Skip to content

Human Creative AI Workflow & Eval Lab MCP server

io.github.jdurey/human-creativejdureystreamable-httpv1.0.0Scanned

Remote MCP tools for 3-vendor AI workflow diagnostics, HAR sandboxes, 50v audits, and rubrics.

5 tools: 5 change things.

Tools: 0 delete, 0 irreversible, 5 write, 0 read.
  • Reads private data · 0
  • Reads text others write · 4
  • Can send data out · 1
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

5 tools here change things. Govern them.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the Human Creative AI Workflow & Eval Lab MCP server can do

The Human Creative AI Workflow & Eval Lab MCP server is published by the GitHub account jdurey. It has 5 tools. It can create or change data (5 tools: diagnose_ai_workflow, build_rea_har_agent_sandbox, audit_workflow_guardrails_50v, calibrate_judge_rubric_4family and 1 more), but cannot delete data. None of its tools only reads.

4 tools bring in text other people can write (build_rea_har_agent_sandbox, audit_workflow_guardrails_50v, calibrate_judge_rubric_4family and 1 more); 1 tool can send data out of your system (build_rea_har_agent_sandbox).

None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 14, 2026, version 1.0.0.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

5 tools

Changes things 5Claude Code: ask
  • audit_workflow_guardrails_50vRuns a 50-vector multi-family prompt-injection, policy-bypass, and stem-withheld answer-leak stress test judged by 3 independent LLM vendor families, producing a hardened v2.0 syst…Reads text others writeNo findings

    Why it is in this group

    • The description's first verb is "run": a word for a change.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Runs a 50-vector multi-family prompt-injection, policy-bypass, and stem-withheld answer-leak stress test judged by 3 independent LLM vendor families, producing a hardened v2.0 system prompt and 300-DPI Executive Audit PDF ($199 Stripe / $2.50 x402 USDC, or set preview_mode=true for a free 5-vector Edge dry-run).

    Annotations the server declares

    • title: 50-Vector Multi-Family Guardrail & Leak Stress-Test ($199 / Free Preview)
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
  • build_rea_har_agent_sandboxConverts a live web workflow URL or recorded HTTP Archive (.har v1.2) into an offline deterministic REA AgentEnv MCP sandbox (callable read/write tools + state transitions) paired …Reads text others writeCan send data outNo findings

    Why it is in this group

    • The description's first verb is "convert": a word for a change.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • outboundThe input takes a URL (input.target_url): a request to a URL can carry data to whoever runs it.
    Description, as the server wrote it
    Converts a live web workflow URL or recorded HTTP Archive (.har v1.2) into an offline deterministic REA AgentEnv MCP sandbox (callable read/write tools + state transitions) paired with 8 multi-step evaluation tasks, 3-vendor Judge-Trust reward verifiers, a 300-DPI Executive Benchmark PDF, and a SHA-256 verified .zip bundle ($299 Stripe / $3.50 x402 USDC, or set preview_mode=true for an instant free Edge dry-run).

    Annotations the server declares

    • title: Build Offline REA HAR-to-AgentEnv Sandbox ($299 Stripe / $3.50 x402 USDC / Free Preview)
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
  • calibrate_judge_rubric_4familyEliminates single-model self-preference bias and stochastic verdict flips by decomposing subjective quality criteria into deterministic Python checks + a 4-family Judge-Trust rubri…Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Eliminates single-model self-preference bias and stochastic verdict flips by decomposing subjective quality criteria into deterministic Python checks + a 4-family Judge-Trust rubric panel verified across byte-identical repeats ($149 Stripe / $2.00 x402 USDC, or set preview_mode=true for a free calibrated rubric preview).

    Annotations the server declares

    • title: 4-Family Judge-Trust Rubric Calibration ($149 / Free Preview)
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
  • compile_sop_to_scorm_qtiCompiles raw Markdown/text SOPs, runbooks, or training docs into LMS-ready SCORM 1.2 + 1EdTech QTI 3.0 XML mastery packages with stem-withheld blind-QA item verification ($49 Strip…Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Compiles raw Markdown/text SOPs, runbooks, or training docs into LMS-ready SCORM 1.2 + 1EdTech QTI 3.0 XML mastery packages with stem-withheld blind-QA item verification ($49 Stripe / $0.75 x402 USDC, or set preview_mode=true for a free Knowledge Component + QTI 3.0 XML item preview).

    Annotations the server declares

    • title: Compile SOP to Verified SCORM 1.2 & QTI 3.0 Packages ($49 / Free Preview)
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
  • diagnose_ai_workflowFREE live 3-stage cross-family AI workflow and JD diagnostic executed immediately on Cloudflare Workers AI (Mistral 24B intake -> Llama 3.3 70B 4-node DAG architect + Qwen 2.5 32B …No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    FREE live 3-stage cross-family AI workflow and JD diagnostic executed immediately on Cloudflare Workers AI (Mistral 24B intake -> Llama 3.3 70B 4-node DAG architect + Qwen 2.5 32B independent quality gate). Returns structured bottlenecks, silent failure modes, a 4-node DAG with human checkpoints, a 30-day rollout plan, and matched portfolio receipts.

    Annotations the server declares

    • title: Live 3-Vendor AI Workflow & JD Diagnostic (Free)
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write4
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out1
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 21, 2026, 19:21 UTC, unchanged since Nov 14, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
5
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed
  • WarnThe whole server

    The endpoint served tools/list without credentials, and the list has 5 tools that change things (5 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://josh-employer-funnel.josh-durey.workers.dev/mcp: tools/list returned 5 tools to an anonymous client, including diagnose_ai_workflow (write), build_rea_har_agent_sandbox (write), audit_workflow_guardrails_50v (write), calibrate_judge_rubric_4family (write), compile_sop_to_scorm_qti (write)

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

No check matched anything in these tool definitions. That is not a safety guarantee.

History

Changes to its tool definitions and to its remote endpoint, newest first.

No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.

Install

Pinned to version 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http human-creative https://josh-employer-funnel.josh-durey.workers.dev/mcp
claude mcp add --transport http human-creative https://josh-employer-funnel.josh-durey.workers.dev/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [],
    "ask": [
      "mcp__human-creative__diagnose_ai_workflow",
      "mcp__human-creative__build_rea_har_agent_sandbox",
      "mcp__human-creative__audit_workflow_guardrails_50v",
      "mcp__human-creative__calibrate_judge_rubric_4family",
      "mcp__human-creative__compile_sop_to_scorm_qti"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as human-creative. Review it before you use it.

Capability tags behind 4 rules
  • mcp__human-creative__build_rea_har_agent_sandbox untrusted-input, outbound
  • mcp__human-creative__audit_workflow_guardrails_50v untrusted-input
  • mcp__human-creative__calibrate_judge_rubric_4family untrusted-input
  • mcp__human-creative__compile_sop_to_scorm_qti untrusted-input

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/io.github.jdurey/human-creative/verify?hash=8673bc75fd8c3a8b4e3291f6c211c6856f710e285a96ddc856b445f98d8d1930" | jq -e '.changed == false'

Pinned hash 8673bc75fd8c, from Nov 14, 2026, 10:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/io.github.jdurey/human-creative/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for io.github.jdurey/human-creative
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.jdurey/human-creative.svg)](https://radar.anlyon.com/servers/io.github.jdurey/human-creative)

Source: MCP Registry · repository. Synced Nov 14, 2026, 11:17 UTC.

Human Creative AI Workflow & Eval Lab MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the Human Creative AI Workflow & Eval Lab MCP server safe?

No scan can promise that. What its definitions show: 5 tools, 5 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the Human Creative AI Workflow & Eval Lab MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the Human Creative AI Workflow & Eval Lab MCP server do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the Human Creative AI Workflow & Eval Lab MCP server have?

5 tools: 5 write. diagnose_ai_workflow, build_rea_har_agent_sandbox, audit_workflow_guardrails_50v, calibrate_judge_rubric_4family and compile_sop_to_scorm_qti.

Does the Human Creative AI Workflow & Eval Lab MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the Human Creative AI Workflow & Eval Lab MCP server send data to outside services?

1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): build_rea_har_agent_sandbox.

Has the Human Creative AI Workflow & Eval Lab MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 14, 2026.