Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/lucaspretti/drupal-mcp/drupal-apinpx skills add lucaspretti/drupal-mcp --skill drupal-apigit clone --depth 1 https://github.com/lucaspretti/drupal-mcpWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00139 | $0.00709 |
| Opus 5 | $0.00069 | $0.00354 |
| Sonnet 5 | $0.00028 | $0.00142 |
| Haiku 4.5 | $0.00014 | $0.00071 |
Grade A, and why
drupal-api scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Drupal MCP
This plugin exposes a Drupal site's core JSON:API as MCP tools. It works on any Drupal 10/11 site with the jsonapi core module enabled.
Tools
drupal_list_nodes— list nodes of a bundle (filter / sort / paginate).drupal_get_node— fetch one node by UUID.drupal_create_node— create a new node.drupal_update_node— patch attributes or relationships.drupal_delete_node— delete by UUID.drupal_list_taxonomy_terms— list terms in a vocabulary.drupal_list_users— list users.drupal_query_jsonapi— escape hatch for arbitrary GETs.
Conventions
- All identifiers are UUIDs (JSON:API canonical), not numeric
nids. Usedrupal_list_nodesfirst to find the UUID. - Bundle = content type machine name (e.g.
article,page). attributesis a flat object of JSON:API field names → values, e.g.{ title: '...', body: { value: '...', format: 'basic_html' }, status: true }.relationshipsfollow JSON:API shape:{ field_image: { data: { type: 'file--file', id: 'uuid' } } }.- Filter shorthand:
{ field_category: '1' }becomesfilter[field_category]=1. Operators:{ field_category: { value: '1', operator: '=' } }.
Auth + permissions
The MCP runs as a configured Drupal user. Permissions on that user's role decide what is reachable. For least privilege, create a mcp_bot user with a dedicated role that only grants the bundles/operations you actually need. JSON:API ignores the access_check flag — Drupal field access still applies.
Pre-flight
Before any write, confirm with the user:
- Which bundle / vocabulary?
- Which environment (prod vs dev)?
- Show the full payload before issuing the call.
Deletion is irreversible. Always read first, then ask, then delete.
Common patterns
Find the latest published articles:
drupal_list_nodes(bundle='article', filter={status: 1}, sort='-created', limit=5)
Update an article body:
drupal_update_node(bundle='article', uuid='<uuid>', attributes={ body: { value: '...', format: 'basic_html' } })
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 59 lines · 139 tokens per session scan A 23d2e16e9bdc
drupal-api is a skill published in the GitHub repository lucaspretti/drupal-mcp (0 stars, last pushed 20d ago), licensed MIT. It adds 139 tokens to every session and 709 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.