{
  "markdown": "# agentblueprint\n\nCLI and MCP server for [Agent Blueprint](https://app.agentblueprint.ai) — 23 MCP tools for creating structured business profiles, generating pipeline artifacts, exploring blueprint data, syncing implementation state, and downloading full Agent Skills directories. Vendor-agnostic output works with ServiceNow, Salesforce, OpenClaw, or any platform.\n\n## CLI Quick Start\n\n```bash\n# Install globally\nnpm install -g agentblueprint\n\n# Store your API token (one-time)\nagentblueprint login\n\n# List blueprints\nagentblueprint list\n\n# Get a blueprint summary (JSON to stdout)\nagentblueprint get blueprint <id>\n\n# Get other artifacts\nagentblueprint get business-case <id>\nagentblueprint get use-case <id>\nagentblueprint get implementation-plan <id>\nagentblueprint get implementation-spec <id>\nagentblueprint get business-profile\n\n# Download as Agent Skills directory\nagentblueprint download <id>\n\n# Partner cross-org access\nagentblueprint list --org <customer-org-id>\nagentblueprint get blueprint <id> --org <customer-org-id>\n```\n\nOr run without installing via npx:\n\n```bash\nnpx agentblueprint list --token <your-api-key>\nnpx agentblueprint get blueprint <id> --token <your-api-key>\n```\n\n## MCP Server Setup\n\nThe same binary auto-detects MCP mode when stdin is piped (non-interactive). No separate command needed.\n\nAdd to your Claude Code MCP config (`.claude/settings.json` or project settings):\n\n```json\n{\n  \"mcpServers\": {\n    \"agent-blueprint\": {\n      \"command\": \"npx\",\n      \"args\": [\"@agentblueprint/mcp-server\"],\n      \"env\": {\n        \"AGENT_BLUEPRINT_API_KEY\": \"<your-api-key>\"\n      }\n    }\n  }\n}\n```\n\nYou can also start the MCP server explicitly with `agentblueprint serve`.\n\n## Get an API Key\n\n1. Go to [Agent Blueprint Settings > API Tokens](https://app.agentblueprint.ai/settings/api-tokens)\n2. Click \"Create Token\"\n3. Copy the token (shown once)\n\n## Supported Headless Workflow\n\nCurrent scope is intentionally narrow:\n\n`existing PAT + existing org -> create_business_profile -> generate_use_cases -> generate_blueprint or trigger_full_pipeline -> get_generation_status -> download_blueprint`\n\nThis release does **not** handle organization creation, OAuth bootstrap, or free-form context extraction into the business profile.\n\n## Download Blueprint as Agent Skills\n\nDownload a blueprint as a local Agent Skills directory that any coding agent can read from the filesystem. This is the recommended way to work with blueprints.\n\n```bash\n# Using the CLI (after `agentblueprint login`)\nagentblueprint download <id>\nagentblueprint download <id> --dir ./my-skills\n\n# Or via npx\nnpx agentblueprint download --token <key> --blueprint <id>\n```\n\nThis creates an Agent Skills directory structure:\n\n```\n.agent-blueprint/<blueprint-slug>/\n├── SKILL.md                              # Overview + frontmatter (auto-discovered by agents)\n├── references/\n│   ├── business-context.md               # Use case, pain points, transformation story\n│   ├── agent-specifications.md           # Full agent specs with tools, guardrails, metrics\n│   ├── financial-case.md                 # ROI, cost breakdown, sensitivity, 5-year projection\n│   ├── implementation-roadmap.md         # Epics, stories, timeline, roles, dependencies\n│   ├── architecture-decisions.md         # Platform, pattern, integration gaps, feasibility\n│   └── guardrails-and-governance.md      # Risks, mitigation, per-agent guardrails\n└── scripts/\n    └── validate-spec.sh                  # Structure completeness checker\n```\n\nThe [Agent Skills](https://agentskills.io) standard is supported by Claude Code, Codex, Cursor, GitHub Copilot, Windsurf, and 18+ other coding agents. SKILL.md loads automatically at activation (~100 tokens), reference files load on demand.\n\n## Available Tools\n\n| Tool | Description |\n|------|-------------|\n| `create_business_profile` | Create or upsert a structured business profile for an existing organization |\n| `generate_use_cases` | Generate normalized use cases from the current business profile and readiness assessment |\n| `generate_blueprint` | Start blueprint generation for a chosen use case and return an `auditId` |\n| `trigger_full_pipeline` | Start the full pipeline for an existing business profile and return a `jobId` |\n| `get_generation_status` | Poll either blueprint generation or full-pipeline generation status |\n| `list_blueprints` | List all blueprints (summaries) |\n| `get_blueprint` | Blueprint summary — title, agents, phases, pattern |\n| `get_business_case` | Business case summary — ROI, pilot economics, recommendation |\n| `get_implementation_plan` | Implementation plan summary — epics, timeline, story counts |\n| `get_use_case` | Use case analysis for a blueprint |\n| `get_implementation_spec` | Implementation spec metadata |\n| `get_business_profile` | Organization business profile |\n| `download_blueprint` | Download full blueprint as Agent Skills file manifest |\n\nThe `generate_blueprint` and `trigger_full_pipeline` tools are asynchronous. Use `get_generation_status` to poll until the run completes, then call `download_blueprint` with the resolved `blueprintId`.\n\nThe `get_blueprint`, `get_business_case`, and `get_implementation_plan` tools return concise summaries optimized for agent context windows. For full details (agent specs, financial projections, user stories), use `download_blueprint` to get the complete Agent Skills directory.\n\n## Available Resources\n\n| URI | Description |\n|-----|-------------|\n| `agentblueprint://blueprints` | Blueprint list (JSON) |\n| `agentblueprint://blueprints/{id}` | Blueprint detail (Markdown) |\n| `agentblueprint://blueprints/{id}/spec` | Implementation spec (Markdown) |\n\n## Authentication\n\nThree ways to provide your API token (checked in this order):\n\n1. `--token <key>` flag on any command\n2. `AGENT_BLUEPRINT_API_KEY` environment variable\n3. `agentblueprint login` (saved to `~/.config/agentblueprint/config.json`)\n\n## Environment Variables\n\n| Variable | Required | Default | Description |\n|----------|----------|---------|-------------|\n| `AGENT_BLUEPRINT_API_KEY` | No | — | Your API token (alternative to `agentblueprint login`) |\n| `AGENT_BLUEPRINT_API_URL` | No | `https://app.agentblueprint.ai` | API base URL |\n",
  "bytes": 6204,
  "sha": "49d8ab7de02506f3ca1c187c111eec07a4a092129293de198f6d6f2566851cbd",
  "repo_slug": "agent-blueprint/mcp-server",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_agent_blueprint_mcp_server_72100bda/readme"
}