Skip to main content
Glama

Server Details

ZEN SecDB MCP server for CVE intelligence, CVSS/EPSS scoring, advisories, SSVC, and package audits.

If you are the author of this connector, you can claim ownership. Claimed connector authors can inspect health checks, view analytics, and manage their listing.
Status
Healthy
Uptime
78.3% over the last 24 hours
Last Tested
Transport
Streamable HTTP · MCP 2025-11-25
URL
ChatGPT
–
Claude
–

TDQS

A4.4/5.0

Scored across 23 tools

Disambiguation4/5

Tools are largely distinct by resource and action, and descriptions explicitly cross-reference siblings (e.g. use kev_check vs kev_list, purl_audit vs package_info vs linux_audit). A few genuine overlaps remain, notably vulnerability_score vs vulnerability_info (both return CVSS/EPSS) and sightings_search vs vulnerability_exploits for Exploit-DB/PoC material, but the guidance mostly resolves them.

Naming Consistency4/5

Nearly all names follow a consistent resource_operation pattern (advisory_info, kev_check, cve-centric vulnerability_* cluster, product_vulnerabilities). Minor deviations like epss_timeseries (noun_noun) and the prefix shift between attack_info and vulnerability_attack are small blemishes in an otherwise predictable scheme.

Tool Count4/5

At 23 tools this is on the heavy side, but the server spans a wide domain (CVE, advisory, CWE, ATT&CK, CPE, KEV, EPSS, SSVC, package audits, feeds, sightings) so each tool maps to a real need. The count is defensible rather than padded, though a few could conceivably be consolidated.

Completeness5/5

Coverage is exceptionally thorough for a read-only vulnerability-intelligence surface: lookup, full-text search, scoring, history, exploit/PoC, KEV, EPSS timeseries, SSVC, ATT&CK/CWE mapping, CPE discovery, and three audit entry points (purl, linux, package). No obvious lifecycle gaps for the stated purpose.

Available Tools

23 tools
advisory_infoA
Read-onlyIdempotent
Inspect

Get detailed information about a specific security advisory.

What this tool does

Retrieves a security advisory (for example RHSA, DSA, USN, GHSA) from SecDB, including title, publication date, severity, summary, description, linked CVEs, CVSS metrics, weaknesses, and the affected and fixed packages and products.

When to use this tool

Use this tool when the user asks:

  • "Give me details about RHSA-2026:1234."

  • "Which CVEs are fixed by this advisory?"

  • "Which package versions are affected, and which version fixes them?"

For a CVE, use vulnerability_info. If the exact advisory ID is not known, use vulnerability_search with type set to advisory.

Inputs

  • advisory_id: exact advisory identifier (e.g. RHSA-2026:1234, GHSA-xxxx-xxxx-xxxx).

Outputs

  • advisory_id, url (page on SecDB), source, source_url (original advisory), title, summary, description, solution, severity, published, modified, rights

  • cves: identifiers of the linked CVEs. Use vulnerability_info, vulnerability_score, or kev_check for their details

  • cvss: each with cve_id, version, score, severity, and vector. An entry with a null cve_id refers to the whole advisory; the others refer to that CVE

  • cwe: each with id, name, and url

  • packages: each with purl, status (for example affected or fixed), vers (versions as a VERS range, for example vers:maven/>=2.0.0|<2.0.11), and remediation. It is null when the packages could not be read, which does not mean that no package is affected

  • products: each with vendor, product, version, fixed_in, status, text, cpe22, and cpe23

  • tags, impacts

Fields that SecDB does not have for the advisory are null or empty.

LLM usage guidelines

  • Do not guess advisory IDs: use the IDs returned by other tools or provided by the user.

  • If the advisory is not found, try vulnerability_search before saying that it does not exist.

  • An advisory can list packages of other projects that include the vulnerable code: check purl before saying that a package is affected.

  • Some advisories list thousands of packages or products, so the response can be very large.

Inputs: advisory_id (required). Returns: cwe, url, cves, cvss, +15 more

attack_infoA
Read-onlyIdempotent
Inspect

Get information about a MITRE ATT&CK technique and the weaknesses and vulnerabilities linked to it through CAPEC.

What this tool does

Returns the name, description, tactics and platforms of an ATT&CK technique (Enterprise, Mobile or ICS), its parent technique or sub-techniques, the CAPEC attack patterns mapped to it, the weaknesses (CWE) exploited by those attack patterns, and the number of CVEs with those weaknesses. A parent technique also includes what is mapped to its sub-techniques.

When to use this tool

Use this tool when the user asks:

  • "What is T1574?"

  • "Which weaknesses or attack patterns are related to this technique?"

  • "How many vulnerabilities could be linked to this technique?"

Inputs

  • technique_id: ATT&CK technique identifier (T1574, T1574.010, 1574.010 or T1574/010).

Outputs

  • id, name (with the parent technique name for a sub-technique), domain, description

  • tactics: each with id and name

  • platforms: list of platforms

  • parent_id, subtechniques (each with id and name)

  • deprecated, revoked, revoked_by (the technique that replaces a revoked one)

  • capec: attack patterns, each with id, name, direct and via

  • weaknesses: CWE, each with id, name, direct and via

  • cve_count: number of CVEs with these weaknesses

  • url: link to the technique on SecDB, mitre_url: link to the technique on attack.mitre.org

LLM usage guidelines

  • direct is true when CAPEC maps the attack pattern to this technique; via lists the sub-techniques it comes from.

  • The link to CVEs is derived from the weaknesses: a CVE in cve_count is not known to be exploited with this technique. Say so when you report it.

  • If revoked is true and revoked_by is set, call this tool again with revoked_by for the current technique.

  • For the CVEs themselves, search on SecDB from url (Vulnerabilities tab), or use cwe_info and vulnerability_search with the weaknesses.

Inputs: technique_id (required). Returns: id, url, name, capec, +12 more

cvss_explainA
Read-onlyIdempotent
Inspect

Calculate the score of any CVSS vector string and explain it in natural language.

What this tool does

Takes a CVSS vector string, not tied to a specific CVE, and returns its version, base score, severity, and a human-readable explanation.

When to use this tool

Use this tool when the user:

  • provides a CVSS vector and asks what it means

  • wants to see how the score changes when a metric changes

  • has adjusted a vector for their own environment

For the official CVSS of a CVE, use vulnerability_score.

Inputs

  • vector_string: CVSS vector string, e.g. CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H.

Outputs

  • cvss_version

  • cvss_base_score

  • cvss_base_severity

  • cvss_vector_string

  • cvss_explain: human-readable explanation of the vector

LLM usage guidelines

  • Never calculate CVSS scores by hand: use this tool.

Inputs: vector_string (required). Returns: cvss_explain, cvss_version, cvss_base_score, cvss_base_severity, +1 more

cwe_infoA
Read-onlyIdempotent
Inspect

Get information about a specific weakness (CWE), its related attack patterns (CAPEC) and ATT&CK techniques.

What this tool does

Returns the name and description of a CWE, its type, the related CAPEC attack patterns, the ATT&CK techniques mapped to those attack patterns, and the number of CVEs linked to it, with how many of them are in the CISA KEV and EU KEV catalogs.

When to use this tool

Use this tool when the user asks:

  • "What is CWE-79?"

  • "Which attack patterns are related to this weakness?"

  • "Which ATT&CK techniques are related to this weakness?"

  • "How often is this weakness exploited in the wild?"

Inputs

  • cwe_id: CWE identifier (CWE-79 or 79).

Outputs

  • id, name, type, description

  • capec: related attack patterns, each with id and name

  • attack: ATT&CK techniques mapped to these attack patterns (active techniques only), each with id, name and via (the CAPEC it comes from)

  • cve_count: number of CVEs linked to this CWE

  • cisa_kev_count: how many of these CVEs are in the CISA KEV catalog

  • eu_kev_count: how many of these CVEs are in the EU KEV catalog

  • kev_count: how many of these CVEs are in at least one of the two catalogs

  • url: link to the CWE on SecDB

LLM usage guidelines

  • Do not explain a CWE from memory when the user needs the official definition: use this tool.

  • Do not add cisa_kev_count and eu_kev_count: a CVE can be in both catalogs. Use kev_count for the total.

  • Use attack_info for the details of an ATT&CK technique.

Inputs: cwe_id (required). Returns: id, url, name, type, +7 more

epss_timeseriesA
Read-onlyIdempotent
Inspect

Get the historical EPSS time series for a specific CVE.

What this tool does

Returns the historical EPSS score, percentile, and model version available for a CVE across time, ordered by date. Useful for analyzing how exploitability likelihood has evolved over time.

When to use this tool

Use this tool when the user asks about:

  • EPSS trend over time

  • how exploitability probability changed

  • whether EPSS spiked or dropped

  • historical comparison of risk

If the user only wants the current EPSS score, use vulnerability_score instead.

Inputs

  • cve_id: valid CVE identifier (CVE-YYYY-NNNNN).

  • days: optional number of days of history to return, counting back from today (default 365, maximum 3650).

Outputs

  • series: array of objects, each containing:

    • date: measurement date in ISO format

    • score: EPSS score, as a percentage (94.36 means 94.36%)

    • percentile: EPSS percentile, as a percentage

    • model: EPSS model version

LLM usage guidelines

  • Never guess EPSS values-use this tool for all EPSS time-series questions.

  • If cve_id is malformed or incomplete, ask the user to correct it before calling.

  • If the user mentions multiple CVEs, call the tool once per CVE as needed.

  • Request a longer days window only when the user needs it: a full history is very large.

  • If no historical data is available, the tool returns an empty series: state that no EPSS history was found.

Inputs: cve_id (required), days. Returns: series

feed_reportA
Read-onlyIdempotent
Inspect

Run a public ZEN SecDB feed report.

What this tool does

Executes a predefined report on ZEN SecDB public feed data and returns structured results for analytics, trends, distributions, and top-N summaries.

Supported reports can cover public datasets such as:

  • CVEs

  • security advisories

  • EPSS

  • weaknesses

  • CPE vendors and products

  • exploit references

  • sightings and IOC-related data

Use feed_report_catalog to discover the list of available reports and their supported input parameters.

When to use this tool

Use this tool when the user asks about:

  • distributions, trends, or counts across public vulnerability data

  • top CVEs, top weaknesses, top vendors, or similar rankings

  • timeline-based summaries such as yearly or monthly trends

  • aggregated views over public SecDB feed data

Do not use this tool when the user asks for details about a single CVE, advisory, or exploit. Use the dedicated lookup tools instead.

Inputs

  • report_id: identifier of the report to execute

  • filters: optional object with report-specific filters

  • limit: optional maximum number of results to return, when supported by the selected report

Outputs

  • report_id: executed report identifier

  • filters: applied filters

  • data: structured report rows or aggregated values

LLM usage guidelines

  • Use feed_report_catalog when you need to discover which public reports are available or which parameters they support.

  • Do not guess report IDs-use the catalog when uncertain.

  • Use only the filters listed in the catalog: a report can ignore any other filter without an error, and return unfiltered data.

  • Use data for structured follow-up analysis, comparisons, or tool chaining.

  • If the selected report does not exist, return a clear not-found error instead of guessing an alternative.

Inputs: report_id (required), limit, filters. Returns: data, filters, report_id

feed_report_catalogA
Read-onlyIdempotent
Inspect

List available public ZEN SecDB feed reports.

What this tool does

Returns the catalog of available ZEN SecDB public feed reports, including their identifiers, descriptions, and supported input parameters.

This tool helps discover which reports can be executed through feed_report.

When to use this tool

Use this tool when:

  • the user asks what public reports are available

  • you need to discover the correct report ID before running a report

  • you need to inspect supported filters or input parameters

  • you are unsure which report best matches the user request

Inputs

This tool does not require any input.

Outputs

  • reports: array of report definitions, each containing:

    • report_id: report identifier

    • title: human-readable report title

    • description: short explanation of what the report returns

    • input_schema: optional JSON schema describing supported input parameters

LLM usage guidelines

  • Use this tool before feed_report whenever the correct report ID or supported parameters are not already known.

  • Do not invent report IDs or parameters not present in the catalog.

  • Prefer the most specific matching report for the user request.

  • When useful, briefly summarize the most relevant available reports before calling feed_report.

Returns: reports

kev_checkA
Read-onlyIdempotent
Inspect

Check whether one or more CVEs are listed in the CISA KEV or EU KEV catalogs of known exploited vulnerabilities.

What this tool does

For each CVE, returns whether it is in a KEV catalog and, if so, the dates, the known use in ransomware campaigns, and the threat actors reported by the EU catalog.

When to use this tool

Use this tool when the user asks:

  • "Is this CVE in CISA KEV?"

  • "Which of these CVEs are known to be exploited?"

  • to prioritize a list of CVEs

For a single CVE, this is lighter than vulnerability_info. To find the entries of a catalog by date, vendor, or product, use kev_list.

Inputs

  • cve_ids: list of CVE identifiers (CVE-YYYY-NNNNN), up to 100.

Outputs

  • results: one object for each CVE, containing:

    • cve_id

    • in_kev: whether the CVE is in at least one KEV catalog

    • when in_kev is true: in_cisa, in_eu, vendor, product, vulnerability_name, ransomware, cisa_added_date, cisa_due_date, eu_reported_date, euvd_id, eu_exploitation_type, eu_threat_actors_exploiting

LLM usage guidelines

  • Send all the CVEs in one call instead of calling the tool once per CVE.

  • in_kev: false means that the CVE is not in these catalogs, not that it is not exploited: use sightings_search for other evidence.

  • in_kev: false does not confirm that the CVE exists: use vulnerability_score or vulnerability_info to check it.

Inputs: cve_ids (required). Returns: results

kev_listA
Read-onlyIdempotent
Inspect

List the entries of the CISA KEV and EU KEV catalogs of known exploited vulnerabilities, most recent first.

What this tool does

Returns the CVEs in the catalogs, filtered by listing date, catalog, vendor, product, and known use in ransomware campaigns.

When to use this tool

Use this tool when the user asks:

  • "What was added to KEV this week?"

  • "Which Fortinet vulnerabilities are known to be exploited?"

  • "Which KEV entries are used in ransomware campaigns?"

To check CVEs that you already know, use kev_check.

Inputs

  • since: only return entries listed since then: a period (P7D, P1W, P3M, P1Y) or a date (2026-10-01, included).

  • catalog: cisa or eu (default: both). It also selects the date used by since and by the order of the results.

  • vendor: part of the vendor name, for example fortinet.

  • product: part of the product name, for example fortios.

  • ransomware: true to only return entries with known use in ransomware campaigns, false for the others.

  • limit: maximum number of entries to return (default 25, maximum 100).

  • page: page of results to return (default 1).

Outputs

  • total_results, total_pages, current_page

  • entries: each with cve_id, in_cisa, in_eu, vendor, product, vulnerability_name, ransomware, first_listed_date, first_listed_by, cisa_added_date, cisa_due_date, eu_reported_date

LLM usage guidelines

  • Without catalog, since uses first_listed_date: a CVE already in CISA KEV that has just been added to EU KEV does not appear. To see the recent entries of a catalog, set catalog.

  • When total_results is greater than the returned entries, say so before drawing conclusions.

  • An empty list does not mean that nothing is exploited: the catalogs only contain confirmed cases. Use sightings_search for other evidence.

  • For the score of the CVEs, use vulnerability_score.

Inputs: page, limit, since, vendor, +3 more. Returns: entries, total_pages, current_page, total_results

linux_auditA
Read-onlyIdempotent
Inspect

Perform a Linux package vulnerability audit using SecDB.

What this tool does

Analyzes the installed packages of a Linux system-identified by OS and OS version-and returns vulnerability information plus a Markdown summary. The audit results are based exclusively on the package list provided by the user.

When to use this tool

Use this tool when the user wants to determine:

  • whether installed packages contain known vulnerabilities

  • whether a host, VM, container, or base image is affected by security advisories

  • which packages require patching or upgrading

If the user does not know the valid values for os or version, first call the linux_os tool to retrieve the exact supported combinations.

Inputs

  • os: Linux distribution identifier supported by SecDB (use linux_os to obtain allowed values).

  • version: OS version or codename corresponding to the selected distribution, exactly as returned by linux_os (for example focal, not 20.04). Any other value is rejected with the list of supported values.

  • packages: list of installed packages, one per line, generated using the appropriate system command:

For RPM-based distributions (RHEL, CentOS, Rocky, Alma, SUSE)

rpm -qa --qf '%{NAME}-%{VERSION}-%{RELEASE}.%{ARCH}\n'

For DEB-based distributions (Ubuntu, Debian)

dpkg-query -W -f='${Package} ${Version} ${Architecture}\n'

For Alpine Linux

apk list -I

For Slackware

ls -1 /var/log/packages/

The raw output of these commands can be passed directly as the packages input (one package per line).

...
python3 3.12.3-0ubuntu2.1 amd64
systemd 255.4-1ubuntu8.10 amd64
tmux 3.4-1ubuntu0.1 amd64
...

Outputs

  • report: structured objects describing the advisories affecting the audited packages. Packages without known vulnerabilities are not listed.

  • summary: Markdown summary including vulnerable packages, total CVEs, and severity breakdown.

LLM usage guidelines

  • Never guess whether a package is vulnerable-always call this tool for Linux audits.

  • If os or version is unclear or missing, call linux_os and ask the user to choose a valid combination.

  • Normalize the package list to “one entry per line” if the user provides unstructured output.

  • The summary is already Markdown and can be shown directly.

  • Use report when deeper technical analysis is required.

Inputs: os (required), version (required), packages (required). Returns: report, summary

linux_osA
Read-onlyIdempotent
Inspect

List supported Linux operating systems and their corresponding versions for use with the linux_audit tool.

What this tool does

Returns the supported OS/version pairs in supported, each in the form:

{"os":"name", "versions":["version or codename"]}

This allows the LLM and the user to know exactly which inputs are valid for the linux_audit tool.

When to use this tool

Use this tool when:

  • the user does not know which OS names or versions are supported

  • the user provides unclear or ambiguous OS information

  • you need to validate os/version before performing a Linux audit

This tool should typically be called before linux_audit whenever parameters are uncertain.

Inputs

This tool does not require any input.

Outputs

  • supported: array of objects, each containing:

    • os: supported Linux distribution identifier

    • versions: corresponding list of supported release or codename

Example:

{
    "supported": [
        {"os": "ubuntu", "versions": ["noble","focal"]},
        {"os": "debian", "versions": ["bookworm","sid"]},
        {"os": "redhat", "versions": ["redhat-9.0"]}
    ]
}

LLM usage guidelines

  • Use this tool to validate or suggest correct OS/version combinations before calling linux_audit.

  • If the user provides invalid or misspelled OS names, retrieve the official list here and ask them to select one.

  • Do not guess operating system identifiers-always rely on this tool to confirm correctness.

Returns: supported

package_infoA
Read-onlyIdempotent
Inspect

List the security advisories known for a package, with the affected and fixed versions.

What this tool does

Returns the advisories of a package across all its versions, most recent first. This covers more ecosystems than purl_audit, for example github, cpan, apache, and freebsd.

When to use this tool

Use this tool when the user asks:

  • "Which vulnerabilities has this package had?"

  • "Which version fixes this vulnerability?"

  • "Which version should I upgrade to?"

To check whether a specific version is vulnerable, use purl_audit or linux_audit: this tool does not evaluate versions.

Inputs

  • purl: Package URL. The version is ignored. For Linux packages, add the distro qualifier to limit the results to one release, for example pkg:deb/ubuntu/curl?distro=noble.

  • limit: maximum number of advisories to return (default 25, maximum 100).

  • page: page of results to return (default 1).

Outputs

  • total_results, total_pages, current_page: advisories for the package across all pages

  • advisories: each with advisory_id, title, severity, published, cves, status, affected, fixed_versions

    • affected: version ranges, each with versions and, for Linux packages, distro

    • fixed_versions: each with version and, for Linux packages, distro. A version is either reported as fixed by the advisory or the exclusive upper bound of an affected range

LLM usage guidelines

  • When total_results is 0, say that SecDB has no advisories for this package name, not that the package is safe. Names must match exactly.

  • To recommend an upgrade, consider all the advisories and check the resulting version with purl_audit when its ecosystem is supported.

  • status can include malicious: tell the user to remove the package instead of upgrading it.

  • If fixed_versions is empty, say that no fix is known. Do not guess a version.

Inputs: purl (required), page, limit. Returns: advisories, total_pages, current_page, total_results

product_vulnerabilitiesA
Read-onlyIdempotent
Inspect

List the CVEs of a product by its CPE vendor and product names, with the affected version ranges.

What this tool does

Returns the CVEs whose CPE configuration marks the product as vulnerable, most recent first. Use it for assets that have no Package URL, such as appliances, operating systems, and commercial software.

When to use this tool

Use this tool when the user asks:

  • "Which CVEs affect FortiOS?"

  • "What are the latest vulnerabilities of this product?"

  • "Is this product version affected by a known CVE?"

For open source dependencies, use purl_audit. If the CPE names are not known, use cpe_search first.

Inputs

  • vendor: CPE vendor name, for example fortinet.

  • product: CPE product name, for example fortios.

  • limit: maximum number of CVEs to return (default 25, maximum 100).

  • page: page of results to return (default 1).

Outputs

  • total_results, total_pages, current_page: CVEs for the product across all pages

  • cves: each with cve_id, published, severity, score, description, affected_versions

  • note: present when no CVE matches

LLM usage guidelines

  • This tool does not filter by version: compare the user's version with affected_versions, and say that the comparison is yours. An entry of all means that the configuration has no version limits.

  • When total_results is greater than the returned CVEs, say so before drawing conclusions about a version.

  • When total_results is 0, do not say that the product is safe: the vendor or product name may differ from the CPE one. Use cpe_search to find it.

Inputs: vendor (required), product (required), page, limit. Returns: cves, note, total_pages, current_page, +1 more

purl_auditA
Read-onlyIdempotent
Inspect

Perform a software package vulnerability audit using SecDB.

What this tool does

Analyzes a list of software packages identified by PURL (Package URL) and returns vulnerability information plus a Markdown summary. The audit results are based exclusively on the package list provided.

When to use this tool

Use this tool when the user wants to determine:

  • whether application dependencies contain known vulnerabilities

  • whether a project is affected by security advisories

  • which packages require patching or upgrading

Supported ecosystems

Inputs

  • purls: list of Package URLs, one per entry. Generate them from your project manifest files:

    • Node.js: package.json / package-lock.json

    • Python: requirements.txt / Pipfile.lock / pyproject.toml

    • Ruby: Gemfile.lock

    • Go: go.mod / go.sum

    • Rust: Cargo.lock

    • PHP: composer.lock

    • Java: pom.xml / build.gradle

    • .NET: *.csproj / packages.lock.json

Outputs

  • report: structured JSON objects describing the advisories affecting the audited packages. Packages without known vulnerabilities are not listed.

  • summary: Markdown summary including vulnerable packages, total CVEs, and severity breakdown.

  • audited: number of PURLs that were checked.

  • ignored: PURLs that were not checked because they are malformed or from an unsupported ecosystem.

LLM usage guidelines

  • Never guess whether a package is vulnerable — always call this tool.

  • Only submit PURLs from the supported ecosystems listed above; others are returned in ignored.

  • Tell the user about any ignored PURL: they were not checked, so they are not known to be safe.

  • The summary is already Markdown and can be shown directly.

  • Use report when deeper technical analysis is required.

Inputs: purls (required). Returns: report, audited, ignored, summary

ssvc_calculatorA
Read-onlyIdempotent
Inspect

Compute CISA SSVC (Stakeholder-Specific Vulnerability Categorization) for a CVE.

What this tool does

Calculates the SSVC decision (Track, Track*, Attend, Act) using:

  • exploitation status

  • technical impact

  • automatable exploitation

  • mission prevalence (user-provided)

  • public well-being impact (user-provided)

This reflects CISA's official SSVC prioritization model.

When to use this tool

Use this tool when the user asks about:

  • how urgently a CVE should be remediated

  • CISA SSVC priority or risk category

  • a structured decision model for remediation

Inputs

  • cve_id: the vulnerability to evaluate (CVE-YYYY-NNNNN)

  • mission_prevalence: M, S, or E (must be provided by the user)

  • public_well_being_impact: M, A, or I (must be provided by the user)

Outputs

  • decision: one of Track, Track*, Attend, Act

  • exploitation

  • technical_impact

  • automatable

  • mission_prevalence

  • public_well_being_impact

  • mission_and_well_being_impact_value

  • vector_string

  • summary: Markdown explanation of the outcome

LLM usage guidelines

  • Always ask the user for mission_prevalence (M/S/E) and public_well_being_impact (M/A/I) before calling.

  • Never guess these values—SSVC depends on user context.

  • Use the summary to explain clearly why the decision was returned.

  • Combine with vulnerability_score or sightings_search if the user needs additional context.

Inputs: cve_id (required), mission_prevalence (required), public_well_being_impact (required). Returns: summary, decision, automatable, exploitation, +5 more

vulnerability_attackA
Read-onlyIdempotent
Inspect

Get the weaknesses (CWE), attack patterns (CAPEC) and MITRE ATT&CK techniques linked to a specific CVE.

What this tool does

Follows the chain CVE → CWE → CAPEC → ATT&CK: returns the weaknesses of the CVE, the CAPEC attack patterns that exploit them, the ATT&CK techniques mapped to those attack patterns (active techniques only), and a summary of the ATT&CK tactics involved.

When to use this tool

Use this tool when the user asks:

  • "Which ATT&CK techniques are related to CVE-XYZ?"

  • "Which tactics could an attacker use with this vulnerability?"

  • "Which attack patterns exploit the weaknesses of this CVE?"

Inputs

  • cve_id: valid CVE identifier (CVE-YYYY-NNNNN).

Outputs

  • cve_id, url: link to the CVE on SecDB

  • cwe: weaknesses, each with id, name and url

  • capec: attack patterns, each with id, name, via (the CWE it comes from) and url

  • attack: ATT&CK techniques, each with id, name, tactics (id and name), via (the CAPEC it comes from), url and mitre_url

  • tactics: ATT&CK tactics, each with id, name and technique_count

LLM usage guidelines

  • The link is derived from the weaknesses of the CVE: it does not mean that the vulnerability is exploited with these techniques. Say "related to" or "could be linked to", never "exploited via".

  • Empty lists are normal: many weaknesses have no CAPEC attack pattern and many attack patterns have no ATT&CK technique.

  • For real-world exploitation use kev_check, vulnerability_exploits and sightings_search.

  • For the details of a technique or a weakness use attack_info or cwe_info.

Inputs: cve_id (required). Returns: cwe, url, capec, attack, +2 more

vulnerability_exploitsA
Read-onlyIdempotent
Inspect

List the known exploits, proofs of concept, and detection templates for a specific CVE.

What this tool does

Returns the exploit maturity of a CVE and the related public material known to SecDB:

  • Metasploit modules

  • Exploit-DB entries

  • Nuclei templates

  • proofs of concept published on GitHub

When to use this tool

Use this tool when the user asks:

  • "Is there a public exploit for this CVE?"

  • "Is there a Metasploit module or a Nuclei template for this vulnerability?"

  • "How mature is the exploitation of this CVE?"

For other evidence (scanner plugins, social media, MISP), use sightings_search.

Inputs

  • cve_id: valid CVE identifier (CVE-YYYY-NNNNN).

  • limit: maximum number of items to return for each kind of material (default 10, maximum 100).

Outputs

  • exploit_maturity: score, max, and the sources that contribute to the score

  • metasploit: modules, each with module, name, type

  • exploitdb: entries, each with id, description, type, platform, date_published

  • nuclei: templates, each with template, name, severity

  • poc: repositories, each with name, html_url, description

  • totals: total number of items for each kind of material, before limit is applied

LLM usage guidelines

  • Empty lists mean that SecDB knows no such material, not that the vulnerability cannot be exploited.

  • Report references and availability only: do not reproduce or write exploit code.

Inputs: cve_id (required), limit. Returns: poc, cve_id, nuclei, totals, +3 more

vulnerability_historyA
Read-onlyIdempotent
Inspect

Get the timeline of events for a specific CVE.

What this tool does

Returns the dated events known to SecDB for a CVE, most recent first:

  • published: publication of the CVE

  • nvd: NVD changes (CVSS, CPE, CWE, references, description)

  • advisory: security advisories that mention the CVE

  • nasl: NASL detection plugins that cover the CVE

  • cisa-kev, eu-kev: addition to a Known Exploited Vulnerabilities catalog

  • poc: public proof-of-concept repositories on GitHub

  • exploitdb: Exploit-DB entries

  • alias: public disclosure under a known name

Every event carries the date of the event itself, not the date it reached SecDB. Sources without a date are not included. EPSS changes are not included: use epss_timeseries.

When to use this tool

Use this tool when the user asks:

  • "What changed on CVE-XYZ since last week?"

  • "When was this CVE added to KEV?"

  • "When did the first PoC or detection plugin appear?"

For the current state of a CVE, use vulnerability_info.

Inputs

  • cve_id: valid CVE identifier (CVE-YYYY-NNNNN).

  • types: only return these event types (default: all).

  • since: only return events from this date, included (YYYY-MM-DD).

Outputs

  • cve_id: CVE identifier.

  • returned: number of events returned.

  • counts: number of events for each type. It follows since but not types, so it also shows what types left out.

  • events: each with type, timestamp, and change. The fields of change depend on the type:

    • published: none

    • nvd: source, event, action, type, old, new

    • advisory: advisory_type, advisory_id, advisory_severity, advisory_title

    • nasl: plugin_id, plugin_vendor, plugin_name

    • cisa-kev: vulnerability_name, due_date

    • eu-kev: vulnerability_name, patched_since

    • poc: name, description, url

    • exploitdb: id, description, file

    • alias: alias

LLM usage guidelines

  • The response is not paginated and can be very large for well-known CVEs, mostly because of poc and nasl events: use types and since to request only what you need.

  • An event dated before since can still be new to SecDB: do not use this tool to prove that nothing changed.

  • Do not guess dates or events: use what the tool returns.

Inputs: cve_id (required), since, types. Returns: counts, cve_id, events, returned

vulnerability_infoA
Read-onlyIdempotent
Inspect

Get detailed information about a specific CVE.

What this tool does

Retrieves the full vulnerability record for a CVE from SecDB, including:

  • official description and summary

  • CVSS metrics (all versions available)

  • current EPSS score and percentile (if present)

  • CISA KEV details (if listed)

  • affected products

  • vendor/security advisories

  • weakness classification (CWE)

  • number of known Metasploit modules and Exploit-DB entries

When to use this tool

Use this tool when the user asks:

  • "Give me details about CVE-XYZ."

  • "Which products are affected by this vulnerability?"

  • "Show me advisories or references for this CVE."

  • "Explain what this vulnerability is and how serious it is."

This tool is ideal for deep inspection of a single vulnerability. For multiple CVEs, call the tool once per CVE.

Inputs

  • cve_id: valid CVE identifier (CVE-YYYY-NNNNN).

Outputs

  • cve_id, url, title, description, cna, status, published, modified, aliases

  • cwe: each with id, name, and url

  • cvss: one entry for each CVSS version available, with version, score, severity, and vector

  • epss: score and percentile (both as percentages) and date, or null

  • exploits: number of known metasploit modules and exploitdb entries

  • kev: listed, in_cisa, in_eu, date (first listing), ransomware, and cisa (vendor, product, description, required_action, notes, added_date, due_date, or null)

  • affected_products: each with vendor, product, part, title, and url, without versions

  • advisories: each with id, source, severity, and url. Use advisory_info for the details of an advisory

LLM usage guidelines

  • Always prefer this tool when the user needs factual information about a specific CVE.

  • If multiple CVEs are mentioned, call the tool once per CVE.

  • Combine with:

    • vulnerability_score - to get the CVSS vector explained in natural language

    • vulnerability_exploits - to list the known exploits and PoCs

    • vulnerability_history - to get the timeline of events

    • vulnerability_attack - to get the CAPEC attack patterns and ATT&CK techniques related to the weaknesses

    • sightings_search - to check real-world exploitation, PoCs, plugins, advisories

    • ssvc_calculator - to compute prioritization based on the vulnerability data

  • Do not hallucinate product lists, advisories, or details—use what the tool returns.

Inputs: cve_id (required). Returns: cna, cwe, kev, url, +12 more

vulnerability_scoreA
Read-onlyIdempotent
Inspect

Get CVSS and current EPSS score for one CVE, or for a list of CVEs in a single call.

What this tool does

Returns a full risk snapshot for a CVE, including:

  • CVSS version

  • CVSS base score

  • CVSS severity

  • CVSS vector string

  • human-readable explanation of the CVSS vector

  • current EPSS score

The field cvss_explain provides a natural-language interpretation of the CVSS vector (attack conditions, privileges, user interaction, impact breakdown).

Example: For CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H, the explanation may read: "The vulnerability can be exploited remotely over the network with low complexity, without authentication and without user interaction. Exploitation may lead to high impact on confidentiality, high impact on integrity, and high impact on availability."

When to use this tool

Use this tool when the user asks:

  • "What is the CVSS/EPSS of this CVE?"

  • "Explain the CVSS vector of this vulnerability."

  • "What is the severity and why?"

  • "Give me the risk profile for this CVE."

For EPSS historical trends, use epss_timeseries.

Inputs

Send one of these:

  • cve_id: valid CVE identifier (CVE-YYYY-NNNNN).

  • cve_ids: list of up to 100 CVE identifiers.

Outputs

With cve_ids:

  • results: one item for each CVE found, with cve_id and the fields below except cvss_explain

  • not_found: the CVEs that SecDB does not know

With cve_id:

  • cvss_version

  • cvss_base_score

  • cvss_base_severity

  • cvss_vector_string

  • cvss_explain - human-readable explanation of the CVSS vector

  • epss_score - as a percentage (94.36 means 94.36%)

Any of these fields is null when SecDB has no such data for the CVE (for example a CVE not yet analyzed or scored).

LLM usage guidelines

  • Never guess CVSS or EPSS values—always call this tool.

  • If a field is null, say that the value is not available.

  • Use the cvss_explain field directly when the user wants an interpretation of the vector string.

  • If multiple CVEs are referenced, send them all in cve_ids. To explain a vector from the results, use cvss_explain.

  • Combine this tool with sightings_search or ssvc_calculator for more complete risk assessments.

Inputs: cve_id, cve_ids. Returns: results, not_found, epss_score, cvss_explain, +4 more

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      C
      maintenance
      MCP server to query and manage CISA Known Exploited Vulnerabilities catalog with EPSS overlay, enabling vulnerability checks and remediation deadline tracking.
      35 PyPI
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      MCP server for querying live CISA KEV, EPSS, and enriched vulnerability feeds with full provenance. Enables natural-language access to auditable security-intelligence data from Claude Desktop and other MCP clients.
      MIT
    • A
      license
      A
      quality
      C
      maintenance
      Unifies NVD, EPSS, CISA KEV, GitHub Advisory, and OSV into a single MCP server, enabling AI agents to query vulnerability intelligence conversationally with 23 tools for incident response, prioritization, dependency audits, and threat monitoring.
      41
      1,150 npm
      32
      MIT
    Try in Browser

    Glama MCP Gateway

    Add one secure layer between your agents and this server.

    Resources