Skip to main content
Glama

ClevSec EU compliance tools

Vendor security risk assessment

vendor_risk_assessment
Read-onlyIdempotent

Use when an organisation evaluates a supplier, SaaS or ICT provider (vendor due diligence, third-party risk, supply chain security under NIS2 Art. 21(2)(d) or DORA). Call without input to get the questions. Call with the vendor profile (type, criticality, data access, regimes) and answers (yes, partial, no, unknown) to get a risk score, risk level, monitoring tier and the gaps.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "vendor_risk_assessment"
  }
}

Input Schema

NameRequiredDescriptionDefault
bcp1NoDoes the vendor have a business continuity / disaster recovery plan?
bcp2NoDoes the vendor offer a defined SLA with uptime guarantees?
bcp3NoCan data be exported/migrated if you terminate the relationship?
bcp4NoDoes the vendor have geographic redundancy for critical services?
bcp5NoIs the vendor financially stable (no signs of distress)?
com1NoIs the vendor compliant with GDPR (if processing EU personal data)?
com2NoWill the vendor sign a Data Processing Agreement?
com3NoDoes the vendor provide right-to-audit or access to audit reports?
com4NoDoes the vendor's contract include security requirements and SLAs?
com5NoDoes the vendor have adequate insurance coverage (cyber liability)?
inc1NoDoes the vendor have a documented incident response plan?
inc2NoWill the vendor notify you of security incidents within 24-48 hours?
inc3NoHas the vendor experienced any data breaches in the last 3 years?
inc4NoDoes the vendor conduct incident response exercises/tabletop tests?
sec1NoDoes the vendor hold relevant security certifications (ISO 27001, SOC 2, etc.)?
sec2NoDoes the vendor have a documented information security policy?
sec3NoDoes the vendor encrypt data at rest and in transit?
sec4NoDoes the vendor enforce multi-factor authentication?
sec5NoDoes the vendor conduct regular penetration testing?
sec6NoDoes the vendor have a vulnerability management program?
sec7NoDoes the vendor perform background checks on employees with data access?
sup1NoDoes the vendor disclose its key subprocessors/subcontractors?
sup2NoWill the vendor notify you before changing subprocessors?
sup3NoDoes the vendor assess the security of its own suppliers?
sup4NoAre subprocessor contracts held to the same security standards?
regimesNoWhich of these apply to your organization? (optional)
dataAccessNoWhat data will this vendor access?
vendorTypeNoType of service
criticalityNoHow critical is this vendor to your operations?

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already establish readOnly/idempotent/non-destructive/closed-world, so the safety profile is covered. The description still adds value by disclosing the stateless two-mode behavior (questionnaire vs. computation) and naming the outputs (risk score, risk level, monitoring tier, gaps), which the annotations cannot convey.

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

Conciseness5/5

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

Three sentences, all load-bearing: trigger first, then the two invocation modes and their returns. No filler, and the most decision-relevant information (when to call) is front-loaded.

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

Completeness4/5

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

For a 29-param, output-schema-less tool this is well covered: it explains both call modes and enumerates the return fields. It omits edge behavior (e.g., a partial answer set, unknown handling beyond the enum, or how regimes affects scoring), which keeps it from a 5.

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, but the description contributes a partition the flat 29-parameter schema lacks: 'vendor profile (type, criticality, data access, regimes)' versus 'answers (yes, partial, no, unknown)'. It also restates the answer scale, useful for a caller without the schema open.

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

Purpose4/5

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

The description names a specific verb and resource: assessing a supplier/SaaS/ICT vendor's security risk, with regulatory framing (NIS2 Art. 21(2)(d), DORA). It does not explicitly distinguish itself from close siblings like vendor_due_diligence_plan or cyber_risk_score, so the agent must infer the split, but the standalone purpose is unmistakable.

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?

It gives an explicit trigger ('Use when an organisation evaluates a supplier...') and, unusually well, states both call modes: no input returns the questions, full input returns the score. It stops short of naming which alternative to pick when a plan or a standalone score is wanted, so no explicit when-not routing.

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.

Resources