Calculate and validate CVSS 2.0, 3.0, 3.1, and 4.0 base scores.
Scored across 1 tool
With a single tool there is no possible confusion about which tool to select, and the description makes the exact scope (Base score, four CVSS versions) explicit. Metric abbreviations are spelled out so the parameter space is self-documenting.
The single tool follows a clear verb_noun convention (calculate_cvss) in snake_case, which is exactly the pattern one would want extended across a larger set.
For a narrowly scoped calculator, one tool is the right shape rather than a mismatch, so this is well-scoped rather than thin. It is only slightly under-scoped in that vector-string parsing/validation or a metric-listing helper could reasonably live alongside it.
Coverage of the domain is deliberately partial: only Base scores for 2.0/3.0/3.1/4.0, with temporal and environmental metrics explicitly rejected and no way to parse or validate an existing CVSS vector string. For a server named 'CVSS Calculator' those are notable gaps an agent may hit in real triage workflows.
Calculate a CVSS Base-only score for 2.0, 3.0, 3.1 or 4.0. Supply every metric; never guess. v2: AV Access Vector, AC Access Complexity, Au Authentication, C/I/A Confidentiality/Integrity/Availability. v3: AV Attack Vector, AC Attack Complexity, PR Privileges Required, UI User Interaction, S Scope, C/I/A impact. v4: AT Attack Requirements, VC/VI/VA Vulnerable System impact, SC/SI/SA Subsequent System impact. Rejects non-Base metrics.
| Name | Required | Description | Default |
|---|---|---|---|
| vector | Yes | Complete case-sensitive Base-only vector. v2: AV L/A/N, AC H/M/L, Au M/S/N, C/I/A N/P/C. v3: AV N/A/L/P, AC L/H, PR N/L/H, UI N/R, S U/C, C/I/A H/L/N. v4: AV N/A/L/P, AC L/H, AT N/P, PR N/L/H, UI N/P/A, VC/VI/VA/SC/SI/SA H/L/N. | |
| version | Yes | CVSS version |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It does disclose validation behavior (rejects non-Base vectors) and the required version-specific metric sets, but says nothing about what is returned (score plus any computed components) or how errors surface—material gaps for a tool with zero annotation coverage.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Front-loaded with the action and version scope, then the metric glossary. Dense but every clause carries information; the per-version metric lists partly duplicate the schema's enumerated values, which is the only waste.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
A two-parameter, single-purpose tool with no output schema and full schema coverage needs little more than this. The one real omission is the return value (a numeric score and possibly per-metric breakdown), which the agent must infer.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is already 100%, so the baseline is 3; the description earns above it by expanding abbreviations the schema only lists cryptically (AV Access Vector, AT Attack Requirements, SC/SI/SA Subsequent System impact) and by warning that the vector is case-sensitive. It stops short of giving format examples or ordering rules.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb and resource ('Calculate a CVSS Base-only score') and scopes it precisely to versions 2.0/3.0/3.1/4.0 and Base-only metrics. An agent knows exactly what computation this performs and what it will refuse.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Gives explicit input discipline ('Supply every metric; never guess') and an exclusion rule ('Rejects non-Base metrics'), which amounts to a when-not condition. It lacks any statement of when to prefer a different approach, but with no siblings that gap is minor.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
calculate_cvssLook up CVEs, CISA KEV, EPSS and open-source package vulnerabilities, including malicious packages.
CVE triage in one call: NVD, CVSS, CISA KEV, EPSS, public exploits and an explained risk score.
Look up FIRST EPSS scores and daily history, find CVEs by threshold, and prioritize them with CVSS.
Defensive vulnerability intelligence search across public CVE/NVD and GitHub advisory APIs with CVSS
Add one secure layer between your agents and this server.