Skip to main content
Glama

cisa-cybersecurity-mcp-server

cisa_get_ssvc

cisa_get_ssvc
Read-onlyIdempotent

Fetch the SSVC decision points CISA publishes per CVE as a CVE Authorized Data Publisher — Exploitation, Automatable, and Technical Impact — along with the CVSS score and CWE CISA contributes where present, and compute the BOD 26-04 remediation timeline those values imply for the asset exposure you supply. The computed timeline applies CISA's published decision table to CISA's published decision points and your stated exposure; it is not a compliance determination and it is not CISA's own due-date assignment, which is reported separately when the CVE is in KEV and can differ. Not every CVE is enriched — a miss returns found false with guidance rather than an error. Call cisa_list_reference with topic ssvc_values for the decision-point vocabulary.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "cveIds": "<cveIds>"
    },
    "name": "cisa_get_ssvc"
  }
}

Input Schema

NameRequiredDescriptionDefault
cveIdsYesCVE identifiers to look up, up to 1,000 accepted and 50 processed per call. Oversized batches return normalized unprocessedIds for a follow-up call unless normalization is disabled. Each uncached CVE needs its own live enrichment lookup rather than a cached batch check.
assetExposureNoWhether the affected asset is reachable by unauthenticated or untrusted entities over public networks. The one BOD 26-04 decision point CISA cannot publish. "unknown" returns both arms so the spread is visible without guessing.unknown

Output Schema

NameRequiredDescriptionDefault
echoNoThe request as the server parsed it.
errorNoPresent when the call failed. Absent on success.
noticeNoGuidance when nothing was enriched, or when a decision timestamp predates KEV.
resultsNoOne result per processed CVE, in the order supplied.
foundCountNoHow many CVEs carry published SSVC decision points.
failedCountNoHow many processed CVE lookups failed; absence is unknown.
notFoundCountNoHow many processed CVEs have confirmed absence of SSVC decision points.
unprocessedIdsNoNormalized CVE IDs not processed; send these in a follow-up call.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedOutput schema / properties / results / items / properties / assignmentAgrees / description
      Previous value: -"Whether CISA's assigned day count and forensic-triage requirement both match the computed timeline. Present when both are available and an exposure was stated."New value: +"Whether CISA's assigned day count and forensic-triage requirement both match the computed timeline. Requires a comparable timeline, stated exposure, and a KEV entry citing BOD 26-04."
    • changedOutput schema / properties / results / items / properties / guidance / description
      Previous value: -"Guidance for a miss, a failed lookup, or unsupported decision points that prevent timeline computation."New value: +"Guidance for a miss, a failed lookup, unsupported decision points, or a KEV entry that does not cite BOD 26-04 when a comparison would otherwise apply."
  2. Changed5 schema fields changed
    • changedOutput schema / properties / results / items / properties / assignmentAgrees / description
      Previous value: -"Whether CISA's assigned deadline matches the computed timeline. Present only when the CVE is in KEV and an exposure was stated. Reported, never reconciled."New value: +"Whether CISA's assigned day count and forensic-triage requirement both match the computed timeline. Present when both are available and an exposure was stated."
    • changedOutput schema / properties / results / items / properties / automatable / description
      Previous value: -"The SSVC Automatable value (yes or no)."New value: +"The SSVC Automatable value (yes or no). Unsupported values are passed through verbatim."
    • changedOutput schema / properties / results / items / properties / bod2604 / description
      Previous value: -"The BOD 26-04 timeline implied by the published decision points."New value: +"The BOD 26-04 timeline implied by supported published decision points."
    • changedOutput schema / properties / results / items / properties / guidance / description
      Previous value: -"What to do instead, present on every result where found is false."New value: +"Guidance for a miss, a failed lookup, or unsupported decision points that prevent timeline computation."
    • changedOutput schema / properties / results / items / properties / technicalImpact / description
      Previous value: -"The SSVC Technical Impact value (partial or total)."New value: +"The SSVC Technical Impact value (partial or total). Unsupported values are passed through verbatim."
  3. Changed12 schema fields changed
    • changedInput schema / properties / cveIds / description
      Previous value: -"CVE identifiers to look up, up to 50 per call — lower than cisa_check_cve_status's 200-CVE cap because each CVE needs its own live enrichment lookup rather than a cached batch check."New value: +"CVE identifiers to look up, up to 1,000 accepted and 50 processed per call. Oversized batches return normalized unprocessedIds for a follow-up call unless normalization is disabled. Each uncached CVE needs its own live enrichment lookup rather than a cached batch check."
    • changedInput schema / properties / cveIds / maxItems
      Previous value: -50New value: +1000
    • changedOutput schema / anyOf
      Previous value: -[
      -  {
      -    "not": {
      -      "required": [
      -        "error"
      -      ]
      -    },
      -    "required": [
      -      "results",
      -      "foundCount",
      -      "notFoundCount",
      -      "echo"
      -    ]
      -  },
      -  {
      -    "required": [
      -      "error"
      -    ]
      -  }
      -]New value: +[
      +  {
      +    "not": {
      +      "required": [
      +        "error"
      +      ]
      +    },
      +    "required": [
      +      "results",
      +      "foundCount",
      +      "notFoundCount",
      +      "failedCount",
      +      "echo"
      +    ]
      +  },
      +  {
      +    "required": [
      +      "error"
      +    ]
      +  }
      +]
    • changedOutput schema / properties / error / properties / data / properties / reason / description
      Previous value: -"Machine-readable failure mode. Declared by this tool: `enrichment_source_unavailable`: Every per-CVE fetch failed with a transport or 5xx error. Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `read_limit_exceeded`: The batch exceeds the per-call cap and input normalization is disabled. `enrichment_source_unavailable`: Every processed per-CVE fetch failed, including rejected HTTP responses. Other values are possible when a failure originates below the handler."
    • changedOutput schema / properties / error / properties / data / properties / reason / examples
      Previous value: -[
      -  "enrichment_source_unavailable"
      -]New value: +[
      +  "read_limit_exceeded",
      +  "enrichment_source_unavailable"
      +]
    • addedOutput schema / properties / failedCount
      Added value: +{
      +  "description": "How many processed CVE lookups failed; absence is unknown.",
      +  "maximum": 9007199254740991,
      +  "minimum": -9007199254740991,
      +  "type": "integer"
      +}
    • changedOutput schema / properties / notFoundCount / description
      Previous value: -"How many CVEs do not."New value: +"How many processed CVEs have confirmed absence of SSVC decision points."
    • changedOutput schema / properties / results / description
      Previous value: -"One result per requested CVE, in the order supplied."New value: +"One result per processed CVE, in the order supplied."
    • changedOutput schema / properties / results / items / properties / found / description
      Previous value: -"Whether CISA has published SSVC decision points for this CVE."New value: +"Whether CISA has published SSVC decision points for this CVE; outcome explains a false value."
    • addedOutput schema / properties / results / items / properties / outcome
      Added value: +{
      +  "description": "The lookup outcome, distinguishing confirmed absence from fetch failure.",
      +  "enum": [
      +    "ssvc",
      +    "not_found",
      +    "no_cisa_container",
      +    "no_ssvc_metric",
      +    "fetch_failed"
      +  ],
      +  "type": "string"
      +}
    • changedOutput schema / properties / results / items / required
      Previous value: -[
      -  "cveId",
      -  "found",
      -  "cwes",
      -  "inKev",
      -  "sourceUrl"
      -]New value: +[
      +  "cveId",
      +  "found",
      +  "outcome",
      +  "cwes",
      +  "inKev",
      +  "sourceUrl"
      +]
    • addedOutput schema / properties / unprocessedIds
      Added value: +{
      +  "description": "Normalized CVE IDs not processed; send these in a follow-up call.",
      +  "items": {
      +    "pattern": "^CVE-[0-9]{4}-[0-9]{4,19}$",
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
  4. First observed

TDQS

A4.2/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint and idempotentHint, and the description adds genuinely useful context: the timeline is a computed value from a published decision table, not a compliance determination and not CISA's own due-date. However, it omits important disclosed behavior that the schema carries instead (50-per-call processing cap, normalized unprocessedIds, per-CVE live lookup), so the safety and batch semantics live largely in structured fields rather than the prose.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the primary action, and each sentence carries caveats that matter (computed vs. CISA-assigned, non-error misses, vocabulary lookup). It is dense and slightly repetitive in the phrase "CISA's published decision table to CISA's published decision points," but nothing is filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only enrichment tool with an output schema, every ambiguity an agent needs resolved is covered: what is returned, what the computed timeline does and does not mean, how misses surface, and where to find the vocabulary. Return-shape details are correctly delegated to the output schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3; the description goes slightly beyond by framing assetExposure as "the one BOD 26-04 decision point CISA cannot publish" and noting the unknown value returns both arms. That adds conceptual meaning to the parameter, though the mechanics of cveIds batching are left to the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (fetch) plus the exact resource (SSVC decision points CISA publishes per CVE) and enumerates the three decision points. It also names the secondary computation (BOD 26-04 remediation timeline) and distinguishes the value from KEV due-dates reported elsewhere, so an agent can separate it from cisa_search_kev without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives clear prerequisites and routing: call cisa_list_reference with topic ssvc_values to learn the decision-point vocabulary, and expect a found=false miss rather than an error for unenriched CVEs. It stops short of explicitly contrasting against cisa_check_cve_status, which also returns per-CVE status, leaving one plausible alternative unexplained.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.