Provides tools for searching files via macOS Spotlight (mdfind) by full-text, filename, or raw Spotlight queries, and reading file metadata with mdls.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@mcp-for-spotlight find all PDFs in my Downloads folder containing "invoice""
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Ein kleiner MCP-Server (Model Context Protocol), der die macOS-Spotlight-Suche
als Tools bereitstellt. Er kapselt mdfind (Volltext- und Metadaten-Suche über
den Spotlight-Index) und mdls (Metadaten einer Datei). Systemweite
Dateisuche, nicht auf eine App beschränkt.
MCP (Model Context Protocol) ist ein offener Standard, über den KI-Anwendungen (der Host, etwa Claude Desktop oder Claude Code) mit externen Werkzeugen und Daten sprechen. Ein Server stellt Fähigkeiten (Tools) bereit und weiß selbst nichts von KI. Kommunikation über JSON-RPC 2.0, hier per stdio.
Related MCP server: @codesift/mcp
locate oder AppleScriptSpotlight (mdfind) indexiert Datei-Inhalt und Metadaten (Betreff,
Autor, Typ, Datum) und wird live aktualisiert. Der richtige Index für
Inhaltssuche.
locate kennt nur Datei-Pfade/-Namen, keinen Inhalt, und ist oft
veraltet oder inaktiv.
AppleScript-whose (etwa in Mail) ist ein linearer Scan ohne Index.
Tool | Zweck |
| Dateien per |
| Spotlight-Metadaten einer Datei per |
spotlight_search erwartet genau eine Suchart:
text — Freitext (Volltext + Metadaten), z. B. "Quartalsbericht"
name — Teilstring im Dateinamen
query — rohe Spotlight-Abfrage, z. B.
kMDItemContentType == "com.adobe.pdf" && kMDItemFSName == "*Rechnung*"c
Optional onlyIn (auf ein Verzeichnis begrenzen) und limit (Vorgabe 50).
npm installKein Build-Schritt: reines ESM-JavaScript, läuft direkt mit Node (>= 18).
Geschützte Orte (z. B. ~/Library/Mail, ~/Library/Messages) liefern nur
Treffer, wenn der ausführende Prozess Full Disk Access hat
(Systemeinstellungen → Datenschutz & Sicherheit → Festplattenvollzugriff, dort
das Terminal bzw. den Node-Host freigeben). Ohne FDA sind normale
Nutzerdateien trotzdem durchsuchbar.
npm run inspectClaude Code:
claude mcp add spotlight -- node /absolute/path/to/mcp-for-spotlight/src/index.jsClaude Desktop, in ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"spotlight": {
"command": "node",
"args": ["/absolute/path/to/mcp-for-spotlight/src/index.js"]
}
}
}spotlight_search name="Rechnung" onlyIn="/Users/me/Documents"
spotlight_search query='kMDItemContentType == "com.adobe.pdf"' onlyIn="/Users/me/Downloads"
spotlight_metadata path="/Users/me/Downloads/x.pdf" attributes=["kMDItemContentCreationDate"]MIT
Liest die von Spotlight indexierten Metadaten einer Datei (mdls). Ohne attributes alle, sonst nur die genannten (z. B. kMDItemContentType, kMDItemContentCreationDate).
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes | Absoluter Dateipfad | |
| attributes | No | Attributnamen, z. B. ["kMDItemContentType", "kMDItemPixelHeight"] |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description reveals that it uses mdls under the hood and that omitting attributes returns everything, which is useful behavioral context beyond the schema. It notes the read-only nature ('liest') implicitly. However, no annotations are present, and it doesn't disclose error behavior for nonexistent files, non-indexed locations, or what happens when attributes are unavailable.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two compact sentences with zero waste. Front-loaded with the tool's purpose and efficiency. The example attribute names embedded in the description are helpful and concise.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple read tool with 2 well-described parameters and no output schema, the description adequately covers what's needed: what it reads, how attribute filtering works, and the default behavior. The behavior is fully specified given the schema coverage, though it could mention that results depend on Spotlight indexing availability.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, with both parameters well-documented in the schema itself (path as absolute file path, attributes as array of attribute names with examples). The description adds a small clarification that omitting attributes returns all metadata, slightly augmenting the schema meaning but not substantially beyond it.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb (reads/Liest), the resource (Spotlight-indexed file metadata via mdls), and the behavior (all attributes by default, named subset otherwise). It's specific and distinguishable from spotlight_search, the sibling that performs searches rather than reading metadata for a given path.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explains the attribute filtering behavior (all vs. specific named attributes) which informs usage, but it doesn't explicitly state when to prefer this over spotlight_search or what kind of use cases it serves. The tool itself is self-evident for reading metadata, but no exclusions or alternative-navigation guidance is provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Durchsucht den macOS-Spotlight-Index (mdfind) nach Dateien: Volltext und Metadaten. Genau eine Suchart angeben: text (Freitext), name (Dateiname) oder query (rohe Spotlight-Abfrage). Liefert Dateipfade. Hinweis: geschützte Orte wie ~/Library/Mail liefern nur mit Full Disk Access Treffer.
| Name | Required | Description | Default |
|---|---|---|---|
| name | No | Teilstring im Dateinamen | |
| text | No | Freitext (Volltext + Metadaten), z. B. "Quartalsbericht" | |
| limit | No | Ausgabe auf so viele Pfade begrenzen (Vorgabe 50) | |
| query | No | Rohe Spotlight-Abfrage, z. B. kMDItemContentType == "com.adobe.pdf" | |
| onlyIn | No | Suche auf ein Verzeichnis begrenzen (absoluter Pfad) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the behavioral disclosure burden. It discloses output (file paths), the single-search-type constraint, and the Full Disk Access limitation for protected locations. However, it does not specify whether limit applies across all three modes, the default formatting, or that mdfind output could be huge without a limit.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is compact (two sentences) and front-loaded with the purpose. It packs purposeful detail into the caveat sentence. Minor inefficiency: the tool name is in German but the search-mode keywords are English, which is understandable but slightly awkward.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a search tool with 5 parameters at 100% schema coverage, the description is reasonably complete. It explains the three search modes, the output format, and the protected-locations caveat. It lacks an explicit mention of behavior when no search-type param is given (error vs empty), and doesn't contrast with spotlight_metadata, but these are minor gaps given good schema coverage.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so parameters are already documented in the schema. The description adds value by clarifying the mutual exclusivity of text/name/query and the requirement to choose exactly one, which goes beyond the individual parameter docs. It doesn't add much per-parameter detail but the schema coverage makes that acceptable.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb+resource ('Durchsucht den macOS-Spotlight-Index (mdfind) nach Dateien') and clearly distinguishes three search modes (text, name, query). It also differentiates from the sibling tool spotlight_metadata by focusing on files/full-text, adding scoping clarity.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives clear context on when to use this tool (searching files via mdfind) and explicitly states that exactly one search type must be provided. It mentions the protected-locations caveat. However, it does not explicitly contrast against spotlight_metadata (the sibling) or state when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v0.1.0spotlight_metadataspotlight_searchScored across 2 tools
The two tools have clearly distinct purposes: one searches the Spotlight index, the other reads metadata for a specific file. No meaningful overlap exists between search and metadata retrieval.
Both tools follow the consistent 'spotlight_<operation>' convention: spotlight_search and spotlight_metadata. The naming pattern is clear and predictable for a server scoped to Spotlight functionality.
With only 2 tools, the surface feels thin for a domain that could reasonably include other operations (e.g., file info, indexed-item lifecycle ops). However, the two tools cover the core search+metadata workflow reasonably for a Spotlight-focused server.
The pair covers the two primary Spotlight operations (search and metadata retrieval), which is the obvious core workflow. However, there are minor gaps—e.g., no tool for getting indexed status, no way to count results, or handling common variations like filtering by path—though agents can usually compose around these with the search tool.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Personal assistant MCP server with search, execute, packages, jobs, secrets, and integrations.
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
MCP server for searching Airweave collections with natural language queries.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/shaack/mcp-for-spotlight'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
