Patchfirst is an MCP server published by co.patchfirst, hosted at patchfirst.co. When last checked on 2026-11-22 it was working: it answers and lists its tools. It declares 7 tools, including get_vulnerability, techniques_for_cve, cves_for_technique, list_exploited, list_feed.
Exploited CVEs ranked by what to patch first, with CISA KEV, EPSS and ATT&CK evidence.
1 connections through 4 shared values. Tap any node.
Full Patchfirst record for one CVE: description, CVSS, EPSS, CISA KEV status, the ATT&CK techniques attackers use with it (each with provenance badge, basis, evidence quotes and report links), threat reports that name it, and the priority score with its factors. Every field carries provenance and a source URL.
| Parameter | Type | Description |
|---|---|---|
| cve_id * | string | CVE id, e.g. "CVE-2024-3400" |
{
"name": "get_vulnerability",
"title": "Get vulnerability",
"description": "Full Patchfirst record for one CVE: description, CVSS, EPSS, CISA KEV status, the ATT&CK techniques attackers use with it (each with provenance badge, basis, evidence quotes and report links), threat reports that name it, and the priority score with its factors. Every field carries provenance and a source URL.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"cve_id"
],
"properties": {
"cve_id": {
"type": "string",
"description": "CVE id, e.g. \"CVE-2024-3400\""
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}None yet. Changes appear after a server's second daily check.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
Inferred from the host name and headers: what a server runs on, not who runs it.
What attackers do with a CVE: its MITRE ATT&CK techniques grouped by tactic in kill-chain order (Reconnaissance -> Impact). Each technique lists every supporting link with provenance badge, basis, evidence quote and report URL, strongest provenance first.
| Parameter | Type | Description |
|---|---|---|
| cve_id * | string | CVE id, e.g. "CVE-2023-4966" |
{
"name": "techniques_for_cve",
"title": "Techniques for CVE",
"description": "What attackers do with a CVE: its MITRE ATT&CK techniques grouped by tactic in kill-chain order (Reconnaissance -> Impact). Each technique lists every supporting link with provenance badge, basis, evidence quote and report URL, strongest provenance first.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"cve_id"
],
"properties": {
"cve_id": {
"type": "string",
"description": "CVE id, e.g. \"CVE-2023-4966\""
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Reverse ATT&CK lookup: which CVEs lead to a given technique, e.g. "which exploited CVEs give T1190 Exploit Public-Facing Application?". Sorted by Patchfirst priority. Parent ids include sub-techniques (T1059 matches T1059.004). Each hit shows the link's provenance badge and best evidence quote.
| Parameter | Type | Description |
|---|---|---|
| limit | integer | Max results, default 10, max 25. |
| kev_only | boolean | Only CVEs in CISA KEV (known exploited). Default false. |
| technique_id * | string | ATT&CK technique id, e.g. "T1190" or "T1059.004" |
| include_subtechniques | boolean | For a parent id, also match its sub-techniques. Default true. |
{
"name": "cves_for_technique",
"title": "CVEs for technique",
"description": "Reverse ATT&CK lookup: which CVEs lead to a given technique, e.g. \"which exploited CVEs give T1190 Exploit Public-Facing Application?\". Sorted by Patchfirst priority. Parent ids include sub-techniques (T1059 matches T1059.004). Each hit shows the link's provenance badge and best evidence quote.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"technique_id"
],
"properties": {
"limit": {
"type": "integer",
"maximum": 25,
"minimum": 1,
"description": "Max results, default 10, max 25."
},
"kev_only": {
"type": "boolean",
"description": "Only CVEs in CISA KEV (known exploited). Default false."
},
"technique_id": {
"type": "string",
"description": "ATT&CK technique id, e.g. \"T1190\" or \"T1059.004\""
},
"include_subtechniques": {
"type": "boolean",
"description": "For a parent id, also match its sub-techniques. Default true."
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Top known-exploited CVEs (CISA KEV) ranked by Patchfirst priority, optionally filtered to known ransomware use, an ATT&CK tactic (e.g. "initial-access", "Privilege Escalation", "TA0004") or a technique id. Each result lists its techniques with provenance badges.
| Parameter | Type | Description |
|---|---|---|
| limit | integer | Max results, default 10, max 25. |
| tactic | string | ATT&CK tactic id, name or TA id. One of: reconnaissance, resource-development, initial-access, execution, persistence, privilege-escalation, defense-evasion, stealth, defense-impairment, credential-access, discovery, lateral-movement, collection, command-and-control, exfiltration, impact |
| technique | string | ATT&CK technique id, e.g. "T1190"; parent ids include sub-techniques. |
| ransomware_only | boolean | Only KEV entries with known ransomware campaign use. |
{
"name": "list_exploited",
"title": "List exploited CVEs",
"description": "Top known-exploited CVEs (CISA KEV) ranked by Patchfirst priority, optionally filtered to known ransomware use, an ATT&CK tactic (e.g. \"initial-access\", \"Privilege Escalation\", \"TA0004\") or a technique id. Each result lists its techniques with provenance badges.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"limit": {
"type": "integer",
"maximum": 25,
"minimum": 1,
"description": "Max results, default 10, max 25."
},
"tactic": {
"type": "string",
"description": "ATT&CK tactic id, name or TA id. One of: reconnaissance, resource-development, initial-access, execution, persistence, privilege-escalation, defense-evasion, stealth, defense-impairment, credential-access, discovery, lateral-movement, collection, command-and-control, exfiltration, impact"
},
"technique": {
"type": "string",
"description": "ATT&CK technique id, e.g. \"T1190\"; parent ids include sub-techniques."
},
"ransomware_only": {
"type": "boolean",
"description": "Only KEV entries with known ransomware campaign use."
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Newest CVEs by published date, with KEV/EPSS/CVSS (source data) and priority. Complete for the last 30 days (every CVE published in that window is core tier); older dates list core-tier CVEs only. Filter by a since-date and minimum CVSS severity.
| Parameter | Type | Description |
|---|---|---|
| limit | integer | Max results, default 20, max 100. |
| since | string | Only CVEs published on/after this date (YYYY-MM-DD). |
| min_severity | string | Minimum CVSS base severity. |
{
"name": "list_feed",
"title": "Newest CVEs",
"description": "Newest CVEs by published date, with KEV/EPSS/CVSS (source data) and priority. Complete for the last 30 days (every CVE published in that window is core tier); older dates list core-tier CVEs only. Filter by a since-date and minimum CVSS severity.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"limit": {
"type": "integer",
"maximum": 100,
"minimum": 1,
"description": "Max results, default 20, max 100."
},
"since": {
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}",
"description": "Only CVEs published on/after this date (YYYY-MM-DD)."
},
"min_severity": {
"enum": [
"LOW",
"MEDIUM",
"HIGH",
"CRITICAL"
],
"type": "string",
"description": "Minimum CVSS base severity."
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Check a list of packages for known vulnerabilities via OSV.dev, then join with Patchfirst exploitation data (CISA KEV, EPSS, priority, ATT&CK techniques). Results are sorted exploited-first so you fix what attackers actually use. Ecosystems use OSV names: npm, PyPI, Maven, Go, crates.io, RubyGems, NuGet, Packagist, Debian, Alpine, etc.
| Parameter | Type | Description |
|---|---|---|
| packages * | array |
{
"name": "check_stack",
"title": "Check stack",
"description": "Check a list of packages for known vulnerabilities via OSV.dev, then join with Patchfirst exploitation data (CISA KEV, EPSS, priority, ATT&CK techniques). Results are sorted exploited-first so you fix what attackers actually use. Ecosystems use OSV names: npm, PyPI, Maven, Go, crates.io, RubyGems, NuGet, Packagist, Debian, Alpine, etc.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"packages"
],
"properties": {
"packages": {
"type": "array",
"items": {
"type": "object",
"required": [
"ecosystem",
"name"
],
"properties": {
"name": {
"type": "string",
"description": "Package name, e.g. \"lodash\" or \"org.apache.logging.log4j:log4j-core\""
},
"version": {
"type": "string",
"description": "Installed version. Omit to list all known vulns for the package."
},
"ecosystem": {
"type": "string",
"description": "OSV ecosystem, e.g. \"npm\", \"PyPI\", \"Maven\""
}
}
},
"maxItems": 100,
"minItems": 1
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}Search every published CVE (all tiers) by CVE id (full or partial, e.g. "CVE-2024-3400", "2024-34"), vendor, product or title words (e.g. "fortinet fortios", "confluence", "sql injection"). Ranked by match quality, then priority.
| Parameter | Type | Description |
|---|---|---|
| limit | integer | Max results, default 10. |
| query * | string | CVE id, vendor, product or title words |
{
"name": "search",
"title": "Search CVEs",
"description": "Search every published CVE (all tiers) by CVE id (full or partial, e.g. \"CVE-2024-3400\", \"2024-34\"), vendor, product or title words (e.g. \"fortinet fortios\", \"confluence\", \"sql injection\"). Ranked by match quality, then priority.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"query"
],
"properties": {
"limit": {
"type": "integer",
"maximum": 50,
"minimum": 1,
"description": "Max results, default 10."
},
"query": {
"type": "string",
"minLength": 1,
"description": "CVE id, vendor, product or title words"
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Patchfirst: CVE intelligence with the MITRE ATT&CK and evidence layer (what attackers do with a CVE, and which threat-report passage says so). Every claim carries a provenance badge. Respect it when you answer: - [Source data] (provenance "source"): copied from an authoritative feed (NVD, CVE.org, CISA KEV, FIRST EPSS, MITRE CTID mappings). Safe to state as fact, citing the feed. - [Machine-matched] ("machine"): keyword/pattern matching over threat-report text, or a dataset annotation on a passage in the same sentence as the CVE (~64% link precision). UNVERIFIED. Say "a report passage suggests..." / "machine-matched, unverified", never "attackers use X". - [AI-written] ("ai"): language-model summary; always shows the model. Do not present as sourced fact. - [Human-checked] ("human"): confirmed by a named Patchfirst reviewer. Never upgrade a badge. When a technique has several links, the strongest one is listed first; quote the evidence and link the report URL rather than paraphrasing. Priority (0-100) is computed by Patchfirst from source data, the order to patch in: 35 if in a KEV catalog (CISA or VulnCheck) + 10 for a KEV listing in the last 90 days (5 within a year) + 10 known ransomware use + 20 x EPSS percentile + up to 10 for threat-report mentions + 5 public exploit code + up to 3 for OTX pulses + 0.7 x CVSS, minus 15 for an end-of-life product (floor 0). Each result lists its factors; quote them rather than inventing a reason. Coverage: every published CVE has a record (search, get_vulnerability), but ATT&CK techniques and threat reports exist only for the "core" tier (KEV, report-named, high EPSS, recent critical). No technique link does not mean no exploitation. Quotes are short excerpts; follow the report URL for context. Which tool to use: - "What should I patch first?" / "what is being exploited?": list_exploited (filter by ransomware, tactic or technique). - One CVE in depth: get_vulnerability. Only its ATT&CK techniques: techniques_for_cve. - "Which CVEs give an attacker T1190?": cves_for_technique. - "Is my project affected?": check_stack with the packages and versions from a lockfile. - Newest CVEs since a date: list_feed. A product or vendor name, or a partial CVE id: search. Link the Patchfirst page (url field) when you cite a CVE. Data is rebuilt daily; a weekly digest of CISA KEV additions is at https://patchfirst.co/weekly/.
Names, descriptions and schemas were written by the server and are shown as data.