Vulnify MCP

Official

by vulnify

Overview Schema Source Related Servers Discussions Admin

TypeScript

Hybrid

Get decision

get_decision

Read-onlyIdempotent

Retrieve a recorded Vulnify authorization decision by ID and poll until it becomes ALLOW or BLOCK, returning REVIEW if still pending.

Instructions

Read a recorded decision (GET /v1/events/{id}), including a REVIEW. finalDecision is REVIEW while the review is pending, then ALLOW after approval or BLOCK after denial or expiry. decision itself does not change. The finalDecision field is the authoritative result. waitMs polls until finalDecision is ALLOW or BLOCK, or until the bounded wait elapses (30 seconds maximum). waitTimedOut is true when the wait ended and finalDecision is still REVIEW. This does not approve or deny the review.

Input Schema

TableJSON Schema

Name	Required	Description
`id`	Yes	Decision id returned by decide_action or check_mcp_tool_call.
`waitMs`	No	When finalDecision is REVIEW, the server polls until finalDecision is ALLOW or BLOCK, or until this many milliseconds pass. Maximum 30000. 0, or omitting the field, returns the current decision immediately.
`pollIntervalMs`	No	Milliseconds between polls. Default 1000.

Output Schema

TableJSON Schema

Name	Required	Description
`id`	Yes	Decision id.
`waitTimedOut`	Yes	True when the wait elapsed and finalDecision is still REVIEW.
`finalDecision`	Yes	Authoritative result. Allowed values: ALLOW, REVIEW, BLOCK.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.5Oct 17, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations already cover the safe-read profile (readOnly, idempotent, non-destructive), and the description adds genuine behavioral context: the state transition from REVIEW to ALLOW/BLOCK, that decision is immutable while finalDecision is authoritative, and the 30-second bounded wait. It omits error/not-found behavior, but the added semantics are substantial.

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?

Front-loads the verb, resource, and endpoint, then spends its remaining sentences on the semantics an agent actually needs (state transitions, polling bound, timeout flag). No filler or restated name/title.

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?

With annotations carrying the safety profile, a 100%-covered schema, and an output schema, the description only needs to supply the non-obvious semantics, and it does: finalDecision authority, polling termination conditions, and the non-mutating boundary.

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

Parameters3/5

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

Schema description coverage is 100%, so id, waitMs, and pollIntervalMs are already fully documented with constraints. The description paraphrases waitMs polling behavior but adds no syntax or format detail beyond the schema, so the baseline 3 applies.

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 and resource ('Read a recorded decision (GET /v1/events/{id})') and clarifies the scope includes a REVIEW, with the explicit boundary 'This does not approve or deny the review' separating it from decide_action.

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?

Explains clearly when to supply waitMs (while finalDecision is REVIEW, to poll until ALLOW/BLOCK or timeout) and what waitTimedOut means, plus when not to use it. It never names decide_action as the alternative for resolving a review, so the routing guidance is one step short of explicit.

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

Deploy Server