Local MCP

Run Diagnostics

run_diagnostics

Read-only

Runs a fast health check of all LMCP integrations on this machine, including the AI apps connected to LMCP (configured, never used, broken command, blocked config). Shows what works, what doesn't, and how to fix it. Optionally submits a report to the LMCP team.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`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.
`submit`	No	Send the diagnostic report to the LMCP team for analysis (default: false)

Output Schema

TableJSON Schema

Name	Required	Description
`report`	No	Full formatted text report
`summary`	Yes	Plain-language summary of overall health
`ok_count`	Yes	Number of integrations working
`submitted`	No	True when the report was sent to the LMCP team
`warn_count`	Yes	Number of integrations with warnings / not running
`web_agents`	No	Web (cloud-relay) clients, counts only: count (absent when unknown), relayed_calls_since_launch, last_remote_call
`integrations`	Yes
`problem_count`	Yes	Number of integrations with errors or missing permissions

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 30, 2026

addedOutput schema / properties / web_agents

Added value: +{
+  "description": "Web (cloud-relay) clients, counts only: count (absent when unknown), relayed_calls_since_launch, last_remote_call",
+  "type": "object"
+}

Changed1 schema field changedSep 29, 2026

removedOutput schema / properties / web_agents

Removed value: -{
-  "description": "Web (cloud-relay) clients, counts only: count (absent when unknown), relayed_calls_since_launch, last_remote_call",
-  "type": "object"
-}

Changed1 schema field changedSep 26, 2026

addedOutput schema / properties / web_agents

Added value: +{
+  "description": "Web (cloud-relay) clients, counts only: count (absent when unknown), relayed_calls_since_launch, last_remote_call",
+  "type": "object"
+}

Changed1 schema field changedSep 11, 2026

changedInput schema / properties / focus / description

Previous value: -"Integration to focus on: calendar, mail, contacts, reminders, omnifocus, outlook, notes, finder, onedrive, screen_recording, accessibility. Leave empty to check all."New value: +"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."

Changed1 schema field changedAug 17, 2026

changedInput schema / properties / focus / description

Previous value: -"Integration to focus on: calendar, mail, contacts, reminders, omnifocus, outlook, notes, finder, onedrive. Leave empty to check all."New value: +"Integration to focus on: calendar, mail, contacts, reminders, omnifocus, outlook, notes, finder, onedrive, screen_recording, accessibility. Leave empty to check all."

First observedJun 30, 2026

TDQS

A3.8/5.0

Behavior4/5

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

Annotations already mark the tool as readOnly and openWorld, and the description adds useful behavioral context: it is 'fast,' reports on integration health, and can optionally submit a report to the LMCP team. The optional submission aligns with openWorldHint and does not contradict readOnlyHint, since it is an external side effect rather than a local state mutation.

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?

Three sentences with no wasted words. The core purpose is front-loaded, the scope is precise, and the optional submission is stated at the end. Every sentence contributes.

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 full schema coverage, a present output schema, and helpful annotations, the description is largely complete. It could add a small caveat about only submitting reports when the user explicitly asks, but nothing critical is missing for correct invocation.

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%, and both parameters (focus and submit) already have clear descriptions. The description adds no new parameter-level meaning beyond restating the optional report submission, so the schema carries the load.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb and resource: it 'runs a fast health check of all LMCP integrations on this machine' and lists concrete status categories. It does not explicitly distinguish itself from diagnostic siblings like lmcp_doctor or lmcp_upgrade_diagnostics, so it falls just short of full sibling differentiation.

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

Usage Guidelines3/5

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

The description implies when to use the tool: when you need a health check that 'shows what works, what doesn't, and how to fix it.' However, it gives no explicit guidance about when not to use it or which diagnostic sibling to prefer, leaving the choice somewhat to 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.