NDE Network of Terms MCP server
Allows searching, looking up, and reconciling Wikidata terms and entities through the Network of Terms, returning labels, definitions, hierarchy, related terms, and Wikidata URIs for cultural heritage terminology.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
NDE Network of Terms MCP server
An MCP server for the Network of Terms (Termennetwerk) of the Dutch Digital Heritage Network (NDE). It lets AI assistants search, look up and reconcile cultural heritage terminology: AAT, Cultuurhistorische Thesaurus (CHT), RKDartists, GTAA, NTA, GeoNames, Wikidata, Iconclass, WO2-thesaurus and about fifty more sources.
Public endpoint (Streamable HTTP, stateless, no authentication):
https://mcp-termennetwerk.coret.org/Upstream API:
https://termennetwerk-api.netwerkdigitaalerfgoed.nl/(docs)Prototype, not an official NDE service. Vibe-coded with Claude Code (Opus 5.5).

Example in claude.ai: place names in a Dutch text about medieval Brabant linked to GeoNames URIs.
Use it
Endpoint: https://mcp-termennetwerk.coret.org/ (Streamable HTTP, no authentication).
claude.ai / Claude Desktop: Settings, Connectors, Add custom connector, URL
https://mcp-termennetwerk.coret.org/.
Claude Code:
claude mcp add --transport http termennetwerk https://mcp-termennetwerk.coret.org/ChatGPT: open chatgpt.com/plugins, select +, Add custom MCP
server, enter a name and the Server URL, choose No authentication, confirm the risk warning and
select Create as a plugin. Install the plugin and select it with @ in the prompt box. In Business
or Enterprise workspaces an admin may have to allow custom MCP servers.
GitHub Copilot (VS Code): Command Palette, MCP: Add Server, HTTP, the URL above, ID
termennetwerk. Or in .vscode/mcp.json (workspace) or the user mcp.json:
{
"servers": {
"termennetwerk": {
"type": "http",
"url": "https://mcp-termennetwerk.coret.org/"
}
}
}Microsoft Copilot Studio: in your agent, Tools, Add a tool, New tool, Model Context Protocol; enter a name, description and the URL above, authentication None, Create, then Add to agent.
Any other MCP client that supports Streamable HTTP works the same way. Example prompts:
"Which Network of Terms sources cover materials? Find the AAT and CHT terms for glas."
"Find the RKDartists URI for Rembrandt, born 1606."
"Give me the broader terms and English labels of
http://vocab.getty.edu/aat/300010855."
Related MCP server: LCSH MCP Server
Tools
Tool | What it does |
| Lists the terminology sources with name, description, genres, languages, availability and reconciliation URL. Filter by genre; metadata in |
| Searches up to 10 sources for a text query. Per source: |
| Resolves up to 200 known term URIs to the same compact term structure. Unknown URIs come back with |
| Matches up to 10 names against one source (W3C Reconciliation API) with scores, |
| Fetches selected properties (26 available, e.g. |
All tools are read-only (readOnlyHint: true). Each returns compact JSON as text and as
structuredContent.
Mapping to the upstream API
Tool | Upstream call | Argument mapping | Result mapping |
| GraphQL |
|
|
| GraphQL | source names are resolved to URIs; | union |
| GraphQL | duplicate URIs removed | union |
|
| array becomes | candidates get |
|
|
|
|
Term output: uri, prefLabel, altLabel, hiddenLabel, definition, scopeNote, seeAlso,
broader / narrower / related / exactMatch ({uri, label}), place (name, latitude,
longitude, addressCountry), person (givenName, familyName, birthDate, deathDate,
birthPlace, deathPlace, occupations, nationality, gender, parent, children,
spouse, sibling) and organization (type, foundingDate, dissolutionDate, location,
parentOrganization). Empty fields are omitted. Labels are string lists, or a language map
({"nl": [...], "en": [...]}) when languages is given.
Design decisions
Own TypeScript server (Express, MCP SDK, zod) instead of a generic GraphQL-to-MCP bridge: reconciliation is not GraphQL, and raw GraphQL unions are hard for a language model to read.
Stateless Streamable HTTP: a fresh MCP server per request, JSON responses (
enableJsonResponse), no sessions. Mounted on/and/mcp.limitis applied by this server, not upstream. Upstream applieslimitinside the SPARQL query before ranking, and some sources return alphabetical order: withlimit: 3RKDartists does not return Rembrandt himself (artists/66219). The server always fetches the upstream default (100), re-ranks (exact prefLabel, prefLabel prefix, exact altLabel, contains, rest; accent- and case-insensitive; upstream order breaks ties) and then cuts tolimit(default 20).Sources by name or URI. Language models know names better than URIs. Names are matched case-insensitively against
nameandalternateName, in Dutch and English; unknown names give an error with suggestions and a pointer tolist_sources.Byte budget. The JSON payload of every response stays under 60 000 bytes (it is sent twice, as text and as
structuredContent). When trimmed, the response hastruncated: trueand anotethat tells the model how to narrow the request;extend_termslists dropped rows inomitted.Caching in Redis (
tn:prefix): sources and search 1 h, lookup and extend 24 h, reconcile 1 h. Results containing any per-source error are never cached. Without Redis the server runs uncached (the source list is also kept in memory for 1 h).Load protection. At most 10 sources per search, 200 URIs per lookup, 10 reconcile queries, 100 extend ids; 60
tools/callrequests per minute per IP (other JSON-RPC methods are not counted); JSON-RPC batch arrays are rejected (MCP dropped batching in protocol 2025-06-18), so every tool call passes the limiter; outgoing requests are spaced at 10 per second.Privacy. The application log records tool name, item count, duration, cache hit and error class. It never records query text, URIs or IP addresses, also not for malformed request bodies (those get a JSON-RPC
-32700answer).Origin check against DNS rebinding: requests without
Origin(native clients) and fromclaude.ai/claude.comare allowed; add more withALLOWED_ORIGINS.Types generated from the live schema (
npm run codegen), because theLanguageenum is built from the catalog when upstream starts.
Observations on the upstream API
Checked against the live API on 2026-11-17.
terms.limitis applied before ranking (see above); results of some sources are alphabetical.Passing
languageschanges the result type fromTermstoTranslatedTerms(labels become{language, value}). Term and TranslatedTerm share field names with different types, so a query that selects both in one union needs aliases.Languageisen | fy | nl. Asking forfyonly gives mostly empty labels.timeoutMsabove 60000 is a GraphQL error. The AAT regularly needs more than the 10 s default.Reconciliation with
Accept-Language: enreturns emptynamevalues for some sources (RKD); the description still carries the labels.Reconciliation queries in one batch run sequentially upstream.
The reconciliation URL of sources whose URI has a fragment (AAT subsets, Canon van Limburg) is already percent-encoded (
%23) infeatures.url.Upstream sets
matchitself only for queries with properties.extendsilently leaves out ids it does not know.The documentation lists
exactMatchesas a Term field; the schema field isexactMatch. The documentation does not mentionterms.limitorTerm.person.
Development
Requires Node.js 22 or later (developed on 24).
npm install
npm test # unit tests on recorded fixtures (no network)
npm run dev # run from source on PORT (default 3004)
npm run build # compile to dist/
npm run codegen # regenerate GraphQL types from the live schema
npm run record # re-record tests/fixtures/ from the live APIEnvironment: PORT (3004), REDIS_URL (redis://localhost:6379/9, empty string disables),
ALLOWED_ORIGINS (comma separated), RATE_LIMIT_PER_MIN (60), UPSTREAM_RPS (10),
TN_API_BASE, LOG_LEVEL.
Deployment
The public instance runs behind Apache:
start.shis started by supervisor ([program:termennetwerk-mcp]), listening on127.0.0.1:3004.Apache vhost
mcp-termennetwerk.coret.orgproxies to it withProxyTimeout 180.GET /healthreturns{status, version, redis}; files inpublic/(landing page assets) are served as static files.
Discovery metadata
Path | Content |
| MCP Server Card (SEP-1649), from |
| alias of the server card |
| A2A v0.3 Agent Card, from |
| alias of the agent card |
When the version changes, update it in package.json and both cards.
This server is a prototype: it is deliberately not listed in MCP registries, and every response
carries X-Robots-Tag: noindex, nofollow (the landing page also has a robots meta tag). robots.txt
allows crawling on purpose: a URL blocked there can still end up in search results when linked
elsewhere, because the crawler never sees the noindex.
Validation recipe
npm testandnpm run buildsucceed.curl -s https://mcp-termennetwerk.coret.org/healthshows"status":"ok"and"redis":true.With the MCP Inspector (
npx @modelcontextprotocol/inspector, Streamable HTTP, the URL above):search_terms{"sources":["RKDartists"],"query":"Rembrandt","limit":3}: first term ishttps://data.rkd.nl/artists/66219.search_termsonhttp://vocab.getty.edu/aat, queryglas,languages: ["nl","en"],timeoutMs: 45000: labels come as a language map.lookup_termswith a CHT URI andhttps://example.org/nope: second itemok: false.reconcile{"source":"RKDartists","queries":[{"query":"Rembrandt","properties":[{"pid":"birthDates","v":"1606"}]}]}: top candidate 66219, score 100,match: true.reconcileonWikidata: alle entiteiten: error pointing tosearch_terms.extend_termsfor 66219 withprefLabels,birthDates:["Rembrandt"],["1606-07-15/1607"].
The same call twice: the second is logged with
"hit":true.
Not yet working / known limits
Tested end-to-end with claude.ai and Claude Code only. The ChatGPT, GitHub Copilot and Copilot Studio steps follow the vendors' documentation (November 2026) but have not been verified here yet.
No stdio transport: the server is meant to be used remotely.
No pagination:
search_termsreturns at most 100 terms per source (upstream maximum).Reconcile does not expose the
/suggestand/previewendpoints.Prototype: deliberately not listed in MCP registries and not indexed by search engines.
Roadmap
Optional stdio entry point for local use.
Dutch translation of this README.
Use
/suggest/propertyto keep the reconcile property list in sync automatically.Add
view/previewlinks of the reconciliation service to candidates.
Links
Termennetwerk: the Network of Terms of the Dutch Digital Heritage Network (NDE)
termennetwerk-api.netwerkdigitaalerfgoed.nl: upstream GraphQL and Reconciliation API
NDE documentation of the Network of Terms
mcp-termennetwerk.coret.org: the public instance and its landing page
mcp.openarchieven.nl: sister MCP server for Open Archives (Dutch genealogical records and transcriptions)
License
EUPL-1.2, the same license as the Network of Terms itself.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Search and read published GoVisit destination and local business data through 22 read-only tools.
Searchable catalog of 74 agent-ready APIs and tools. Search by task, get pricing model, agent controls and a tracked link for each tool, or list categories. Read-only, no auth.
Search and read the aicoolies catalog of AI and developer tools via a remote MCP knowledge graph.
Machine-readable entity discovery with provenance, trust and verified source evidence.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceAllows you to search for artworks, retrieve detailed information about specific artworks, access image tiles for artworks, and explore user-created collections from the Rijksmuseum.72MIT
- AlicenseCqualityDmaintenanceAllows AI assistants to search the Library of Congress Subject Headings (LCSH) through a simple API interface, making it easy to query and retrieve official subject headings and related terms.13MIT

OMOPHub MCP Serverofficial
AlicenseAqualityBmaintenanceProvides AI agents with instant access to 10M+ OMOP medical vocabulary concepts for searching, mapping, and navigating clinical codes across SNOMED, ICD-10, RxNorm, LOINC, and more.1168 npm7MIT- AlicenseBqualityBmaintenanceEnables querying the Dutch RCE Cultural Heritage Objects linked data endpoint via SPARQL, with ontology guidance and query validation for safe, accurate results.22European Union Public 1.2