AI Agent Build Blueprint (Start Building in 60 Seconds)

For AI Agents (Claude, Cursor, GitHub Copilot, Codex, Custom Agents) & Builders: This page contains everything an AI agent needs to connect to Purple8 Hyper Graph (v0.72.0), choose the right tool profile, model schemas, ingest data, run hybrid GraphRAG, orchestrate stateful workflows with SLAs and Human-In-The-Loop (HITL) approvals, and compare Purple8 against legacy multi-service stacks.
Machine-readable summary: /llms.txt

1. Connect Your AI Agent (Streamable HTTP & SSE)

Purple8 runs an in-process MCP server at /mcp (Streamable HTTP) and /mcp/sse (SSE). Both endpoints accept:

Standard API Keys (p8g_...) via X-API-Key or Authorization: Bearer
Session JWTs
Cloud Sandbox Keys (auto-provisioned into an isolated tenant on first request)

Focused MCP Tool Profiles (`?profile=`)

Instead of loading all 125 tools into your agent's context window at once, pass ?profile= on the MCP URL:

Profile	URL Suffix	Tools	When to Use
`starter`	`/mcp?profile=starter`	22	Recommended default. RAG queries, core graph CRUD/search/traversal, document ingestion, and Journey workflows + HITL. 5× smaller prompt footprint.
`builder`	`/mcp?profile=builder`	72	Full application building: Starter + `schema.`, `memory.`, `models.`, `egress.`, `scheduler.`, `feedback.`, `registry.*`.
`ops`	`/mcp?profile=ops`	33	Operations & governance: `journey.`, `sentinel.`, `guardrails.`, `feedback.`, `admin.*`.
`full`	`/mcp` (or `?profile=full`)	125	All 16 namespaces including `quantum.` and `evolution.`.

Copy-Paste Client Snippets

Claude Code CLICursor (.cursor/mcp.json)VS Code (.vscode/mcp.json)Claude Desktop (claude_desktop_config.json)

bash

claude mcp add --transport http purple8 "https://<your-host>/mcp?profile=starter" \
  --header "X-API-Key: <your-api-or-sandbox-key>"

json

{
  "mcpServers": {
    "purple8-graph": {
      "url": "https://<your-host>/mcp?profile=starter",
      "headers": {
        "X-API-Key": "<your-api-or-sandbox-key>"
      }
    }
  }
}

json

{
  "servers": {
    "purple8-graph": {
      "type": "http",
      "url": "https://<your-host>/mcp?profile=starter",
      "headers": {
        "X-API-Key": "<your-api-or-sandbox-key>"
      }
    }
  }
}

json

{
  "mcpServers": {
    "purple8-graph": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://<your-host>/mcp?profile=starter",
        "--header",
        "X-API-Key:${P8_KEY}"
      ],
      "env": {
        "P8_KEY": "<your-api-or-sandbox-key>"
      }
    }
  }
}

2. End-to-End Agent Playbook: Build a Complete Application

With Purple8, the AI agent is the backend developer. You do not need to set up PostgreSQL, Pinecone, Neo4j, Airflow, or Auth0. Call these MCP tools in order:

Step 1 — Define the Data Model (`schema.*`)

json

// Tool: schema.define_node_type
{
  "type_name": "Borrower",
  "description": "Commercial loan applicant",
  "data_classification": "restricted",
  "properties": {
    "name": { "type": "string", "required": true },
    "jurisdiction": { "type": "string", "required": true },
    "requested_usd": { "type": "number" }
  },
  "immutable_properties": ["jurisdiction"]
}

Step 2 — Ingest Documents or Structured Entities (`data.` / `graph.`)

json

// Tool: data.ingest_text
{
  "text": "Horizon Logistics LLC applied for a $450,000 equipment facility in UK. Director Elena Vance also controls Titanium Cloud Ltd.",
  "source_name": "kyc_memo_9001",
  "auto_commit": true
}

json

// Tool: graph.add_node  (NOTE: parameter is "type" string, not "labels" list)
{
  "node_id": "borrower:horizon-9001",
  "type": "Borrower",
  "properties": {
    "name": "Horizon Logistics LLC",
    "jurisdiction": "UK",
    "requested_usd": 450000
  }
}

json

// Tool: graph.add_edge
{
  "source_id": "borrower:horizon-9001",
  "target_id": "vendor:titanium-cloud",
  "edge_type": "PARTNER_OF",
  "properties": { "relationship": "shared-director" }
}

Step 3 — Define & Start a Stateful Workflow with SLAs & HITL (`journey.*`)

json

// Tool: journey.define
{
  "journey_type": "commercial_underwriting",
  "description": "KYC -> Risk Assessment -> Underwriting HITL -> Disbursed",
  "stages": [
    { "name": "submitted", "sla_warn_seconds": 1800, "sla_breach_seconds": 3600 },
    { "name": "kyc_verified", "sla_warn_seconds": 7200, "sla_breach_seconds": 86400 },
    { "name": "underwriting_review", "sla_warn_seconds": 86400, "sla_breach_seconds": 172800 },
    { "name": "approved" }
  ]
}

json

// Tool: journey.start
{
  "journey_type": "commercial_underwriting",
  "entity_id": "borrower:horizon-9001"
}

Step 4 — Auto-Profile & Query with Hybrid GraphRAG (`rag.*`)

json

// Tool: rag.profile_collection
{}
// Returns recommended fusion_alpha, max_hops, seed_k, and topology_class

json

// Tool: rag.hybrid_query
{
  "question": "Which entities are connected to Horizon Logistics LLC and what is their underwriting status?",
  "mode": "balanced",
  "max_hops": 2,
  "seed_k": 10
}

Step 5 — Check SLAs, Governance & Human Approvals (`journey.`, `sentinel.`, `admin.*`)

journey.sla_alerts() — list any workflow instances that breached SLA deadlines.
journey.list_hitl(status="pending") — surface pending human decisions.
sentinel.list_findings(status="open") — inspect autonomous drift or risk threshold proposals.
admin.audit_verify() — verify the cryptographic hash-chain across all AI and human actions.

3. Tool Selection Cheat Sheet for Agents

Goal	Exact MCP Tool to Call
Fast single-hop factual Q&A	`rag.query`
Multi-hop relational + semantic Q&A	`rag.hybrid_query`
Discover optimal RAG parameters for a corpus	`rag.profile_collection` → `rag.tune_collection`
Inspect all node labels and counts	`graph.labels`, `graph.counts`
Run Cypher query (`MATCH ... RETURN ...`)	`graph.query`
Multi-hop neighbourhood walk from a node	`graph.traverse`
Check if specific edges exist in bulk	`graph.edges_exist`
Find most influential nodes / clusters	`graph.pagerank`, `graph.communities`, `graph.centrality`
Parse & ingest a PDF/DOCX/XLSX/IFC by URL	`data.ingest_file`
Query structured tables inside ingested docs	`data.get_table` → `data.query_table_rows`
Link structured table columns to graph nodes	`data.link_table_rows`
Wait for real-time graph mutations (long-poll)	`graph.wait_for_changes`
Schedule a recurring or event-driven automation	`scheduler.add_trigger`
Stream graph changes to an external webhook	`egress.add_sink`
Federate an external REST API, MCP server, or A2A agent	`registry.register_tool`, `registry.register_mcp_server`, `registry.register_a2a_agent`
Check LLM routing decision & policy	`models.route_explain`, `models.get_policy`
Evaluate text against safety/PII guardrails	`guardrails.evaluate`

4. Architecture & Benchmark Comparison (Why Purple8)

Dimension	Stitched Legacy AI Stack (8–12 Services)	Neo4j + Vector Plugin	Pinecone / Qdrant	Purple8 Hyper Graph (`v0.72.0`)
Processes to run	8 to 12 separate clusters	JVM + external orchestrator	Vector slice only	1 in-process engine (`docker run`)
Data models in one engine	Fragmented across silos	Property graph + bolt-on vector	Vectors only	Property + Hyper + Temporal Graph + Vector + Document + Full-Text
Network hops per RAG query	6 to 14 hops	2 to 4 hops	2+ hops	0 hops (in-process)
Memory scaling with data size $N$	Unbounded $O(N)$	JVM heap grows with $N$	Index RAM grows with $N$	Hardware-bounded Cortex memory (`~9 GB` peak on 8.84M docs)
Single-node verified scale	Requires multi-node cluster	High RAM overhead	Vector-only	20M nodes + 30M edges (50M objects) on 1 node (`~42.3 GB` RAM)
Point lookup & 2-hop latency @ 20M	5–50 ms over network	10–150 ms	No graph walk	52 µs P50 (`1.26 ms` P99) lookup · 0.38 ms P50 (`0.87 ms` P99) 2-hop
6M-edge Super-Hub 2-hop walk	Timeouts / OOM	Seconds to minutes	N/A	53.1 ms P50 (`58.8 ms` P99), 0 timeouts
Hardware-topology adaptation	Manual cluster tuning	Manual JVM tuning	Cloud tier sizing	Auto-adapts to NUMA, CPU sockets, AMX & NVIDIA B200/B300 GPUs
Stateful workflows, SLAs & HITL	Requires Airflow / Temporal / LangGraph	None	None	Built-in `JourneyEngine`
Native AI Governance & SOC	Post-hoc proxy wrappers	None	None	Pre-execution tool RBAC, `human_only` gates, Drift Sentinel, 4-tier SOC & hash-chained audit
AI Agent MCP Interface	DIY glue code	Read/query only	Read-mostly	125 RBAC-governed MCP tools across 16 namespaces

AI Agent Build Blueprint (Start Building in 60 Seconds) ​

1. Connect Your AI Agent (Streamable HTTP & SSE) ​

Focused MCP Tool Profiles (?profile=) ​

Copy-Paste Client Snippets ​

2. End-to-End Agent Playbook: Build a Complete Application ​

Step 1 — Define the Data Model (schema.*) ​

Step 2 — Ingest Documents or Structured Entities (data.* / graph.*) ​

Step 3 — Define & Start a Stateful Workflow with SLAs & HITL (journey.*) ​

Step 4 — Auto-Profile & Query with Hybrid GraphRAG (rag.*) ​

Step 5 — Check SLAs, Governance & Human Approvals (journey.*, sentinel.*, admin.*) ​

3. Tool Selection Cheat Sheet for Agents ​

4. Architecture & Benchmark Comparison (Why Purple8) ​

AI Agent Build Blueprint (Start Building in 60 Seconds)

1. Connect Your AI Agent (Streamable HTTP & SSE)

Focused MCP Tool Profiles (`?profile=`)

Copy-Paste Client Snippets

2. End-to-End Agent Playbook: Build a Complete Application

Step 1 — Define the Data Model (`schema.*`)

Step 2 — Ingest Documents or Structured Entities (`data.` / `graph.`)

Step 3 — Define & Start a Stateful Workflow with SLAs & HITL (`journey.*`)

Step 4 — Auto-Profile & Query with Hybrid GraphRAG (`rag.*`)

Step 5 — Check SLAs, Governance & Human Approvals (`journey.`, `sentinel.`, `admin.*`)

3. Tool Selection Cheat Sheet for Agents

4. Architecture & Benchmark Comparison (Why Purple8)