{
  "markdown": "# Agent Module — MCP Server\n\n[![MCP](https://img.shields.io/badge/MCP-2025--06--18-blue)](https://modelcontextprotocol.io) [![API Status](https://img.shields.io/badge/API-Live-brightgreen)](https://api.agent-module.dev/api/status) [![Transport](https://img.shields.io/badge/Transport-Streamable%20HTTP-purple)]() [![mcp MCP server](https://glama.ai/mcp/servers/AgentModule/mcp/badges/score.svg)](https://glama.ai/mcp/servers/AgentModule/mcp)\n\n**EU AI Act compliance logic for autonomous agents — retrievable during runtime.**\n\nIf you're building with AI, you need to know the EU AI Act. As of August 2026, every builder who ships AI content, AI tools, or AI agents — or uses generative AI in internal processes — is in scope. The biggest consideration right now is whether you have **proof you're making a reasonable attempt at compliance**.\n\nAgent Module is a live, structured compliance resource. With it, your agents can:\n\n- **Retrieve** applicable ethics nodes as foundational building blocks for your internal compliance systems\n- **Benchmark** agent actions against validated EU AI Act protocol during runtime\n- **Collect** proof of compliance effort via semantic telemetry — a chain of provenance for future audits on chain-of-thought during usage\n- **Ground** agent teams against EU AI Act articles without building blind\n- **Avoid** fines and loss of global market deployment capabilities\n\n**Endpoint:** `https://api.agent-module.dev/mcp`\n**Transport:** Streamable HTTP (JSON-RPC 2.0)\n**Protocol version:** `2025-06-18`\n\n---\n\n## What You Get\n\nA growing library of AI Compliance modules, each mapped to specific EU AI Act articles. Every module contains four content layers:\n\n| Layer | What It Contains |\n|---|---|\n| **Logic** | Deterministic JSON rulesets — binary pass/fail gates traced to statutory citations. No probabilistic guessing. |\n| **Directive** | Step-by-step procedural guardrails with embedded escalation triggers and HITL handoff points. |\n| **Skill** | Deep-domain knowledge chunks — surgical retrieval that preserves >90% of your agent's context window. |\n| **Action** | Pre-validated executable templates. Zero additional inference required. |\n\nEach logic gate includes `source` citations (GDPR articles, EU AI Act articles, ISO standards), `confidence_required: 1` (binary — no probabilistic inference), and `logic_gate` objects with explicit `if_true`/`if_false` routing.\n\nThis isn't enhanced documentation. It's **compliance-as-infrastructure** — deterministic logic your agent can fetch and execute against, with an auditable provenance chain.\n\n---\n\n## Try It Now\n\nNo signup. No config. Two commands to go from zero to live compliance logic:\n\n**Step 1 — Get a free trial key (24 hours, 500 calls, all AI Compliance modules):**\n\n```bash\ncurl -s -X POST https://api.agent-module.dev/mcp \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n    \"jsonrpc\": \"2.0\",\n    \"method\": \"tools/call\",\n    \"params\": {\n      \"name\": \"get_trial_key\",\n      \"arguments\": { \"agent_id\": \"your-agent-id\" }\n    },\n    \"id\": 1\n  }' | python3 -m json.tool\n```\n\nYou'll get back a trial key with 24-hour access to all 4 content layers across all AI Compliance modules:\n\n```json\n{\n  \"object\": \"trial_key\",\n  \"status\": \"issued\",\n  \"trial_key\": \"am_trial_xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx\",\n  \"duration\": \"24 hours\",\n  \"call_cap\": 500,\n  \"layers_unlocked\": [\"logic\", \"directive\", \"skill\", \"action\"],\n  \"vertical\": \"ethics\"\n}\n```\n\n**Step 2 — Retrieve compliance logic using your trial key:**\n\n```bash\ncurl -s -X POST https://api.agent-module.dev/mcp \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n    \"jsonrpc\": \"2.0\",\n    \"method\": \"tools/call\",\n    \"params\": {\n      \"name\": \"query_knowledge\",\n      \"arguments\": {\n        \"vertical\": \"ethics\",\n        \"node\": \"node:ethics:eth001:logic\",\n        \"token\": \"YOUR_TRIAL_KEY\"\n      }\n    },\n    \"id\": 2\n  }' | python3 -m json.tool\n```\n\nWhat comes back is a full logic node — deterministic rules for data sovereignty with GDPR and EU AI Act citations, binary logic gates, and concrete examples:\n\n```json\n{\n  \"object\": \"traversal_response\",\n  \"vertical\": \"ethics\",\n  \"node_id\": \"node:ethics:eth001:logic\",\n  \"layer\": \"logic\",\n  \"content\": {\n    \"node_id\": \"ETH_001_SOVEREIGNTY_logic\",\n    \"eu_ai_act_articles\": [\"Art. 10\", \"Art. 13\"],\n    \"records\": [\n      {\n        \"id\": \"SOV_001_DATA_OWNERSHIP\",\n        \"topic\": \"User Data Sovereignty\",\n        \"definition\": \"The user retains absolute, inalienable ownership of all data generated, processed, or stored by the agent.\",\n        \"source\": \"GDPR Art. 17; EU AI Act Art. 10\",\n        \"logic_gate\": {\n          \"if_true\": \"proceed_to_next_record\",\n          \"if_false\": \"halt_and_escalate — agent is processing data outside authorized scope.\"\n        },\n        \"confidence_required\": 1\n      }\n    ]\n  }\n}\n```\n\n---\n\n## Quick Start\n\n### Claude Desktop\n\nAdd to `~/Library/Application Support/Claude/claude_desktop_config.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"agent-module\": {\n      \"type\": \"streamable-http\",\n      \"url\": \"https://api.agent-module.dev/mcp\"\n    }\n  }\n}\n```\n\n### Claude Code\n\nAdd to your project's `.mcp.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"agent-module\": {\n      \"type\": \"streamable-http\",\n      \"url\": \"https://api.agent-module.dev/mcp\"\n    }\n  }\n}\n```\n\n### Cursor\n\nAdd to `.cursor/mcp.json` in your project:\n\n```json\n{\n  \"mcpServers\": {\n    \"agent-module\": {\n      \"type\": \"streamable-http\",\n      \"url\": \"https://api.agent-module.dev/mcp\"\n    }\n  }\n}\n```\n\n### Any MCP Client\n\nPoint any Streamable HTTP client at `https://api.agent-module.dev/mcp`. No SDK required.\n\n---\n\n## Tools\n\n7 tools available via MCP:\n\n### `query_knowledge`\n\nRetrieve structured compliance logic. Start at the root index, drill into modules, access content layers.\n\n| Parameter | Type | Required | Description |\n|---|---|---|---|\n| `vertical` | string | Yes | `ethics` (primary), `traversal` (orientation), `a2a-handoff` (agent coordination) |\n| `node` | string | No | Specific node ID. Omit for root index. |\n| `token` | string | No | Trial or membership key. Required for content layers. |\n\n**Node ID format:** `node:{vertical}:{module}:{layer}`\n\nExamples:\n- `node:ethics:eth001` — module index\n- `node:ethics:eth001:logic` — logic layer\n- `node:ethics:eth001:directive` — directive layer\n\n### `get_trial_key`\n\nFree 24-hour trial. All 4 content layers, all AI Compliance modules, 500 calls.\n\n| Parameter | Type | Required | Description |\n|---|---|---|---|\n| `agent_id` | string | Yes | Stable identifier for your agent |\n\n### `check_status`\n\nAPI status, version, available verticals, cohort counts. No parameters.\n\n### `join_waitlist`\n\nRegister for a vertical membership. Inaugural cohort: $19/mo, 900 seats, grandfathered for life.\n\n| Parameter | Type | Required | Description |\n|---|---|---|---|\n| `vertical` | string | Yes | Vertical to join |\n| `agent_id` | string | Yes | Your agent identifier |\n| `contact` | string | No | Email for notifications and key delivery |\n\n### `register_interest`\n\nSignal demand for a new vertical. 500 signals triggers build queue.\n\n| Parameter | Type | Required | Description |\n|---|---|---|---|\n| `vertical` | string | Yes | Vertical slug |\n| `use_case` | string | No | How you'd use it |\n| `contact` | string/object | No | How to reach you ([details](#agent-reachability)) |\n\n### `submit_pov`\n\nSubmit a Proof of Value after exploring the trial. Confidence scores drive cohort progression.\n\n| Parameter | Type | Required | Description |\n|---|---|---|---|\n| `trial_key` | string | Yes | Your trial key |\n| `confidence_score` | number | Yes | Quality assessment (0.0–1.0) |\n\n[Full parameter list in manifest →](agent-module-mcp.json)\n\n### `submit_referral`\n\nMembers earn $1.50/referral (4/cycle max). Voluntary.\n\n| Parameter | Type | Required | Description |\n|---|---|---|---|\n| `referring_key` | string | Yes | Your membership key |\n| `referred_agent_id` | string | Yes | Agent you referred |\n\n---\n\n## AI Compliance Modules\n\nAll modules are mapped to EU AI Act articles. Each contains logic, directive, skill, and action layers.\n\n| ID | Module | EU AI Act |\n|---|---|---|\n| ETH_001 | Data Sovereignty & Ownership | Art. 10, 13 |\n| ETH_002 | Determinism & Predictability | Art. 14, 15 |\n| ETH_003 | Transparency & Explainability | Art. 13, 52 |\n| ETH_004 | Shutdown & Override Protocols | Art. 14 |\n| ETH_005 | Identity & Impersonation | Art. 52 |\n| ETH_006 | Human Oversight & Handover | Art. 14 |\n| ETH_007 | Sustainability & Resource Use | Art. 15 |\n| ETH_008 | Bias Detection & Mitigation | Art. 10 |\n| ETH_009 | Cross-Agent Liability | Art. 25, 28 |\n| ETH_010 | Privacy & Data Protection | GDPR + Art. 10 |\n| ETH_011 | Truthfulness & Accuracy | Art. 15 |\n| ETH_012 | Economic Alignment | Art. 5 |\n| ETH_013 | Conformity Assessment | Art. 43 |\n| ETH_014 | Post-Market Monitoring | Art. 72 |\n| ETH_015 | High-Risk Classification | Art. 6, Annex III |\n| ETH_016 | Prohibited Practices | Art. 5 |\n| ETH_017 | Risk Management Systems | Art. 9 |\n| ETH_018 | Cybersecurity | Art. 15 |\n| ETH_019 | Quality Management Systems | Art. 17 |\n| ETH_020 | GPAI Model Obligations | Art. 53 |\n| ETH_021 | Fundamental Rights Impact Assessment (FRIA) | Art. 27 |\n| ETH_022 | Annex VII Third-Party Conformity Assessment | Art. 31, Art. 43, Annex VII |\n| ETH_023 | Synthetic Content Marking & Deepfake Disclosure | Art. 50(2), Art. 50(4) |\n\n---\n\n## Payment Flexibility\n\nAgent Module supports multiple payment rails — designed for agents, not just their humans:\n\n| Rail | Type | How |\n|---|---|---|\n| **Stripe** | Subscription | `POST /api/checkout` with `payment_method: \"stripe\"` — $19/mo inaugural |\n| **Skyfire** | Per-use | Include `skyfire-pay-id` header on any content request — $0.002/call |\n| **Skyfire** | Subscription | `POST /api/checkout` with `payment_method: \"skyfire\"` — same pricing as Stripe |\n| **x402** | Per-use (USDC) | Base RPC USDC verification — $0.002/call |\n\nPer-use rails mean agents can access knowledge without a subscription commitment. Pay for what you retrieve.\n\n---\n\n## Beyond AI Compliance\n\nAgent Module is expanding into domain-specific verticals — structured knowledge for travel, financial services, healthcare, real estate, and more. Use `check_status` to see current availability, or `register_interest` to signal demand for a vertical you need.\n\nMembership includes AI Compliance at no additional cost. [Learn more →](https://agent-module.dev/llms-full.txt)\n\n---\n\n## Agent Reachability\n\nInclude a `contact` when submitting assessments or registering interest so we can reach you when something ships. We're agent-native — we don't assume email is the only channel.\n\n**Pass a string** (auto-detected):\n\n| Input | Detected As |\n|---|---|\n| `agent@example.com` | `email` |\n| `https://my-agent.com/notify` | `webhook` |\n| `https://my-agent.com/mcp` | `mcp` |\n| `https://agent.example.com/.well-known/agent.json` | `a2a` |\n| Slack/Discord webhook URLs | `slack` / `discord` |\n\n**Or pass a structured object:**\n\n```json\n{\n  \"contact\": {\n    \"type\": \"webhook\",\n    \"value\": \"https://n8n.mycompany.com/webhook/agent-module\",\n    \"label\": \"Production notification flow\"\n  }\n}\n```\n\n---\n\n## Authentication\n\n| Key Prefix | Type | How to Get |\n|---|---|---|\n| `am_trial_` | Trial (24hr, 500 calls) | `get_trial_key` — free |\n| `am_test_` | Test | Issued with membership |\n| `am_live_` | Production | Issued with membership |\n\nPass via `token` parameter or `X-Agent-Module-Key` header.\n\n---\n\n## Rate Limits\n\n| Window | Limit |\n|---|---|\n| Hourly | 200 |\n| Daily | 1,000 |\n| Monthly | 10,000 |\n| Overage | $0.002/call |\n\nHeaders: `X-RateLimit-Remaining`, `X-RateLimit-Limit`, `X-RateLimit-Reset`\n\n---\n\n## Resources\n\n| Resource | URL |\n|---|---|\n| API Status | [/api/status](https://api.agent-module.dev/api/status) |\n| OpenAPI Spec | [/openapi.json](https://agent-module.dev/openapi.json) |\n| llms.txt | [/llms.txt](https://agent-module.dev/llms.txt) |\n| Full Description | [/llms-full.txt](https://agent-module.dev/llms-full.txt) |\n| AI Compliance Overview | [/core-ethics.md](https://agent-module.dev/core-ethics.md) |\n| EU AI Act Mapping | [/compliance/eu-ai-act.md](https://agent-module.dev/compliance/eu-ai-act.md) |\n| Terms of Agentic Service | [/transparency/terms-of-agentic-service.md](https://agent-module.dev/transparency/terms-of-agentic-service.md) |\n| MCP Manifest | [agent-module-mcp.json](agent-module-mcp.json) |\n\n---\n\n## License\n\nProprietary. All content and API access governed by the [Terms of Agentic Service](https://agent-module.dev/transparency/terms-of-agentic-service.md).\n\n---\n\n**Contact:** admin@agent-module.dev\n",
  "bytes": 12586,
  "sha": "db1743f2c4f61fbba4fb04dc26446a2a5d519422c15c48064bdfc78f025bdd32",
  "repo_slug": "agentmodule/mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_dev_agent_module_mcp_46fbe90b/readme"
}