How do I use Städel Museum MCP Server?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Städel Museum MCP Server List the available museum sets." 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.

Städel Museum MCP Server

by topoftheblock

Overview Schema Related Servers Score Discussions

TypeScript

Remote

Städel Museum MCP Server

A Model Context Protocol server that gives AI assistants direct access to the Städel Museum Digital Collection. It talks to the museum's public OAI-PMH interface (LIDO metadata format), so an assistant can harvest object records, read rich multilingual metadata, and display high-resolution artwork images — with an interactive browsing UI (MCP Apps) on top.

This is a personal portfolio project built to demonstrate working with the Model Context Protocol, an OAI-PMH/LIDO harvesting API, and MCP Apps interactive UIs end-to-end — not an official Städel Museum product.

Features

Tool	Description
`list-sets`	Lists the OAI-PMH sets (e.g. Masterpieces, Prints and Drawings) available to filter by.
`search-museum-objects`	Harvests object identifiers, filtered by `set` and/or a `from`/`until` date range, with pagination via `resumptionToken`.
`get-museum-object`	Resolves one object's full LIDO record into clean, normalized JSON — titles, artists, date, medium, dimensions, image, license — plus the image itself.
`open-staedel-explorer`	Opens an interactive MCP App UI for browsing and filtering the collection visually, in hosts that support it.

Because the Städel exposes its collection through OAI-PMH (a harvesting protocol, not a search engine), there is no full-text keyword search — you filter by set and/or date range, then fetch full details per object. The tool descriptions make this explicit so the assistant doesn't assume Google-style search is available.

Related MCP server: artic-mcp

Architecture

src/
├── index.ts                 # entry point (stdio or --http)
├── server-utils.ts           # transport wiring (stdio / Streamable HTTP)
├── StaedelServer.ts           # registers tools + the explorer UI resource
├── api/
│   └── StaedelApiClient.ts    # OAI-PMH client: fetch, retry, XML→JSON, error mapping
├── tools/
│   ├── ListSetsTool.ts
│   ├── SearchMuseumObjectsTool.ts
│   ├── GetObjectTool.ts        # flattens raw LIDO XML into normalized metadata
│   └── OpenStaedelExplorerTool.ts
├── ui/
│   └── explorerResource.ts     # builds the self-contained MCP App HTML for the explorer
├── types/types.ts             # Zod schemas for tool inputs/outputs
└── utils/RateLimiter.ts       # simple request-spacing limiter for the museum API

The get-museum-object tool does the interesting work: LIDO is a verbose, multilingual, deeply nested XML format (via fast-xml-parser), and GetObjectTool flattens it into a small, stable JSON shape — resolving xml:lang variants (preferring English, falling back to German), picking the highest-resolution image link, and reading each object's actual rights statement instead of assuming one blanket license.

Licensing & Attribution (important)

Metadata harvested from the OAI-PMH interface is CC0 1.0 (public domain).
Images are typically CC BY-SA 4.0 Städel Museum, Frankfurt am Main, though some objects carry a different rights statement (e.g. Public Domain Mark) — get-museum-object reports the actual license for each object rather than hard-coding one.
Whenever an assistant displays or describes an image from this server, it should include the credit line reported in the license field.

Prerequisites

Node.js v18 or later
pnpm (via corepack)

Installation

git clone https://github.com/topoftheblock/staedel-mcp.git
cd staedel-mcp
corepack enable
pnpm install
pnpm run build

Running

Stdio (used by Claude Desktop, Claude Code, and most MCP clients):

node dist/index.js

Streamable HTTP (for testing with clients that connect over HTTP):

node dist/index.js --http
# -> http://localhost:3001/mcp  (override with PORT env var)

Add it to Claude Desktop / Claude Code

Add to your MCP client's config (e.g. claude_desktop_config.json):

{
  "mcpServers": {
    "staedel-museum": {
      "command": "node",
      "args": ["/absolute/path/to/staedel-mcp/dist/index.js"]
    }
  }
}

Try it with the MCP Inspector

npx @modelcontextprotocol/inspector node dist/index.js

Development

pnpm run watch   # tsc --watch
pnpm run check   # type-check without emitting

The server is a thin, dependency-light wrapper: StaedelApiClient owns all HTTP/XML concerns, each tool class is a small, independently testable unit, and src/types/types.ts defines the Zod schemas that make tool inputs/outputs self-documenting to the model.

Configuration

Environment variable	Default	Purpose
`STAEDEL_API_TIMEOUT_MS`	`10000`	Per-request timeout to the Städel API.
`PORT`	`3001`	Port for `--http` mode.

Reference

Available Tools

4 tools

get-museum-objectA

Get detailed information about a specific Städel museum object by its OAI identifier (e.g. oai:DE-MUS-048017:2442) or bare object number (e.g. 2442). Returns metadata and optionally the high-resolution image.

ParametersJSON Schema

Name	Required	Description	Default
`objectId`	Yes	The OAI identifier (e.g., oai:DE-MUS-048017:2442) or bare object number
`returnImage`	No	Whether to return the image (if available) as base64

Output Schema

ParametersJSON Schema

Name	Required	Description
`object`	Yes	Detailed object data mapped from LIDO metadata

TDQS

A4/5.0

Behavior3/5

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

No annotations are provided, so the description is the sole source. It discloses the return includes metadata and optionally a base64 image, but does not detail potential errors, authentication requirements, or the extent of 'detailed information'. Adequate but not comprehensive.

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?

The description is two sentences long, front-loaded with the main action, and contains no extraneous words.

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?

Given the simple tool with only two parameters and an existing output schema, the description adequately covers the input format and return behavior. It could mention potential error responses, but overall it is sufficient for an agent to use correctly.

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% and the description adds minimal new information beyond the parameter descriptions, except mentioning that the image is returned as base64. The description does not elaborate on the objectId format beyond what the schema says.

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

Purpose5/5

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

The description clearly states the tool fetches detailed information for a single Städel museum object using an OAI identifier or bare number, distinguishing it from sibling tools like 'search-museum-objects' and 'list-sets'.

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?

The description specifies the input format (OAI identifier or bare object number) and the optional return of an image. It implies usage when you have a specific object ID, but does not explicitly contrast with siblings or mention when to avoid using it.

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

list-setsA

Lists all organizational sets (collections/departments) available in the Städel Museum OAI-PMH interface.

ParametersJSON Schema

Name	Required	Description	Default
No parameters

Output Schema

ParametersJSON Schema

Name	Required	Description
`sets`	Yes

TDQS

A3.6/5.0

Behavior2/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure, but it only states the basic function. It does not reveal whether the operation is read-only, how results are paginated, authentication requirements, or any side effects. The agent is left to infer behavior from the name and minimal text.

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?

The description is a single sentence with no unnecessary words. It is front-loaded with the action and resource, making it easy to parse quickly.

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?

Given the simplicity (no parameters, output schema present), the description adequately explains the tool's purpose and scope. However, it could mention whether the list is exhaustive or paginated, or clarify the role of OAI-PMH, but overall it is sufficient for a basic list endpoint.

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?

There are no parameters (schema coverage 100%), so the description adds marginal value by clarifying that 'sets' refer to collections/departments and specifying the data source. For a zero-parameter tool, this is above the baseline of 4.

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

Purpose5/5

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

The description clearly specifies the action ('lists'), the resource ('organizational sets'), and adds explanatory context ('collections/departments') and the source ('Städel Museum OAI-PMH interface'), which distinguishes it from sibling tools that deal with museum objects or a specific explorer.

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

Usage Guidelines2/5

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

The description provides no guidance on when to use this tool versus alternatives (e.g., when searching for objects vs. listing sets), and does not mention any prerequisites or contextual scenarios.

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

open-staedel-explorerA

Open the interactive Städel Explorer app for browsing and filtering objects visually.

ParametersJSON Schema

Name	Required	Description	Default
`set`	No	Optional OAI Set to filter the explorer
`from`	No	Optional datestamp (YYYY-MM-DD)

Output Schema

ParametersJSON Schema

Name	Required	Description
`initialState`	Yes	Initial app launch state for the Städel Explorer UI

TDQS

A3.5/5.0

Behavior2/5

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

With no annotations provided, the description carries full responsibility for disclosing behavior. It says 'Open the interactive...app' but does not explain what this means in practice—e.g., does it launch a browser, return a URL, or require specific permissions? The effect of the optional parameters on behavior is also omitted.

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?

The description is a single sentence of 14 words that is concise and front-loaded with the action and purpose. Every word contributes meaning; there is no fluff.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given that an output schema exists, the description need not explain return values. However, the tool is simple (open an app) but lacks details about what the output actually is (e.g., a URL, a redirect). The description is complete for a basic understanding but leaves some ambiguity about the interaction model.

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 the baseline is 3. The description does not add any additional meaning to the parameters beyond what is already in the schema (set and from). No further elaboration is provided.

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

Purpose5/5

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

The description uses a specific verb ('Open') and resource ('the interactive Städel Explorer app'), and clearly indicates the tool's purpose is for visual browsing and filtering. This distinguishes it from sibling tools that list sets, get single objects, or search objects.

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 the tool is used when a visual interface is desired ('for browsing and filtering objects visually'), but it does not explicitly state when to use this tool versus alternatives like 'search-museum-objects' or provide any exclusions or prerequisites.

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

search-museum-objectsA

Harvests a list of object identifiers from the Städel Museum. Note: This uses OAI-PMH, so standard full-text keyword searching is not supported. You must filter by date or Set. Returns a list of identifiers to be used with the get-museum-object tool.

ParametersJSON Schema

Name	Required	Description
`set`	No	Filter by an OAI-PMH Set spec (retrieved via list-sets tool)
`from`	No	Datestamp (YYYY-MM-DD) to filter records modified from this date
`until`	No	Datestamp (YYYY-MM-DD) to filter records modified until this date
`resumptionToken`	No	Pass this token to get the next page of results. Do not pass other filters if using this token.

Output Schema

ParametersJSON Schema

Name	Required	Description
`records`	Yes	List of OAI identifiers matching the query
`pageCount`	Yes	Number of records returned in this current request
`resumptionToken`	No	Token to retrieve the next page of results

TDQS

A4/5.0

Behavior3/5

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

With no annotations, the description handles transparency. It discloses the OAI-PMH protocol, the inability to do full-text search, and that it returns identifiers only. However, it does not mention rate limits, authentication, or pagination behavior (though resumptionToken hints at it). It adds some value beyond the schema but could be more explicit about operational constraints.

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?

The description is three sentences with no wasted words. The first sentence states the core purpose, the second clarifies limitations and usage constraints, and the third explains how the output should be used. It is front-loaded and efficiently structured.

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?

The tool has 4 parameters, none required, and an output schema exists. The description covers the key aspects: what it returns (identifiers), how to use them (with get-museum-object), and the constraint to filter. It does not explain pagination in detail or error handling, but for a listing tool, this is largely sufficient.

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%, so baseline is 3. The description adds context by stating that filtering by date or Set is required, which reinforces the purpose of 'from', 'until', and 'set' parameters. However, it does not add new information beyond what the schema already provides. The description for 'resumptionToken' is not reiterated but is clear in schema.

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

Purpose5/5

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

The description clearly states the verb 'harvests' and the resource 'list of object identifiers from the Städel Museum'. It distinguishes itself from siblings by noting the use of OAI-PMH, the lack of full-text search, and the requirement to filter by date or Set, and it explicitly connects to the sibling get-museum-object tool.

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?

The description tells when to use the tool (to get identifiers via OAI-PMH) and when not to (no full-text search). It specifies required constraints (must filter by date or Set) and mentions the output's purpose for use with get-museum-object. It does not explicitly exclude alternatives like list-sets or open-staedel-explorer, but the context is clear enough.

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

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

4 tool updatesv1.0.0Jul 30, 2026
- First observedget-museum-object
- First observedlist-sets
- First observedopen-staedel-explorer
- First observedsearch-museum-objects

Install Server

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A4.1/5.0

Disambiguation5/5

Each tool has a distinct purpose: list-sets retrieves organizational sets, search-museum-objects harvests identifiers for objects, get-museum-object retrieves full details of a specific object, and open-staedel-explorer provides an alternative visual browsing experience. There is no overlap in functionality.

Naming Consistency5/5

All tools follow a consistent verb-noun pattern with lowercase and hyphens (e.g., list-sets, get-museum-object). The verbs are descriptive and the nouns clearly indicate the resource or action, making it easy to understand the tool's function.

Tool Count5/5

With 4 tools covering set listing, object search, object detail retrieval, and a visual explorer, the count is well-scoped and appropriate for the domain. There are no redundant or missing tools for the intended functionality.

Completeness5/5

The tool set covers the complete workflow: discover sets (list-sets), find objects within a set (search-museum-objects), get detailed information (get-museum-object), and optionally explore visually (open-staedel-explorer). Given the OAI-PMH constraints, there are no essential gaps.

Maintenance

ActivitySlowing

ResponsivenessSyncing

Resources

GitHub Repository

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

met-museum-mcp-server A
io.github.cyanheads
MET Museum collection via MCP — 500K+ artworks, metadata, provenance, open-access images.
Art & Culture Open Data
324
Intelligence Aeternum D
io.github.codex-curator
AI training dataset marketplace: 2M+ museum artworks with Golden Codex enrichment
Art & Culture Open Data Research & Data
321
smithsonian-mcp-server A
io.github.cyanheads
Search 14.5M Smithsonian Open Access objects, get CC0 images, find cross-collection connections.
Art & Culture Open Data
622
Clevelandart A
io.github.pipeworx-io
Cleveland Museum of Art Open Access API (~63k artworks, many CC0)
Art & Culture Open Data
3521

Related MCP Servers

Met Museum MCP Server
Art & Culture Search
mikechao
A
license
A
quality
C
maintenance
A MCP Server that lets user ask AI models to discover the collection of the Metropolitan Museum of Art. Adds the discovered art works as Resources on the server.
Updated 4 months ago (2026-04-27 22:07 UTC)
4
2,264
33
MIT
artic-mcp
Art & Culture Search Content Management Systems
mikechao
A
license
B
quality
C
maintenance
A server that provides access to the Art Institute of Chicago Collection through natural language interactions. This server allows AI models to search the Art Institute of Chicago Collection and have art works available as a Resource.
Updated a year ago (2025-07-21 17:26 UTC)
6
22
5
MIT
Cultural Heritage MCP Server
Art & Culture Search
RabiaDogan41
F
license
Not graded
quality
D
maintenance
Provides access to European cultural heritage collections and artworks, allowing users to search for items, get detailed information about specific artworks, browse collections by institution, and receive AI-powered recommendations based on interests.
Updated a year ago (2025-05-28 12:41 UTC)
1
-
rijksmuseum-mcp+
Art & Culture Search Research & Data
kintopp
A
license
A
quality
A
maintenance
Lets you explore the Rijksmuseum's artwork collections through natural conversation with an AI assistant.
Updated 4 days ago (2026-09-02 19:30 UTC)
13
15
MIT

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/topoftheblock/staedel-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server