Local MCP

Submit Diagnostics

submit_diagnostics

Destructive

Runs the same health check as run_diagnostics and sends the result to the LMCP team so they can look into a problem. What is sent: for each integration its status, the detail found and the fix hint, plus the LMCP version, the macOS version and the processor architecture. Without confirm=true it only PREVIEWS what would be sent: nothing is checked and nothing is sent (run_diagnostics shows the report itself, and only reads). With confirm=true the check runs and the report is sent; it cannot be recalled, so tell the user first.

Input Schema

Name	Required	Description
`focus`	No	Integration to focus on: calendar, mail, contacts, reminders, omnifocus, outlook, notes, finder, onedrive, screen_recording, accessibility — or `clients` for the AI apps connected to LMCP (or one app id, e.g. cursor). Leave empty to check all.
`confirm`	No	Must be true to actually send. Without it, returns a preview of the report — nothing is sent.
`remember`	No	With confirm: true, also stop asking for this kind of action from now on. Only when the person said so ("don't ask again"). The person can revoke it in LMCP or with set_always_allowed.

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 24, 2026

addedInput schema / properties / remember

Added value: +{
+  "description": "With confirm: true, also stop asking for this kind of action from now on. Only when the person said so (\"don't ask again\"). The person can revoke it in LMCP or with set_always_allowed.",
+  "type": "boolean"
+}

AddedOct 22, 2026

TDQS

A4.6/5.0

Behavior4/5

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

Adds substantial context beyond the annotations: it enumerates exactly what data leaves the machine (per-integration status, detail, fix hint, LMCP version, macOS version, processor architecture), and discloses irreversibility ("cannot be recalled, so tell the user first"). The annotations already flag destructiveHint and openWorldHint, but the data-disclosure inventory and the user-consent instruction are genuinely additive.

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?

Front-loaded with the action and recipient, then the payload list, then the confirm dichotomy, then the consent warning — a sensible order. Slightly dense with the mid-sentence parenthetical about run_diagnostics, but every clause carries information.

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 destructive, open-world submission tool the critical unknowns are what is transmitted, whether it can be undone, and how to preview — all answered. Annotations carry the safety profile and an output schema exists, so return values need no explanation.

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 adds real meaning: confirm gates both the check and the send ("nothing is checked"), and remember is framed as a persistent permission change the user must request and can revoke. It does not touch focus, leaving one parameter entirely to 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 and resource ("Runs the same health check as run_diagnostics and sends the result to the LMCP team") and explicitly distinguishes itself from the sibling run_diagnostics. An agent knows immediately this is diagnostics plus submission, not just diagnostics.

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?

Gives an explicit two-branch rule: without confirm=true it only previews and checks nothing; with confirm=true it runs and sends irreversibly. It also names the alternative (run_diagnostics) and its role (shows the report, only reads), so tool selection is resolved without inference.

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.