Local MCP

OneDrive Set Scope

onedrive_set_scope

Destructive

Limits LMCP's access to one OneDrive to a single folder. Once set, every LMCP tool that reads, lists, searches, writes, deletes or moves files — the onedrive_* tools and the general file tools alike — refuses any path in that OneDrive outside the folder, including the OneDrive's own top level; searches only return what is inside it. If the folder is later moved or deleted, that OneDrive is closed until the limit is changed. Pass an empty folder to remove the limit. Changes take effect immediately.

Input Schema

Name	Required	Description	Default
`folder`	No	Allowed folder path relative to the root (e.g. '/000-Claude Personal Agent'). Empty string removes the scope.
`root_name`	Yes	OneDrive root name (from onedrive_root, e.g. 'OneDrive-WPPCloud')

Output Schema

Name	Required	Description	Default
`root`	No
`access`	No
`effect`	No
`scope_set`	No
`scope_removed`	No
`allowed_folder`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 22, 2026

removedInput schema / properties / confirm

Removed value: -{
-  "description": "Must be true to apply",
-  "type": "boolean"
-}

First observedJun 30, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Goes well beyond the annotations: it discloses that the limit is enforced across all file tools, that the OneDrive top level itself becomes inaccessible, that searches are narrowed, that a moved/deleted folder closes the OneDrive, and that changes take effect immediately. That is exactly the consequence-level detail destructiveHint=true hints at but cannot express.

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?

Four sentences, front-loaded with the core effect, then enforcement scope, then failure mode, then removal. The enumeration of read/list/search/write/delete/move is long but directly serves the 'which tools are affected' question, so every clause earns its place.

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?

An output schema exists so return values need not be described; for a scope-management tool with enforcement side effects across the whole tool surface, the description covers what an agent needs: what the limit bounds, what it blocks, how it fails, and how to undo it.

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 coverage is 100% and the schema already documents 'path relative to the root' with an example and 'Empty string removes the scope.' The description restates the empty-folder behavior and doesn't add format details (trailing slash, case sensitivity, validation errors) beyond the schema. Baseline 3 is appropriate.

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: 'Limits LMCP's access to one OneDrive to a single folder.' It also scopes the effect to named families of tools (onedrive_* and general file tools), which distinguishes it from every sibling in the list, none of which manage access scope.

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 the trigger condition implicitly (set a scope to constrain access) and explicitly documents the removal path: 'Pass an empty folder to remove the limit.' It doesn't state when an agent should prefer to leave scope unset or warn about prerequisites, but the usage context is clear enough to act on.

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

All Local MCP tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.