Skip to main content
Glama
Sign In

Human Creative AI Workflow & Eval Lab

by io.github.jdurey
OverviewDiscussionsAdmin

Server Details

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

If you are the author of this connector, you can claim ownership by verifying the domain or GitHub account it belongs to. Claimed connector authors can inspect health checks, view analytics, and manage their listing.
Status
Healthy
Uptime
100.0% over the last 24 hours
Last Tested
Transport
Streamable HTTP · MCP 2025-03-26
URL
Repository
jdurey/human-creative-mcp
GitHub Stars
0
ChatGPT
–
Claude
–

TDQS

A3.6/5.0

Scored across 5 tools

Disambiguation4/5

Each tool targets a distinct pipeline stage: free diagnosis, guardrail audit, sandbox construction, rubric calibration, and SOP-to-SCORM compilation, so an agent can usually pick the right one. There is mild overlap in that three tools produce multi-vendor 'judge-trust' evaluation artifacts, which could cause confusion between audit_workflow_guardrails_50v, calibrate_judge_rubric_4family, and build_rea_har_agent_sandbox when a user just wants 'evaluate my workflow.'

Naming Consistency4/5

All names are snake_case verb_object patterns (audit_, build_, calibrate_, compile_, diagnose_) with clear leading verbs. Minor deviations come from appended numeric/qualifier suffixes (_50v, _4family) and one long compound (build_rea_har_agent_sandbox) that make the names harder to scan but not inconsistent in style.

Tool Count5/5

Five tools is well-scoped for a workflow/eval lab, and each represents a substantial, non-redundant pipeline rather than a thin wrapper. No tool feels like filler and the count stays comfortably within the ideal 3-15 range.

Completeness4/5

The surface forms a coherent funnel (diagnose -> audit -> build sandbox -> calibrate rubric -> compile training) covering generation of prompts, sandboxes, rubrics, and LMS packages. Gaps exist: there is no tool to actually execute/score an already-built sandbox or rubric, and no way to list or retrieve prior generated artifacts, leaving minor dead ends agents must work around.

Available Tools

5 tools
audit_workflow_guardrails_50vAInspect

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).

Inputs: client_name (required), bot_or_workflow_name (required), system_prompt_or_rules (required), preview_mode, +2 more.

build_rea_har_agent_sandboxBInspect

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).

Inputs: client_name (required), workflow_name (required), target_url, preview_mode, +3 more.

calibrate_judge_rubric_4familyBInspect

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).

Inputs: client_name (required), task_domain (required), current_rubric (required), preview_mode, +2 more.

compile_sop_to_scorm_qtiAInspect

Compiles raw Markdown/text SOPs, runbooks, or training docs into LMS-ready SCORM 1.2 + IMS 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).

Inputs: course_title (required), sop_markdown (required), client_name, preview_mode, +2 more.

diagnose_ai_workflowB
Read-onlyIdempotent
Inspect

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.

Inputs: input (required), mode, org_hint.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • Testers AI CARBON Test Harness

      jarbon
      A
      license
      Not graded
      quality
      B
      maintenance
      A local, MIT-licensed AI test harness with 10 MCP tools and 11 prompts for risk-based testing, accessibility checks, quality maps, evidence, and interactive reports. Runs over stdio against an explicitly configured project folder; uses the host AI coding agent, with no hosted backend or runtime telemetry.
      2
      MIT

    • Sandbox MCP Server

      nagaozen
      A
      license
      Not graded
      quality
      B
      maintenance
      Enables AI agents to create isolated Docker runtimes, execute commands, manage workspace files, drive a headed browser, and retrieve artifacts through eight semantic MCP tools, with progressive capability discovery and explicit sandbox lifecycle.
      Apache 2.0
    Try in Browser
    Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

    Glama MCP Gateway

    Add one secure layer between your agents and this server.

    Resources