Encryptor MCP

trash

Move a file or folder into a vault's encrypted, logged, recoverable deleted-items area; permanent deletion requires separate approval.

Instructions

Put a file or folder (with everything in it) in the vault's own trash, the way to remove things here. It stays encrypted in the vault, the change is logged, and undo takes it back out; trash_list shows what's there. Deleting for good happens only with empty_trash, which the user approves. Returns the path and the change id; if the user asked to approve this, it may instead return a question for them.

Input Schema

Name	Required	Description
`path`	Yes	A path inside the vault, from its top, for example 'Taxes/2025/receipts.md'.
`vault`	Yes	The vault's name, as listed by the vaults tool, for example 'Taxes'.
`confirm`	No	Leave empty. Only pass the code a previous answer gave you, after the user agreed.
`purpose`	Yes	A few words on why, shown to the user or kept in the vault's change log.

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedv0.1.4Oct 21, 2026

addedInput schema / properties / confirm / description

Added value: +"Leave empty. Only pass the code a previous answer gave you, after the user agreed."

addedInput schema / properties / path / description

Added value: +"A path inside the vault, from its top, for example 'Taxes/2025/receipts.md'."

addedInput schema / properties / purpose / description

Added value: +"A few words on why, shown to the user or kept in the vault's change log."

addedInput schema / properties / vault / description

Added value: +"The vault's name, as listed by the vaults tool, for example 'Taxes'."

First observedv0.1.3Oct 20, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations declare destructiveHint=false, and the description actively explains why: contents stay encrypted in the vault, the change is logged, and undo reverses it. It also discloses the approval flow (may return a question instead of a result) and the return shape (path + change id) — well beyond what the annotations carry.

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

Conciseness4/5

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

Four sentences, front-loaded with the core action, then behavior, then alternatives, then returns. Every sentence carries information, though the description is on the longer side and the return-value sentence is partly redundant with the output schema.

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?

For a mutation tool this covers everything an agent needs: safety profile, reversibility, logging, alternatives, and the interactive-approval edge case. An output schema exists, so the return detail is bonus rather than a requirement.

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. The description goes further by explaining the confirm/approval mechanism (a question may be returned, and the code is passed after the user agrees), which adds meaning to the confirm parameter beyond its schema text.

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 ('Put a file or folder ... in the vault's own trash') and immediately frames it as 'the way to remove things here.' It distinguishes itself from siblings by naming trash_list and empty_trash, so an agent can route without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly defines the removal pathway and the alternative: soft delete here versus permanent deletion 'only with empty_trash, which the user approves,' plus trash_list to inspect contents. The when-to-use and when-not-to-use conditions are both present.

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

Deploy Server