Skip to main content
Glama
Sign In
immich-photo-manager

immich-photo-manager

by drolosoft
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

Get capabilities

get_capabilities
Read-only

Check Immich server version, feature flags, and version quirks before offering OCR, smart search, or facial recognition. Use it at session start to confirm available features and read-only behavior.

Instructions

What this Immich server can do: version, feature flags and known quirks. Use this once at the start of a session to learn whether OCR, smart search or facial recognition are available before offering them, and which behaviours differ between Immich 2.x and 3.x. Read-only.

Returns: JSON with server_version, immich_major, features (the server's own
flags: ocr, smartSearch, facialRecognition, map, trash...) and quirks (plain
sentences about version-specific behaviour the caller should know). When the
API key may not read the feature flags, features is empty and a note says so;
the version and the quirks still come back.

Input Schema

NameRequiredDescriptionDefault

No arguments

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv2.0.2

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, and the description usefully adds the degraded-auth path: if the API key cannot read feature flags, features comes back empty with a note while version and quirks still return. That is real behavioral context an agent cannot infer from annotations; the redundant 'Read-only' restatement and absence of caching/latency notes keep it from a 5.

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 purpose sentence, then usage, then return shape — a sensible progression with no filler. The trailing 'Read-only' sentence duplicates the annotation and earns little, so it is not maximally tight.

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 zero-parameter read tool with an output schema already present, the description covers purpose, timing, the empty-features edge case, and the quirks field's nature (plain sentences about version-specific behavior). Nothing an agent needs to call it and interpret the result is missing.

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?

The tool takes zero parameters, so the baseline of 4 applies — there is no parameter semantics to document and nothing is missing.

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?

Names a specific resource and enumerates what it contains: server version, feature flags, and version-specific quirks. It is distinguishable from most siblings, but it does not address the obvious overlap with get_server_version, which also returns version information, leaving a small ambiguity for the agent.

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?

'Use this once at the start of a session... before offering them' gives a clear trigger condition and an explicit downstream purpose (don't promise OCR/facial recognition the server lacks). It stops short of 5 because it never excludes alternatives — an agent weighing this against get_server_version or ping gets no routing guidance.

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

Deploy Server

Other Tools