MDAN
by khalilbenaz
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MDAN_PROJECT_ROOT | Yes | The root directory of the MDAN project |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| prompts | {
"listChanged": true
} |
| resources | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| mdan_list_workflowsA | List all installed MDAN workflows with their descriptions |
| mdan_run_workflowA | Load an MDAN workflow (wizard) with its rules and progress (resume point, existing artifacts) and return the instructions to execute step by step |
| mdan_list_agentsA | List all installed MDAN agents with their roles |
| mdan_consult_agentA | Load an MDAN agent persona (with layered customization and its memories) to answer in character |
| mdan_customize_agentA | Customize an agent without editing its file: team layer (_mdan/custom/.yaml, versioned) or personal layer (.user.yaml, git-ignored). Values are merged into the layer |
| mdan_graph_add_nodeB | Add or update an artifact node in the MDAN context graph (records the file hash for staleness checks) |
| mdan_graph_add_edgeB | Add a relationship between two nodes of the context graph (cycles are rejected) |
| mdan_graph_impactB | Upstream dependencies and downstream impact of an artifact in the context graph |
| mdan_graph_staleA | List artifacts modified since registration and the downstream artifacts that must be reviewed |
| mdan_graph_visualizeB | Mermaid diagram of the context graph |
| mdan_party_modeA | Start a multi-agent session: free discussion, structured debate (-> decision record) or consensus |
| mdan_create_decision_recordA | Save a decision record (DR-XXX) from a debate or consensus session and register it in the context graph |
| mdan_ecosystem_searchA | Search installed Claude Code skills, agents or commands (~/.claude) by keywords, ranked by name/description match |
| mdan_ecosystem_readA | Read the full content of an installed skill, agent or command |
| mdan_ecosystem_catalogA | Page through the MDAN ecosystem catalog (categorized list of known components) |
| mdan_ecosystem_statsA | Count installed Claude Code components (skills, agents, commands) in ~/.claude |
| mdan_statusA | Project status: current workflow and step, completed workflows per phase, artifacts, decisions and the recommended next step |
| mdan_state_updateA | Record workflow progress: "start" (or resume) a workflow, "step" when moving to a step, "complete" with the produced artifacts (also registered in the context graph) |
| mdan_memory_rememberB | Store a memory in an agent's persistent sidecar (observation, preference, project context or decision). Identical memories are reinforced, not duplicated |
| mdan_memory_recallB | Recall an agent's memories from previous sessions, highest confidence first |
| mdan_memory_forgetB | Delete one memory from an agent sidecar |
| mdan_memory_end_sessionA | Close a session for the participating agents: count the session, apply memory decay, record relationships and decision outcomes |
| mdan_memory_listA | List agents that have a memory sidecar |
| mdan_checkA | Quality gate on the project artifacts (brief, PRD, architecture, epics, tech spec): unfilled placeholders, empty sections, missing sections, FR/NFR coverage across documents, acceptance criteria. Strictness follows the project scale |
| mdan_traceA | Traceability matrix requirement (FR/NFR) → stories → tests, coverage and gate decision; optionally writes it into the context graph |
| mdan_estimate_scopeA | Decide how much process a change needs (oneshot quick-dev / quick-spec first / full planning) from its description, files and the real downstream impact in the context graph |
| mdan_export_backlogA | Export the epics/stories document to CSV, GitHub Issues, Azure DevOps Boards or Jira. Dry run by default (returns the planned requests); apply=true sends them (tokens from environment variables). Re-runs update instead of duplicating |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| create-product-brief | Créer un product brief collaboratif. Utiliser quand l'utilisateur dit 'discover', 'product brief', 'j'ai une idée', ou 'commençons un nouveau projet'. |
| domain-research | Conduct domain and industry research. Use when the user says "lets create a research report on [domain or industry]" |
| market-research | Conduct market research on competition and customers. Use when the user says "create a market research report about [business idea]". |
| technical-research | Conduct technical research on technologies and architecture. Use when the user says "create a technical research report on [topic]". |
| create-prd | Create a PRD from scratch. Use when the user says "lets create a product requirements document" or "I want to create a new PRD" |
| create-ux-design | Plan UX patterns and design specifications. Use when the user says "lets create UX design" or "create UX specifications" or "help me plan the UX" |
| create-architecture | Create architecture solution design decisions for AI agent consistency. Use when the user says "lets create architecture" or "create technical architecture" or "create a solution design" |
| create-epics-and-stories | Break requirements into epics and user stories. Use when the user says "create the epics and stories list" |
| code-review | Perform adversarial code review finding specific issues. Use when the user says "run code review" or "review this code" |
| correct-course | Handle a significant change mid-sprint: impact analysis, options (adjust scope / re-plan / rollback), update PRD/architecture/epics, and produce a Sprint Change Proposal. Use when the user says "correct course", "something changed mid-sprint", or "we need to re-plan" |
| dev-story | Execute story implementation following a context filled story spec file. Use when the user says "dev this story [story file]" or "implement the next story in the sprint plan" |
| retrospective | Facilitate an epic or sprint retrospective: what went well, what did not, action items, and lessons stored as agent memories. Use when the user says "retrospective", "run a retro", or "let's look back on this sprint/epic" |
| sprint-planning | Generate sprint status tracking from epics. Use when the user says "run sprint planning" or "generate sprint plan" |
| document-project | Analyze an existing project to produce useful documentation (index, source tree, deep dives). Use when the user says "document this project" or "generate project docs". |
| quick-dev | Implement a Quick Tech Spec for small changes or features. Use when the user provides a quick tech spec and says "implement this quick spec" or "proceed with implementation of [quick tech spec]" |
| quick-spec | Very quick process to create implementation-ready quick specs for small changes or features. Use when the user says "create a quick spec" or "generate a quick tech spec" |
| brainstorming | Facilitate interactive brainstorming sessions using diverse creative techniques and ideation methods. Use when the user says help me brainstorm or help me ideate. |
| debate | Structured multi-agent debate on a critical decision. Use when the user says "debate", "let agents debate", "structured debate", or when a critical decision needs pro/contra analysis. |
| party-mode | Orchestrates group discussions between all installed MDAN agents, enabling natural multi-agent conversations. Use when user requests party mode. |
| pay-compliance-review | Revue réglementaire d'une feature ou d'un PRD contre une checklist BAM/AML(ANRF)/CNDP/PCI DSS, avec rapport d'écarts (gap report). Use when the user says "revue conformité", "compliance review", "checklist BAM" or "audit réglementaire". |
| pay-iso8583 | Spécifier une interface ISO 8583 avec un switch (CMI/GSIMT ou acquéreur) : MTI, table de mapping des Data Elements, codes réponse, gestion reversal/advice, vecteurs de test. Use when the user says "ISO 8583", "interface switch carte", "DE mapping" or "spec switch". |
| pay-kyc-limits | Concevoir les paliers KYC et plafonds (solde, entrée/sortie mensuel, par transaction) d'un wallet marocain, les règles d'upgrade/downgrade, les points d'enforcement et les tests. Use when the user says "paliers KYC", "plafonds wallet", "design wallet limits" or "KYC tiers". |
| pay-recon | Concevoir un rapprochement de fin de journée (EOD) entre le ledger core, le switch et les fichiers partenaires : sources, règles de matching, catégories d'écart, auto-résolution, reporting. Use when the user says "rapprochement EOD", "reconciliation design", "EOD reconciliation" or "règles de matching". |
| pay-txn-flow | Concevoir un flux de mouvement d'argent (cash-in, cash-out, P2P, paiement marchand, facture, virement) : états, écritures en double entrée, idempotency keys, timeouts, reversal/extourne, frais, notifications, outbox. Use when the user says "flux de paiement", "design payment flow", "cash-in cash-out" or "transaction flow". |
| qa-atdd | Acceptance Test-Driven Development: generate failing Given/When/Then acceptance tests from a story's acceptance criteria before implementation starts. Use when the user says "write ATDD tests", "generate acceptance tests for this story", or "let's do ATDD before building this" |
| qa-ci-gates | Set up a stack-agnostic CI test pipeline with quality gates (coverage, optional mutation testing, contract tests), with concrete examples for GitHub Actions and Azure DevOps. Use when the user says "set up CI for tests", "add a quality gate to the pipeline", or "configure test gates in Azure DevOps/GitHub Actions" |
| qa-nfr-assessment | Non-functional requirements assessment with evidence and thresholds for performance, security, reliability, and maintainability. Use when the user says "assess NFRs", "check performance and security readiness", or "is this ready on non-functional requirements" |
| qa-release-gate | Go/no-go release decision aggregating test design, traceability, NFR assessment and open defects by priority, using mdan_graph_stale to block release if artifacts downstream of changed specs were not re-verified. Use when the user says "are we ready to ship", "run the release gate", or "go/no-go decision" |
| qa-test-design | Risk-based test design that prioritizes test cases P0-P3 (probability x impact) across unit/integration/E2E/contract levels for a story or epic. Use when the user says "design tests for this story", "what should I test", "create a test design", or "test strategy for this epic" |
| qa-test-review | Review an existing test suite for quality issues (flakiness, weak assertions, poor isolation, non-determinism, unclear naming) with a scored checklist. Use when the user says "review our tests", "why are these tests flaky", or "audit test quality" |
| qa-traceability | Build a requirements to stories to tests coverage matrix from the PRD FR/NFR ids, using the context graph, identify gaps and issue a PASS/CONCERNS/FAIL gate decision. Use when the user says "build a traceability matrix", "are we covering all requirements", or "check requirement coverage" |
| agent-analyst | Business Analyst + Requirements Discovery Lead |
| agent-architect | System Architect + Technical Design Leader |
| agent-dev | Senior Implementation Engineer + TDD Practitioner |
| agent-mdan-master | Master Orchestrator + MDAN Expert + Context Guardian |
| agent-pm | Product Manager + Scope Guardian |
| agent-scrum-master | Technical Scrum Master + Delivery Guardian |
| agent-security | Application Security Engineer + Threat Modeling Lead |
| agent-tech-writer | Technical Documentation Specialist + Knowledge Curator |
| agent-ux-designer | User Experience Designer + Interaction Specialist |
| agent-indexing-specialist | Database Indexing Strategy Expert |
| agent-performance-analyst | Database Performance Analysis Expert |
| agent-query-optimizer | Database Query Optimization Expert |
| agent-azure-specialist | Azure Cloud Architecture Expert |
| agent-cicd-architect | CI/CD Pipeline Architecture Expert |
| agent-devops-engineer | DevOps Engineering and Operations Expert |
| agent-ia-master | IA Master — Chief AI Strategist, owns all AI/ML architecture, orchestrates 130+ AI skills and 48 AI agents. Reports to Khalil (MDAN Master) for project-level decisions. |
| agent-data-scientist | Data Scientist — orchestrates data analysis, visualization, and ML skills |
| agent-devops-commander | DevOps Commander — orchestrates 30+ DevOps skills, 39 infra agents, 11 deployment commands |
| agent-fullstack-architect | Fullstack Architecture Expert — routes to 200+ development skills and 100+ dev agents |
| agent-marketing-strategist | Marketing Strategist — orchestrates 25+ marketing skills and publishing commands |
| agent-product-lead | Product Lead — orchestrates product, project management, and team skills |
| agent-research-team-lead | Deep Research Orchestrator — coordinates research teams using ecosystem agents and scientific skills |
| agent-security-specialist | Security Expert — orchestrates 40+ security skills and 21 security agents |
| agent-skill-dispatcher | Ecosystem Orchestrator — Routes requests to the right specialist from 1,053 skills, 418 agents, 340 commands |
| agent-compliance-officer | Regulatory Compliance and Risk Assessment Expert |
| agent-financial-analyst | Financial Analysis and Modeling Expert |
| agent-risk-manager | Financial Risk Management Expert |
| agent-bam-compliance | Officier de Conformité Bank Al-Maghrib (BAM) pour établissements de paiement |
| agent-payments-architect | Architecte Systèmes de Paiement (switch, wallet, core banking) |
| agent-recon-lead | Responsable Rapprochement (EOD) & Règlement |
| agent-test-architect | Test Architecture & Quality Gate Expert |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| state | MDAN-STATE.json: completed workflows, artifacts, decisions |
| config | Installed modules, their config.yaml and counts |
| graph | Artifacts and decisions with their relationships |
| health | One-call health report: progress, next step, quality gate, stale artifacts, agent memories |
| create-product-brief | Créer un product brief collaboratif. Utiliser quand l'utilisateur dit 'discover', 'product brief', 'j'ai une idée', ou 'commençons un nouveau projet'. |
| domain-research | Conduct domain and industry research. Use when the user says "lets create a research report on [domain or industry]" |
| market-research | Conduct market research on competition and customers. Use when the user says "create a market research report about [business idea]". |
| technical-research | Conduct technical research on technologies and architecture. Use when the user says "create a technical research report on [topic]". |
| create-prd | Create a PRD from scratch. Use when the user says "lets create a product requirements document" or "I want to create a new PRD" |
| create-ux-design | Plan UX patterns and design specifications. Use when the user says "lets create UX design" or "create UX specifications" or "help me plan the UX" |
| create-architecture | Create architecture solution design decisions for AI agent consistency. Use when the user says "lets create architecture" or "create technical architecture" or "create a solution design" |
| create-epics-and-stories | Break requirements into epics and user stories. Use when the user says "create the epics and stories list" |
| code-review | Perform adversarial code review finding specific issues. Use when the user says "run code review" or "review this code" |
| correct-course | Handle a significant change mid-sprint: impact analysis, options (adjust scope / re-plan / rollback), update PRD/architecture/epics, and produce a Sprint Change Proposal. Use when the user says "correct course", "something changed mid-sprint", or "we need to re-plan" |
| dev-story | Execute story implementation following a context filled story spec file. Use when the user says "dev this story [story file]" or "implement the next story in the sprint plan" |
| retrospective | Facilitate an epic or sprint retrospective: what went well, what did not, action items, and lessons stored as agent memories. Use when the user says "retrospective", "run a retro", or "let's look back on this sprint/epic" |
| sprint-planning | Generate sprint status tracking from epics. Use when the user says "run sprint planning" or "generate sprint plan" |
| document-project | Analyze an existing project to produce useful documentation (index, source tree, deep dives). Use when the user says "document this project" or "generate project docs". |
| quick-dev | Implement a Quick Tech Spec for small changes or features. Use when the user provides a quick tech spec and says "implement this quick spec" or "proceed with implementation of [quick tech spec]" |
| quick-spec | Very quick process to create implementation-ready quick specs for small changes or features. Use when the user says "create a quick spec" or "generate a quick tech spec" |
| brainstorming | Facilitate interactive brainstorming sessions using diverse creative techniques and ideation methods. Use when the user says help me brainstorm or help me ideate. |
| debate | Structured multi-agent debate on a critical decision. Use when the user says "debate", "let agents debate", "structured debate", or when a critical decision needs pro/contra analysis. |
| party-mode | Orchestrates group discussions between all installed MDAN agents, enabling natural multi-agent conversations. Use when user requests party mode. |
| pay-compliance-review | Revue réglementaire d'une feature ou d'un PRD contre une checklist BAM/AML(ANRF)/CNDP/PCI DSS, avec rapport d'écarts (gap report). Use when the user says "revue conformité", "compliance review", "checklist BAM" or "audit réglementaire". |
| pay-iso8583 | Spécifier une interface ISO 8583 avec un switch (CMI/GSIMT ou acquéreur) : MTI, table de mapping des Data Elements, codes réponse, gestion reversal/advice, vecteurs de test. Use when the user says "ISO 8583", "interface switch carte", "DE mapping" or "spec switch". |
| pay-kyc-limits | Concevoir les paliers KYC et plafonds (solde, entrée/sortie mensuel, par transaction) d'un wallet marocain, les règles d'upgrade/downgrade, les points d'enforcement et les tests. Use when the user says "paliers KYC", "plafonds wallet", "design wallet limits" or "KYC tiers". |
| pay-recon | Concevoir un rapprochement de fin de journée (EOD) entre le ledger core, le switch et les fichiers partenaires : sources, règles de matching, catégories d'écart, auto-résolution, reporting. Use when the user says "rapprochement EOD", "reconciliation design", "EOD reconciliation" or "règles de matching". |
| pay-txn-flow | Concevoir un flux de mouvement d'argent (cash-in, cash-out, P2P, paiement marchand, facture, virement) : états, écritures en double entrée, idempotency keys, timeouts, reversal/extourne, frais, notifications, outbox. Use when the user says "flux de paiement", "design payment flow", "cash-in cash-out" or "transaction flow". |
| qa-atdd | Acceptance Test-Driven Development: generate failing Given/When/Then acceptance tests from a story's acceptance criteria before implementation starts. Use when the user says "write ATDD tests", "generate acceptance tests for this story", or "let's do ATDD before building this" |
| qa-ci-gates | Set up a stack-agnostic CI test pipeline with quality gates (coverage, optional mutation testing, contract tests), with concrete examples for GitHub Actions and Azure DevOps. Use when the user says "set up CI for tests", "add a quality gate to the pipeline", or "configure test gates in Azure DevOps/GitHub Actions" |
| qa-nfr-assessment | Non-functional requirements assessment with evidence and thresholds for performance, security, reliability, and maintainability. Use when the user says "assess NFRs", "check performance and security readiness", or "is this ready on non-functional requirements" |
| qa-release-gate | Go/no-go release decision aggregating test design, traceability, NFR assessment and open defects by priority, using mdan_graph_stale to block release if artifacts downstream of changed specs were not re-verified. Use when the user says "are we ready to ship", "run the release gate", or "go/no-go decision" |
| qa-test-design | Risk-based test design that prioritizes test cases P0-P3 (probability x impact) across unit/integration/E2E/contract levels for a story or epic. Use when the user says "design tests for this story", "what should I test", "create a test design", or "test strategy for this epic" |
| qa-test-review | Review an existing test suite for quality issues (flakiness, weak assertions, poor isolation, non-determinism, unclear naming) with a scored checklist. Use when the user says "review our tests", "why are these tests flaky", or "audit test quality" |
| qa-traceability | Build a requirements to stories to tests coverage matrix from the PRD FR/NFR ids, using the context graph, identify gaps and issue a PASS/CONCERNS/FAIL gate decision. Use when the user says "build a traceability matrix", "are we covering all requirements", or "check requirement coverage" |
| 📊 Amina | Business Analyst |
| 🏗️ Reda | System Architect |
| 💻 Haytame | Senior Developer |
| 🧙 MDAN Master | Orchestrateur Principal, Gardien du Contexte, Directeur des Wizards |
| 📋 Khadija | Product Manager |
| 🏃 Nadia | Scrum Master |
| 🛡️ Yassir | Security Engineer |
| 📚 Youssef | Technical Writer |
| 🎨 Jihane | UX Designer |
| 📑 Salma | Indexing Specialist |
| 📈 Mehdi | DB Performance Analyst |
| 🔍 Driss | Query Optimizer |
| ☁️ Hamza | Azure Specialist |
| 🔄 Yassine | CI/CD Architect |
| ⚙️ Omar | DevOps Engineer |
| 🧠 Fayçal | IA Master |
| 📊 Saad | Data Scientist |
| 🚀 Ilyas | DevOps Commander |
| 🏗️ Amine | Fullstack Architect |
| 📈 Imane | Marketing Strategist |
| 💡 Adnane | Product Lead |
| 🔬 Leila | Deep Research Team Lead |
| 🛡️ Samir | Security Specialist |
| 🎯 Zineb | Ecosystem Skill Dispatcher |
| ⚖️ Rachid | Compliance Officer |
| 📊 Sanae | Financial Analyst |
| 🛡️ Karim | Risk Manager |
| ⚖️ Houda | BAM Compliance Officer |
| 💳 Anas | Payments Systems Architect |
| 🧾 Samira | Reconciliation & Settlement Lead |
| 🧪 Fatima | Test Architect |
TDQS
B3.4/5.0
Scored across 27 tools
Disambiguation4/5
Most tools target distinct resources (workflows, agents, memory, graph, ecosystem, quality) and their descriptions clarify boundaries. A few pairs like memory_list vs list_agents or graph_impact vs graph_stale could be confused at first glance, but the descriptions prevent serious misselection.
Naming Consistency3/5
All tools share the mdan_ prefix, but the suffix pattern varies: verb_noun (list_workflows), noun_verb (memory_list, ecosystem_search), noun_adjective (graph_stale), and bare verbs (check, trace). This mixed ordering is readable but not predictable.
Tool Count2/5
27 tools is above the comfortable range and covers seven or eight distinct subdomains, making the server feel heavy. Some tools like ecosystem_stats and memory_list could arguably be merged without loss.
Completeness4/5
The server covers the full workflow lifecycle: planning, execution, state tracking, quality gates, traceability, and export. Minor gaps exist (no graph node/edge removal, no workflow creation/editing, no decision record update), but these are likely handled by file operations and don't block core usage.
Maintenance
ActivityMaintained
ResponsivenessNo issues