Borrowing it
Nothing to install: this file belongs to tternquist/marklogic-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/tternquist/marklogic-mcp/master/.claude/skills/marklogic-oauth-setup/SKILL.mdgit 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-oauth-setup)<a href="https://agentmods.dev/skills/tternquist/marklogic-mcp/marklogic-oauth-setup"><img src="https://agentmods.dev/badge/skills/tternquist/marklogic-mcp/marklogic-oauth-setup/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/tternquist/marklogic-mcp/marklogic-oauth-setup"><img src="https://agentmods.dev/badge/skills/tternquist/marklogic-mcp/marklogic-oauth-setup.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00108 | $0.01730 |
| Opus 5.5 | $0.00043 | $0.00692 |
| Sonnet 5.5 | $0.00022 | $0.00346 |
| Haiku 4.5 | $0.00011 | $0.00173 |
Grade A, and why
marklogic-oauth-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 2mo 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.
curl -u admin:password -X PUT \ How it starts
The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MarkLogic OAuth2 / OIDC Setup
The one thing that trips everyone up
MarkLogic matches JWT claims against external-names, not against role names or
usernames. A JWT carrying "roles": "rest-reader" does not grant the rest-reader
role until you explicitly register rest-reader as an external-name on that role.
Two modes, pick by token structure:
| Mode | Reads | Matches against | Register with |
|---|---|---|---|
oauth (JWT carries role claims) |
claim named by oauth-role-attribute |
each role's external-name list | sec:role-set-external-names() |
internal (users pre-provisioned) |
claim named by oauth-username-attribute (usually sub) |
each user's external-name list | sec:user-set-external-names() |
⚠ Always use sec:create-external-security()
Never build the external security document by hand with xdmp:node-insert-child() or
raw node manipulation. ML 12 requires authentication → cache-timeout →
authorization to appear before oauth-server; wrong ordering silently breaks
role assignment with no error.
Full working XQuery for the external security object, role/user mapping, and
verification is in references/oauth-configuration.md.
Token types and the real version floor
Local JWT validation — MarkLogic verifying the token signature itself instead of calling the provider on every request — arrived in 11.2.0. Before that, only reference tokens were available, validated by a round trip to the provider's introspection endpoint; reference-token support was deprecated in that same release. Everything in this skill assumes local JWT validation, so treat 11.2+ as the floor even though external security itself predates it.
Signature keys come from one of two places: static JWT secrets for symmetric algorithms, or a JWKS URI for asymmetric ones. Prefer the JWKS URI — it survives provider key rotation without a config change. Either way MarkLogic keeps the secrets in its internal keystore, so they do not appear in the external security document when you read it back; an empty-looking secrets field is not evidence of a missing key.
What ships with it
1 file 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.
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.
- 2mo ago First seen · 133 lines · 108 tokens per session scan A d3647e393a23
marklogic-oauth-setup is a skill published in the GitHub repository tternquist/marklogic-mcp (4 stars, last pushed 1mo ago), licensed MIT. It adds 108 tokens to every session and 1,730 once invoked, about $0.0004 per session on Opus 5.5. 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.
marklogic-oauth-setup compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| marklogic-oauth-setuptternquist/marklogic-mcp | Skill | 4 | 1mo ago | MIT | A | 108 | Claude Code |
| mem0-oss-to-platformmem0ai/mem0 | Skill | 68k | 2d ago | Apache-2.0 | A | 217 | Claude Code, Codex |
| azure-mgmt-botservice-dotnetmicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 78 | Claude Code |
| fastapi-router-pymicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 46 | Claude Code |
| dev-runtimelangwatch/langwatch | Skill | 5.0k | yesterday | Apache-2.0 | A | 172 | Claude Code |
| api-designericrisco/rsc-harness | Skill | 503 | 2d ago | MIT | A | 105 | Claude Code, Codex |
| migrate-segw-to-raparc-mcp/arc-1 | Skill | 252 | yesterday | MIT | A | 106 | Claude Code |