immich-mcp

Overview Schema Source Related Servers Discussions Admin

immich_albums

DestructiveIdempotent

Create, update, delete, share, and list photo albums, add or remove assets and users, and retrieve album details, statistics, and map markers. Writes require confirm:true for a dry-run preview first.

Instructions

immich_albums covers the albums toolset (13 operations). Auth header x-api-key. Writes need confirm:true and IMMICH_ALLOW_WRITES=true. Omit confirm for a dry-run preview. Actions: add_assets_to_album: PUT /albums/{id}/assets. Add assets to an album add_assets_to_albums: PUT /albums/assets. Add assets to albums add_users_to_album: PUT /albums/{id}/users. Share album with users create_album: POST /albums. Create an album delete_album: DELETE /albums/{id}. Delete an album get_album_info: GET /albums/{id}. Retrieve an album get_album_map_markers: GET /albums/{id}/map-markers. Retrieve album map markers get_album_statistics: GET /albums/statistics. Retrieve album statistics get_all_albums: GET /albums. List all albums remove_asset_from_album: DELETE /albums/{id}/assets. Remove assets from an album remove_user_from_album: DELETE /albums/{id}/user/{userId}. Remove user from album update_album_info: PATCH /albums/{id}. Update an album update_album_user: PUT /albums/{id}/user/{userId}. Update user role

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "action": "<action>"
    },
    "name": "immich_albums"
  }
}

Input Schema

Name	Required	Description
`body`	No	JSON body for the Immich operation. Secrets are redacted in output.
`query`	No	OpenAPI query parameters.
`action`	Yes	Immich operation to call.
`params`	No	OpenAPI path parameters, such as id.
`confirm`	No	Set to the boolean true to execute the write. Omit this field for a dry-run preview. false and the string true are rejected.
`checksum`	No	Optional x-immich-checksum header for asset upload.
`file_path`	No	Local file to upload as multipart assetData. Confirm-gated. The path is omitted from output.
`save_path`	No	Local path to save a binary download. If omitted, only metadata is returned. The path is omitted from output.
`sidecar_path`	No	Optional local XMP sidecar for asset upload. The path is omitted from output.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 5, 2026

TDQS

A3.8/5.0

Behavior4/5

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

Annotations already declare destructiveHint=true, idempotentHint=true, and openWorldHint=true, so the safety profile is partly covered. The description adds genuinely new behavior: the x-api-key auth header, the required server-side env flag IMMICH_ALLOW_WRITES=true, the confirm:true gate, and the dry-run preview path — none of which appear in annotations. It stops short of saying whether delete_album is irreversible or what a dry-run preview actually returns.

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?

Front-loaded with scope, auth, and the write-confirmation rule before the action catalog, which is exactly the ordering an agent needs. The 13-line action list is dense but each entry is a single clause with no filler, and the whole thing is appropriately sized for a 13-operation multiplexed tool.

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 13-action multiplexer with 9 nested params and no output schema, the description covers scope, auth, write gating, and per-action endpoint routing, which is most of what an agent needs. Gaps remain: it never states whether read actions (get_all_albums, get_album_info) skip the confirm gate, and it does not explain what the dry-run preview or metadata-only responses look like.

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%, so every parameter (body, query, params, confirm, checksum, file_path, save_path, sidecar_path) is already documented in the schema. The description restates the confirm gate but adds no new semantics for params/query/body or how they map to per-action path parameters such as {id}. Baseline 3 applies when the schema carries the weight.

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 the resource scope ("the albums toolset (13 operations)") and enumerates every action with a verb, resource, and HTTP method/path, e.g. "delete_album: DELETE /albums/{id}. Delete an album." An agent can identify exactly which operation to select. It does not explicitly distinguish itself from immich_assets or immich_search, so sibling differentiation is only implicit in the toolset name.

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?

It gives clear operational gating ("Writes need confirm:true and IMMICH_ALLOW_WRITES=true. Omit confirm for a dry-run preview"), which tells the agent how to invoke writes safely. However, there is no guidance on when to choose this toolset over immich_assets or immich_search, nor which actions are reads vs writes; usage is implied by the action list.

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

Deploy Server