Local MCP

LMCP Upgrade Diagnostics

lmcp_upgrade_diagnostics

Destructive

Returns LMCP's self-upgrade health (the LMCP app upgrading itself, not editing your data): current version, the last N app-version upgrade attempts with any errors, whether the upgrade cache dir is writable, and any stale LMCP binaries at alternate paths. Call this when the app's auto-upgrade seems stuck, or to explain why a user is on an old version.

Input Schema

Name	Required	Description	Default
`limit`	No	Max recent attempts to return (default 10, 1-50)
`confirm`	No	Ignored; kept for older clients.

Output Schema

Name	Required	Description
`cache_dir`	No
`running_from`	No	Real path of the currently running binary.
`binaries_found`	No	LMCP binaries found at known alternate paths.
`cache_writable`	No	Whether the update cache dir is writable (#1 silent-failure cause).
`current_version`	Yes
`last_success_at`	No	ISO 8601 timestamp of last successful update, empty if none.
`recent_attempts`	No	Recent update attempts, newest first.
`consecutive_failures`	No
`recent_attempts_count`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 24, 2026

changedInput schema / properties / confirm / description

Previous value: -"Must be true to run the check. Without it the call returns a preview and does nothing."New value: +"Ignored; kept for older clients."

Changed5 schema fields changedOct 22, 2026

addedInput schema / properties / confirm

Added value: +{
+  "description": "Must be true to run the check. Without it the call returns a preview and does nothing.",
+  "type": "boolean"
+}

changedInput schema / properties / limit / description

Previous value: -"Max recent attempts to return (default 10)"New value: +"Max recent attempts to return (default 10, 1-50)"

addedInput schema / properties / limit / maximum
```
Added value: +50
```
addedInput schema / properties / limit / minimum
```
Added value: +1
```

changedOutput schema / required

Previous value: -[
-  "current_version",
-  "running_from",
-  "cache_dir",
-  "cache_writable",
-  "last_success_at",
-  "consecutive_failures",
-  "binaries_found",
-  "recent_attempts",
-  "recent_attempts_count"
-]New value: +[
+  "current_version"
+]

AddedAug 2, 2026

TDQS

A3.5/5.0

Behavior2/5

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

The description discloses behavioral detail beyond the annotations: it explicitly probes cache-dir writability and looks for stale binaries, and asserts 'not editing your data'. That assertion directly conflicts with the annotations (readOnlyHint=false, destructiveHint=true), leaving the agent with contradictory safety signals for a tool it is told is purely informational. Because the safest interpretation of this mismatch is unresolved, an agent cannot know whether calling it has side effects.

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?

Two sentences, front-loaded with the resource and its returned contents, followed immediately by the call condition. The parenthetical clarification earns its place by preventing confusion with data-editing tools. Slight density in the enumerated list, but nothing is superfluous.

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?

For a zero-required-parameter diagnostic tool with an output schema, the description covers what is inspected and when to reach for it, so return-value detail is unnecessary. Its one real gap is the unresolved destructive/read-only conflict, which the description neither acknowledges nor explains away, leaving safety behavior ambiguous.

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%: the `limit` parameter's meaning, default (10), and range (1-50) are fully documented in the schema, and `confirm` is declared ignored there. The description's 'last N app-version upgrade attempts' aligns with `limit` but adds no new semantics. Baseline 3 applies when the schema does the work.

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 subject (LMCP's self-upgrade health) and enumerates exactly what is reported: current version, recent upgrade attempts and errors, cache-dir writability, and stale binaries. The parenthetical 'the LMCP app upgrading itself, not editing your data' usefully separates it from file-editing siblings. It stops short of distinguishing itself from the adjacent lmcp_doctor, lmcp_state, or run_diagnostics tools, which an agent would also see.

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?

It gives a concrete trigger: 'Call this when the app's auto-upgrade seems stuck, or to explain why a user is on an old version.' That is a clear use case rather than vague context. However, it offers no exclusions and never routes the agent to the obvious alternatives (lmcp_state for general state, lmcp_doctor for broader health, lmcp_install_upgrade for the remediation step).

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.