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/tternquist/marklogic-mcp/marklogic-project-setupnpx skills add tternquist/marklogic-mcp --skill marklogic-project-setupgit clone --depth 1 https://github.com/tternquist/marklogic-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/tternquist/marklogic-mcp/marklogic-project-setup)<a href="https://agentmods.dev/skills/tternquist/marklogic-mcp/marklogic-project-setup"><img src="https://agentmods.dev/badge/skills/tternquist/marklogic-mcp/marklogic-project-setup.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.00205 | $0.02934 |
| Opus 5 | $0.00102 | $0.01467 |
| Sonnet 5 | $0.00041 | $0.00587 |
| Haiku 4.5 | $0.00020 | $0.00293 |
Grade A, and why
marklogic-project-setup scanned grade A with 1 finding 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 3d ago.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
in `gradle.properties` makes every subsequent request (curl tests, module reloads, How it starts
The opening of the file, as written. The whole thing — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MarkLogic Project Setup (ml-gradle)
When to scaffold instead of using write tools
The MCP write tools (ml_document_put, ml_tde_install, ml_extension_put) change a
running database. They leave nothing in source control and nothing to promote to
another environment.
Scaffold a project instead when you hear any of:
- "build me an app / API / service / backend"
- "create a new project / repo"
- "set up MarkLogic for…"
- "add a REST endpoint" / "expose this as an API"
- "add an index" / "deploy to production" / "promote to staging"
- "I want this in CI/CD" / "version-controlled" / "multi-environment"
- any request naming a custom REST extension, transform, or module path
Ad-hoc exploration and one-off queries do not need a project.
First decision: plain ml-gradle or DHF?
| Use plain ml-gradle when | Use DHF when |
|---|---|
| custom application, not a data-integration pipeline | entity-centric integration from multiple source systems |
| a single content database | staging (raw) and final (mastered) databases needed |
| you want full control without DHF conventions | ingestion → mapping → matching/merging (mastering) |
| lighter footprint, simpler deploy | SmartMastering or Entity Services features required |
The template below is plain ml-gradle. For DHF, the dhf_* tools scaffold and run flows;
DHF still sits on an ml-gradle project, so most of this skill still applies.
Using the template
templates/ is a complete, deploy-ready ml-gradle tree. Copy it into the target
directory and rename:
cp -r templates/ <project-dir>/
Then replace throughout:
| Placeholder | Replace with |
|---|---|
myapp |
the application name (also in mlAppName, role filenames, TDE schema) |
8010 |
the REST port (mlRestPort) |
localhost |
the target host (mlHost) |
admin / admin |
real credentials — do not commit these |
Deploy with:
cd <project-dir>
gradle mlDeploy
Drop any part you don't need — src/main/ml-data, the roles, the REST extension, and
the environment overlays are all independent.
What ships with it
32 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/gradle-tasks.md 7.4 KB
- references/rest-extensions.md 8.2 KB
- templates/.gitignore 48 B
- templates/build.gradle 816 B
- templates/gradle-dev.properties 53 B
- templates/gradle-local.properties.example 746 B
- templates/gradle-prod.properties 54 B
- templates/gradle.properties 1.7 KB
- templates/README.md 2.6 KB
- templates/settings.gradle 27 B
- templates/src/main/dev-config/databases/content-database.json 97 B
- templates/src/main/ml-config/databases/content-database.json 485 B
- templates/src/main/ml-config/databases/schemas-database.json 46 B
- templates/src/main/ml-config/databases/triggers-database.json 47 B
- templates/src/main/ml-config/security/roles/1-myapp-reader.json 123 B
- templates/src/main/ml-config/security/roles/2-myapp-writer.json 144 B
- templates/src/main/ml-data/items/collections.properties 52 B
- templates/src/main/ml-data/items/item-001.json 91 B
- templates/src/main/ml-data/items/item-002.json 92 B
- templates/src/main/ml-data/items/permissions.properties 104 B
- templates/src/main/ml-modules/options/default.xml 288 B
- templates/src/main/ml-modules/root/lib/items-lib.sjs 1.8 KB
- templates/src/main/ml-modules/services/echo.sjs 690 B
- templates/src/main/ml-modules/services/items.sjs 2.5 KB
- templates/src/main/ml-modules/services/metadata/echo.xml 224 B
- templates/src/main/ml-modules/services/metadata/items.xml 621 B
- templates/src/main/ml-modules/transforms/identity.sjs 267 B
- templates/src/main/ml-modules/transforms/metadata/identity.xml 160 B
- templates/src/main/ml-schemas/tde/items.tdej 632 B
- templates/src/test/ml-modules/root/test/suites/items/setup.sjs 711 B
- templates/src/test/ml-modules/root/test/suites/items/teardown.sjs 303 B
- templates/src/test/ml-modules/root/test/suites/items/test-find-by-category.sjs 1022 B
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.
- 3d ago First seen · 235 lines · 0 tokens per session scan A 2b88817218ab
marklogic-project-setup is a skill published in the GitHub repository tternquist/marklogic-mcp (3 stars, last pushed 13d ago), licensed MIT. It adds 205 tokens to every session and 2,934 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
schema-exploration
Lists tables, describes columns and data types, identifies foreign key relationships, and maps entity relationships in a database. Use when the user asks about database schema, table structure, column types, what tables exist, ERD, foreign keys, or how entities relate.
agent-platform-rag-engine-management
Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…
deploy-docker-compose
Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…
moderator-page-migration
Port a moderator page from the main Next.js app (src/pages/moderator/) into apps/moderator. Use when asked to migrate, move or cut over a /moderator/ page to the spoke, or to port its tRPC procedures and Prisma services to SvelteKit loads/actions and Kysely.
dsql
Build with Aurora DSQL — manage schemas, execute queries, handle migrations, diagnose query plans, diagnose cluster performance, load data, and develop applications with a serverless, distributed SQL database. Covers IAM auth, multi-tenant patterns, MySQL-to-DSQL and PostgreSQL-to-DSQL schema conversion, foreign key…
sql-translate
Translate SQL queries between database dialects (Snowflake, BigQuery, PostgreSQL, MySQL, etc.).