength": 200,
"description": "Vendor, product or vulnerability words, for example \"fortinet fortios\"."
},
"since": {
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$",
"description": "Only entries added on or after this day (YYYY-MM-DD)."
},
"ai_stack": {
"type": "boolean",
"description": "true: only AI and agent software (agent frameworks, MCP, model serving, ML platforms, GPU infrastructure, AI assistants)."
},
"ransomware": {
"type": "boolean",
"description": "true: only entries CISA marks as used in ransomware campaigns."
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}Search Federal Register rules, proposed rules, notices and presidential documents: title, type, agencies, publication and effective dates, citation, abstract and the official document link. Narrow by agency (for example foreign-assets-control-office, industry-and-security-bureau, state-department), type or date.
| Parameter | Type | Description |
|---|---|---|
| term * | string | Words to find, for example "entity list additions". |
| type | string | RULE, PRORULE (proposed rule), NOTICE or PRESDOCU (presidential document). |
| limit | integer | |
| order | string | one of ["newest","relevance"] |
| since | string | Only documents published on or after this day (YYYY-MM-DD). |
| agency | string | Federal Register agency slug, for example foreign-assets-control-office, treasury-department, industry-and-security-bureau, state-department, homeland-security-department. |
{
"name": "search_federal_register",
"title": "Search the Federal Register",
"description": "Search Federal Register rules, proposed rules, notices and presidential documents: title, type, agencies, publication and effective dates, citation, abstract and the official document link. Narrow by agency (for example foreign-assets-control-office, industry-and-security-bureau, state-department), type or date.",
"inputSchema": {
"type": "object",
"required": [
"term"
],
"properties": {
"term": {
"type": "string",
"maxLength": 200,
"minLength": 2,
"description": "Words to find, for example \"entity list additions\"."
},
"type": {
"enum": [
"RULE",
"PRORULE",
"NOTICE",
"PRESDOCU"
],
"type": "string",
"description": "RULE, PRORULE (proposed rule), NOTICE or PRESDOCU (presidential document)."
},
"limit": {
"type": "integer",
"default": 5,
"maximum": 20,
"minimum": 1
},
"order": {
"enum": [
"newest",
"relevance"
],
"type": "string",
"default": "newest"
},
"since": {
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$",
"description": "Only documents published on or after this day (YYYY-MM-DD)."
},
"agency": {
"type": "string",
"pattern": "^[a-z0-9-]+$",
"description": "Federal Register agency slug, for example foreign-assets-control-office, treasury-department, industry-and-security-bureau, state-department, homeland-security-department."
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}US State Department travel advisories, most recently updated first: country, level (1 to 4), the advisory's summary and the official page. Filter by country, minimum level or update date.
| Parameter | Type | Description |
|---|---|---|
| limit | integer | |
| since | string | Only advisories updated on or after this day (YYYY-MM-DD). |
| country | string | A country name, or State's two-letter code. |
| min_level | integer | Only advisories at this level or higher (4 is Do Not Travel). |
{
"name": "list_travel_advisories",
"title": "State travel advisories",
"description": "US State Department travel advisories, most recently updated first: country, level (1 to 4), the advisory's summary and the official page. Filter by country, minimum level or update date.",
"inputSchema": {
"type": "object",
"properties": {
"limit": {
"type": "integer",
"default": 10,
"maximum": 50,
"minimum": 1
},
"since": {
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$",
"description": "Only advisories updated on or after this day (YYYY-MM-DD)."
},
"country": {
"type": "string",
"maxLength": 80,
"minLength": 2,
"description": "A country name, or State's two-letter code."
},
"min_level": {
"type": "integer",
"maximum": 4,
"minimum": 1,
"description": "Only advisories at this level or higher (4 is Do Not Travel)."
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}The New York Fed's reference rates: EFFR and OBFR (unsecured), SOFR, BGCR and TGCR (secured), and the SOFR averages and index (SOFRAI). With no rate, the latest of each; with a rate, its last N days, with percentiles, volume and, for EFFR, the target range.
| Parameter | Type | Description |
|---|---|---|
| last | integer | How many days of history, when a rate is given. |
| rate | string | One rate, for its history. Omit for the latest of all. |
{
"name": "get_reference_rates",
"title": "New York Fed reference rates",
"description": "The New York Fed's reference rates: EFFR and OBFR (unsecured), SOFR, BGCR and TGCR (secured), and the SOFR averages and index (SOFRAI). With no rate, the latest of each; with a rate, its last N days, with percentiles, volume and, for EFFR, the target range.",
"inputSchema": {
"type": "object",
"properties": {
"last": {
"type": "integer",
"default": 5,
"maximum": 60,
"minimum": 1,
"description": "How many days of history, when a rate is given."
},
"rate": {
"enum": [
"EFFR",
"OBFR",
"SOFR",
"BGCR",
"TGCR",
"SOFRAI"
],
"type": "string",
"description": "One rate, for its history. Omit for the latest of all."
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}Treasury's daily par yield curve, newest first: yields by tenor from 1 month to 30 years. Ask for the last N days, and optionally only some tenors (for example ["2 Yr", "10 Yr"]).
| Parameter | Type | Description |
|---|---|---|
| last | integer | How many business days. |
| tenors | array | Tenors as Treasury names them: 1 Mo, 3 Mo, 6 Mo, 1 Yr, 2 Yr, 5 Yr, 10 Yr, 30 Yr… |
{
"name": "get_treasury_yields",
"title": "Treasury par yield curve",
"description": "Treasury's daily par yield curve, newest first: yields by tenor from 1 month to 30 years. Ask for the last N days, and optionally only some tenors (for example [\"2 Yr\", \"10 Yr\"]).",
"inputSchema": {
"type": "object",
"properties": {
"last": {
"type": "integer",
"default": 1,
"maximum": 30,
"minimum": 1,
"description": "How many business days."
},
"tenors": {
"type": "array",
"items": {
"type": "string",
"maxLength": 12
},
"maxItems": 16,
"description": "Tenors as Treasury names them: 1 Mo, 3 Mo, 6 Mo, 1 Yr, 2 Yr, 5 Yr, 10 Yr, 30 Yr…"
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}Everything the record says about one CVE, in one answer: the CVE.org record (description, severity, weakness, affected products, references), CISA's exploitation call (SSVC) and its KEV listing with the federal due date, FIRST's EPSS estimate, and whether it sits in the AI and agent software stack.
| Parameter | Type | Description |
|---|---|---|
| cve * | string | For example CVE-2025-62593. |
{
"name": "get_cve",
"title": "One CVE, in full",
"description": "Everything the record says about one CVE, in one answer: the CVE.org record (description, severity, weakness, affected products, references), CISA's exploitation call (SSVC) and its KEV listing with the federal due date, FIRST's EPSS estimate, and whether it sits in the AI and agent software stack.",
"inputSchema": {
"type": "object",
"required": [
"cve"
],
"properties": {
"cve": {
"type": "string",
"pattern": "^[Cc][Vv][Ee]-\\d{4}-\\d{4,}$",
"description": "For example CVE-2025-62593."
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}CISA's advisories, newest first: alerts, joint cybersecurity advisories (#StopRansomware, state-sponsored activity), ICS and ICS-medical advisories, and analysis reports. Each with its kind, date, summary, the CVEs it names and the official page. Filter by kind, date, words, or the AI stack.
| Parameter | Type | Description |
|---|---|---|
| kind | string | One kind. Asking for one kind reads that kind's own feed, which reaches further back. |
| limit | integer | |
| query | string | Words in the title, summary or CVEs, for example "ransomware" or "Siemens". |
| since | string | Only advisories published on or after this day (YYYY-MM-DD). |
| ai_stack | boolean | true: only advisories that name AI or agent software. |
{
"name": "list_cyber_advisories",
"title": "CISA cybersecurity advisories",
"description": "CISA's advisories, newest first: alerts, joint cybersecurity advisories (#StopRansomware, state-sponsored activity), ICS and ICS-medical advisories, and analysis reports. Each with its kind, date, summary, the CVEs it names and the official page. Filter by kind, date, words, or the AI stack.",
"inputSchema": {
"type": "object",
"properties": {
"kind": {
"enum": [
"alert",
"cybersecurity_advisory",
"ics_advisory",
"ics_medical_advisory",
"analysis_report"
],
"type": "string",
"description": "One kind. Asking for one kind reads that kind's own feed, which reaches further back."
},
"limit": {
"type": "integer",
"default": 10,
"maximum": 40,
"minimum": 1
},
"query": {
"type": "string",
"maxLength": 200,
"description": "Words in the title, summary or CVEs, for example \"ransomware\" or \"Siemens\"."
},
"since": {
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$",
"description": "Only advisories published on or after this day (YYYY-MM-DD)."
},
"ai_stack": {
"type": "boolean",
"description": "true: only advisories that name AI or agent software."
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}Cybersecurity incidents public companies report on Form 8-K, newest first: Item 1.05 (the company judged it material) and, unless excluded, Item 8.01 reports made without that judgment. Each with the company, tickers, filing and event dates, items, state, industry code and the EDGAR filing.
| Parameter | Type | Description |
|---|---|---|
| limit | integer | |
| query | string | Company name, ticker, CIK or state. |
| since | string | Filed on or after this day (YYYY-MM-DD). Default 90 days ago; Item 1.05 began 2023-12-18. |
| until | string | Filed on or before this day. Default today. |
| material_only | boolean | true: only Item 1.05 filings. |
{
"name": "list_cyber_incident_filings",
"title": "Cyber incidents reported to the SEC",
"description": "Cybersecurity incidents public companies report on Form 8-K, newest first: Item 1.05 (the company judged it material) and, unless excluded, Item 8.01 reports made without that judgment. Each with the company, tickers, filing and event dates, items, state, industry code and the EDGAR filing.",
"inputSchema": {
"type": "object",
"properties": {
"limit": {
"type": "integer",
"default": 10,
"maximum": 40,
"minimum": 1
},
"query": {
"type": "string",
"maxLength": 200,
"description": "Company name, ticker, CIK or state."
},
"since": {
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$",
"description": "Filed on or after this day (YYYY-MM-DD). Default 90 days ago; Item 1.05 began 2023-12-18."
},
"until": {
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$",
"description": "Filed on or before this day. Default today."
},
"material_only": {
"type": "boolean",
"default": false,
"description": "true: only Item 1.05 filings."
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}New advisories against the software AI agents run on, newest and most severe first: agent frameworks (LangChain, LlamaIndex, CrewAI, n8n, Langflow), LLM gateways (LiteLLM), MCP servers and SDKs, model serving (vLLM, Ollama), ML platforms (MLflow, Ray, Jupyter), model libraries, AI apps and coding agents. Malicious-package reports (a compromised or lookalike release) come first. CISA KEV entries in the same stack are included. Each with package, severity, fixed versions, CVEs, EPSS and the advisory.
| Parameter | Type | Description |
|---|---|---|
| kind | string | one of ["malicious_package","vulnerability"] |
| layer | string | One layer of the stack. |
| limit | integer | |
| since | string | Advisories dated on or after this day (YYYY-MM-DD). Default 14 days ago; reaches back 30 days. |
| package | string | One package name, for example litellm or @modelcontextprotocol/sdk. |
| include_kev | boolean | Include CISA KEV entries for AI-stack products added in the window. |
{
"name": "list_ai_stack_vulnerabilities",
"title": "AI and agent stack: new advisories",
"description": "New advisories against the software AI agents run on, newest and most severe first: agent frameworks (LangChain, LlamaIndex, CrewAI, n8n, Langflow), LLM gateways (LiteLLM), MCP servers and SDKs, model serving (vLLM, Ollama), ML platforms (MLflow, Ray, Jupyter), model libraries, AI apps and coding agents. Malicious-package reports (a compromised or lookalike release) come first. CISA KEV entries in the same stack are included. Each with package, severity, fixed versions, CVEs, EPSS and the advisory.",
"inputSchema": {
"type": "object",
"properties": {
"kind": {
"enum": [
"malicious_package",
"vulnerability"
],
"type": "string"
},
"layer": {
"enum": [
"agent_framework",
"llm_gateway",
"mcp",
"model_serving",
"ml_platform",
"model_library",
"ai_app",
"coding_agent",
"gpu_infra",
"ai_assistant",
"ai_systems"
],
"type": "string",
"description": "One layer of the stack."
},
"limit": {
"type": "integer",
"default": 15,
"maximum": 50,
"minimum": 1
},
"since": {
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$",
"description": "Advisories dated on or after this day (YYYY-MM-DD). Default 14 days ago; reaches back 30 days."
},
"package": {
"type": "string",
"maxLength": 120,
"description": "One package name, for example litellm or @modelcontextprotocol/sdk."
},
"include_kev": {
"type": "boolean",
"default": true,
"description": "Include CISA KEV entries for AI-stack products added in the window."
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}Which of these package versions have a known vulnerability. Give packages directly (ecosystem, name, version), or paste a lockfile or SBOM as manifest and it is read for you: package-lock.json, pnpm-lock.yaml, yarn.lock, requirements.txt, poetry.lock, Pipfile.lock, go.mod, go.sum, Cargo.lock, Gemfile.lock, composer.lock, packages.lock.json, gradle.lockfile, cyclonedx, spdx, purls. Each version is checked against OSV.dev, which aggregates GitHub's reviewed advisories, the Go and PyPI databases, RustSec and OpenSSF's malicious-package reports across npm, PyPI, Go, Maven, crates.io, NuGet, RubyGems, Packagist and more. Every hit comes back with its severity, the CVEs it is known by, the versions that fix it, whether CISA lists it as exploited with the federal due date, and FIRST's EPSS estimate. Exploited packages come first, then malicious packages, then severity. A version with no hit is a version no advisory in those databases covers; that is not a statement that it is safe. Only resolved versions are read: a file of ranges (package.json, Pipfile, pom.xml) cannot be checked, so pass the lockfile beside it.
| Parameter | Type | Description |
|---|---|---|
| limit | integer | How many affected packages to return. The counts cover all of them. |
| filename | string | The manifest's filename, when you have it. Without it the format is read from the content. |
| kev_only | boolean | true: only advisories CISA lists as exploited. |
| manifest | string | The contents of a lockfile or SBOM. Use this or packages. |
| packages | array | The packages to check, as installed. Use this or manifest. |
| severity_min | string | Only this severity and above. Malicious packages and anything CISA lists as exploited are always returned. |
{
"name": "check_dependencies",
"title": "Check dependencies against the vulnerability record",
"description": "Which of these package versions have a known vulnerability. Give packages directly (ecosystem, name, version), or paste a lockfile or SBOM as manifest and it is read for you: package-lock.json, pnpm-lock.yaml, yarn.lock, requirements.txt, poetry.lock, Pipfile.lock, go.mod, go.sum, Cargo.lock, Gemfile.lock, composer.lock, packages.lock.json, gradle.lockfile, cyclonedx, spdx, purls. Each version is checked against OSV.dev, which aggregates GitHub's reviewed advisories, the Go and PyPI databases, RustSec and OpenSSF's malicious-package reports across npm, PyPI, Go, Maven, crates.io, NuGet, RubyGems, Packagist and more. Every hit comes back with its severity, the CVEs it is known by, the versions that fix it, whether CISA lists it as exploited with the federal due date, and FIRST's EPSS estimate. Exploited packages come first, then malicious packages, then severity. A version with no hit is a version no advisory in those databases covers; that is not a statement that it is safe. Only resolved versions are read: a file of ranges (package.json, Pipfile, pom.xml) cannot be checked, so pass the lockfile beside it.",
"inputSchema": {
"type": "object",
"properties": {
"limit": {
"type": "integer",
"default": 40,
"maximum": 100,
"minimum": 1,
"description": "How many affected packages to return. The counts cover all of them."
},
"filename": {
"type": "string",
"maxLength": 200,
"description": "The manifest's filename, when you have it. Without it the format is read from the content."
},
"kev_only": {
"type": "boolean",
"default": false,
"description": "true: only advisories CISA lists as exploited."
},
"manifest": {
"type": "string",
"maxLength": 1000000,
"description": "The contents of a lockfile or SBOM. Use this or packages."
},
"packages": {
"type": "array",
"items": {
"type": "object",
"required": [
"ecosystem",
"name",
"version"
],
"properties": {
"name": {
"type": "string",
"maxLength": 220,
"minLength": 1,
"description": "The package name: lodash, requests, github.com/gin-gonic/gin, org.apache.logging.log4j:log4j-core."
},
"version": {
"type": "string",
"maxLength": 80,
"minLength": 1,
"description": "The exact installed version, not a range."
},
"ecosystem": {
"enum": [
"CRAN",
"GitHub Actions",
"Go",
"Hackage",
"Hex",
"Maven",
"NuGet",
"Packagist",
"Pub",
"PyPI",
"RubyGems",
"SwiftURL",
"crates.io",
"npm"
],
"type": "string",
"description": "The ecosystem, as OSV names it."
}
},
"additionalProperties": false
},
"maxItems": 600,
"description": "The packages to check, as installed. Use this or manifest."
},
"severity_min": {
"enum": [
"low",
"moderate",
"high",
"critical"
],
"type": "string",
"description": "Only this severity and above. Malicious packages and anything CISA lists as exploited are always returned."
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}What is new across the three vulnerability feeds, exploited first, then by severity, then newest: GitHub's reviewed advisories (the affected package range and the first patched version), NVD's newly published CVE records (software no package ecosystem carries, with NIST's scoring), and the CVEs CISA added to its Known Exploited Vulnerabilities catalog. A KEV addition keeps its own date: it is CISA saying this one is being exploited now, often long after the CVE was published. A CVE that GitHub and NVD both published in the window appears once, from GitHub. For CISA's alerts and joint advisories rather than vulnerabilities, use list_cyber_advisories.
| Parameter | Type | Description |
|---|---|---|
| limit | integer | |
| query | string | Words to find: NVD searches its records, GitHub and KEV entries are matched on summary, package, vendor and product. |
| since | string | Dated on or after this day (YYYY-MM-DD). Default 7 days ago. |
| until | string | Dated on or before this day. Default today. |
| source | array | Which feeds to read. Default all three. A source that cannot honour a filter is skipped and named in the answer. |
| ai_stack | boolean | true: only entries that name AI or agent software. false: only entries that do not. |
| severity | string | This severity band only. GitHub and NVD; KEV, which does not rate severity, is skipped when it is set. |
| ecosystem | string | One package ecosystem, as GitHub names it. GitHub only; NVD and KEV are skipped when it is set. |
{
"name": "list_new_vulnerabilities",
"title": "New vulnerabilities: GitHub, NVD and CISA KEV",
"description": "What is new across the three vulnerability feeds, exploited first, then by severity, then newest: GitHub's reviewed advisories (the affected package range and the first patched version), NVD's newly published CVE records (software no package ecosystem carries, with NIST's scoring), and the CVEs CISA added to its Known Exploited Vulnerabilities catalog. A KEV addition keeps its own date: it is CISA saying this one is being exploited now, often long after the CVE was published. A CVE that GitHub and NVD both published in the window appears once, from GitHub. For CISA's alerts and joint advisories rather than vulnerabilities, use list_cyber_advisories.",
"inputSchema": {
"type": "object",
"properties": {
"limit": {
"type": "integer",
"default": 15,
"maximum": 50,
"minimum": 1
},
"query": {
"type": "string",
"maxLength": 200,
"description": "Words to find: NVD searches its records, GitHub and KEV entries are matched on summary, package, vendor and product."
},
"since": {
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$",
"description": "Dated on or after this day (YYYY-MM-DD). Default 7 days ago."
},
"until": {
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$",
"description": "Dated on or before this day. Default today."
},
"source": {
"type": "array",
"items": {
"enum": [
"github",
"nvd",
"cisa_kev"
],
"type": "string"
},
"description": "Which feeds to read. Default all three. A source that cannot honour a filter is skipped and named in the answer."
},
"ai_stack": {
"type": "boolean",
"description": "true: only entries that name AI or agent software. false: only entries that do not."
},
"severity": {
"enum": [
"low",
"medium",
"high",
"critical"
],
"type": "string",
"description": "This severity band only. GitHub and NVD; KEV, which does not rate severity, is skipped when it is set."
},
"ecosystem": {
"enum": [
"actions",
"composer",
"erlang",
"go",
"maven",
"npm",
"nuget",
"other",
"pip",
"pub",
"rubygems",
"rust",
"swift"
],
"type": "string",
"description": "One package ecosystem, as GitHub names it. GitHub only; NVD and KEV are skipped when it is set."
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}Read-only access to the Distributed Risk public desk and the official US record behind it. Desk notes are short reads on official actions (designations, general licenses, advisories, dates that turn), each citing the record and naming the readers it is for: list_notes for what is current (a page at a time, by topic or reader), search_notes to find a name, list, country or date, get_note for one note with its sources. The official record, read from the government sources directly: search_screening_lists (OFAC, BIS and State screening lists), list_ofac_actions, search_kev (CISA Known Exploited Vulnerabilities), search_federal_register, list_travel_advisories, get_reference_rates (New York Fed EFFR, SOFR and related rates) and get_treasury_yields (Treasury par yield curve). Each answer links the source and says when it was read. Cyber: get_cve (one CVE in full: the CVE.org record, CISA's exploitation call and KEV listing, FIRST's EPSS estimate), list_cyber_advisories (CISA alerts, joint advisories, ICS advisories), list_cyber_incident_filings (incidents public companies report to the SEC on Form 8-K) and list_ai_stack_vulnerabilities (new advisories and malicious-package reports against agent frameworks, LLM gateways, MCP, model serving and ML platforms). Dependencies: check_dependencies takes the packages a codebase installs — as a list, or as a lockfile or SBOM pasted whole — and returns every advisory OSV.dev holds against those exact versions, with the fixing version, CISA's exploitation listing and the EPSS estimate. list_new_vulnerabilities is what is new across GitHub's reviewed advisories, NVD's CVE feed and CISA's KEV additions, exploited first. EPSS is a model estimate, and OSV.dev, the GitHub Advisory Database and NVD are the vulnerability record rather than government action; all are labeled where they appear. A version no advisory covers is not a version shown to be safe. A list match is a lead to check against the official entry, not a determination; no match is not a clearance. Decision support from official public sources. Not a legal determination of sanctions, travel, or cyber status. Readers own their compliance obligations.
Names, descriptions and schemas were written by the server and are shown as data.
Shared addresses on big platforms (Cloudflare, Vercel and the like) put unrelated servers together; those are marked shared_infrastructure. A match is a pivot, not a link between operators.