open-mcp-apps

Overview Schema Source Related Servers Discussions Admin

Set a security policy key

security_set

DestructiveIdempotent

Write reserved security and policy settings, such as allow/deny/confirm rules, tool lists, or CSP origins, to define an app's security policy; generic data tools reject these keys.

Instructions

Settings app only: writes one reserved settings key (security:* / policy:), the person's security policy. The generic data_ tools refuse reserved keys.

Input Schema

TableJSON Schema

Name	Required	Description
`key`	Yes	a reserved key, e.g. security:kanban:send_message (cap suffixes are snake_case — the caps field names)
`value`	Yes	allow \| deny \| confirm, a tool list for call_tools, or a CSP origins object for policy:csp:*. An unknown value is refused
`command_id`	No	idempotency key (uuid); auto-generated if omitted

Output Schema

TableJSON Schema

Name	Required	Description	Default
`id`	No
`ok`	Yes
`eot`	No
`seq`	No
`item`	No
`note`	No
`reason`	No
`deleted`	No
`collection`	No
`violations`	No
`expected_version`	No
`prev_collection_seq`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv0.10.1Oct 18, 2026

changedInput schema / properties / value / description

Previous value: -"the policy value: allow | deny (true/false too); delete_items also takes confirm; call_tools takes \"*\", a JSON array or a comma-separated tool list; policy:csp:<app> (or policy:csp:*) takes a JSON object of origin arrays, e.g. {\"connectDomains\":[\"https://api.example.com\"]}. An unknown value is REFUSED, never stored"New value: +"allow | deny | confirm, a tool list for call_tools, or a CSP origins object for policy:csp:*. An unknown value is refused"

Changed1 schema field changedv0.6.0Sep 5, 2026

changedInput schema / properties / value / description

Previous value: -"the policy value: allow | deny (true/false too); delete_items also takes confirm; call_tools takes \"*\", a JSON array or a comma-separated tool list. An unknown value is REFUSED, never stored"New value: +"the policy value: allow | deny (true/false too); delete_items also takes confirm; call_tools takes \"*\", a JSON array or a comma-separated tool list; policy:csp:<app> (or policy:csp:*) takes a JSON object of origin arrays, e.g. {\"connectDomains\":[\"https://api.example.com\"]}. An unknown value is REFUSED, never stored"

First observedv0.5.7Aug 15, 2026

TDQS

A4/5.0

Behavior3/5

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

Annotations already declare destructiveHint=true, idempotentHint=true and readOnlyHint=false, so the safety profile is covered. The description adds the reserved-key exclusivity mechanism (only this tool can write these keys), which is useful context, but it does not say whether an existing policy value is overwritten or what authorization is required.

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?

Two tight sentences with the scope restriction ('Settings app only') front-loaded, followed immediately by the key namespace and the sibling-alternative note. No filler.

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?

With an output schema present, return values need no explanation, and the description covers scope, key namespace, value semantics and idempotency (via schema/annotations). Only the overwrite behavior on an existing policy remains unstated, which is a minor gap.

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 key, value and command_id are fully documented in the schema. The description only restates that the key is reserved and that unknown values are refused, adding no syntax or format detail beyond 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+resource ('writes one reserved settings key'), gives the exact key namespaces (security:* / policy:*), and scopes it to the Settings app. It is clearly distinguishable from the data_* siblings, which it explicitly contrasts against.

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?

Names the condition that selects this tool (reserved security/policy keys) and the alternative that fails ('The generic data_* tools refuse reserved keys'), which is strong routing guidance. It does not explicitly state when NOT to use it or what prerequisites/authorization apply.

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