ai.purple8.www/purple8-hyper-graph

up checked 2026-11-11T10:37:54.794Z

Unclaimed · Unverified

Agent searches it appeared in, last 30 days: 0. Run this server? Claim the listing: verified label, uptime alerts and analytics.

Publisher-provided title

Purple8 — AI-Native Application Backend

Publisher-provided description

Complete backend for AI-built apps: data, auth, workflows, SLAs, HITL & RAG in 176 MCP tools.

Summary by lookupd

Lets an agent store and query graph data, run hybrid vector and graph retrieval, and drive multi-stage workflows with human approval steps.

Install

Claude Code, remote (streamable-http)

claude mcp add --transport http purple8-hyper-graph 'https://purple8-graph-sandbox.fly.dev/mcp?profile=starter'

Claude Code, remote (sse)

claude mcp add --transport sse purple8-hyper-graph 'https://purple8-graph-sandbox.fly.dev/mcp/sse?profile=starter'

Codex, remote (streamable-http)

codex mcp add purple8-hyper-graph --url 'https://purple8-graph-sandbox.fly.dev/mcp?profile=starter'

Codex, remote (sse)

codex mcp add purple8-hyper-graph --url 'https://purple8-graph-sandbox.fly.dev/mcp/sse?profile=starter'

Cursor, remote (streamable-http) → .cursor/mcp.json

{
  "mcpServers": {
    "purple8-hyper-graph": {
      "url": "https://purple8-graph-sandbox.fly.dev/mcp?profile=starter"
    }
  }
}

Cursor, remote (sse) → .cursor/mcp.json

{
  "mcpServers": {
    "purple8-hyper-graph": {
      "type": "sse",
      "url": "https://purple8-graph-sandbox.fly.dev/mcp/sse?profile=starter"
    }
  }
}

Other clients: docs. Or tell your agent: Set up lookupd for me: read https://lookupd.com/agent.md and follow it.

Tools (28 tools)

Publisher-provided text

• rag.query Flat Vector RAG — retrieves the most relevant graph nodes by pure vector similarity (HNSW + RRF fusion + keyword fallback), then calls the configured LLM to gen
• rag.hybrid_query Hybrid Graph-Vector RAG — fuses vector similarity AND graph structural signals at every stage: dual-seed fusion (Weighted RRF over vector rank + degree centrali
• rag.profile_collection Analyse the graph topology and return recommended RAG retrieval settings. Profiles node count, edge density, degree distribution, edge-type distribution, and e
• graph.query Execute a Cypher query against the Purple8 knowledge graph and return matching records. Use for nodes, edges, paths, or aggregated data.
• graph.vector_search Find the k nearest nodes to a natural-language query using the HNSW vector index.
• graph.hybrid_search Combine vector similarity with graph traversal for highest-recall retrieval. Best when graph structure matters.
• graph.traverse Walk the graph from a starting node following edges up to a given depth.
• graph.add_node Insert a new node into the graph (accepts `type`, `label`, or `node_type`). Requires editor role.
• graph.add_edge Create a directed edge (relationship) between two existing nodes. This is the primary agentic handoff mechanism — agents write their output as edges (e.g. DERI
• graph.update_node Update properties or labels on an existing node. Properties are merged with existing values (patch semantics — only the keys you supply are changed). Labels r
• graph.get_node Retrieve a node and all its stored properties by ID.
• data.ingest_text Extract entities and relationships from raw text and write them into the graph. Calls preview first, then commits the complete extraction on success. auto_commi
• data.commit Commit a reviewed extraction or your own extractor's output without invoking DocIntel. Uses the complete POST /ingest/commit contract: entities, relationships,
• journey.start Create a new Journey Engine instance for an entity and move it to the first stage. All transitions are recorded as immutable graph edges. Requires editor role
• journey.advance Advance a journey instance to the next stage. Actor and notes are written to the audit trail as an ADVANCED_TO edge. Requires editor role.
• journey.status Return the full state and audit trail for a journey instance — every stage transition, AI recommendation, and HITL decision.
• journey.define Define a new journey type (workflow template) with ordered stages, owner systems, and per-stage SLA policies. Once defined, instances can be started with journ
• journey.list List journey instances with optional filters. Use this to discover what is in flight, find instances for a specific entity, or check all instances of a given t
• journey.list_hitl List pending Human-In-The-Loop (HITL) tasks — decisions that require a human (or agent acting as human proxy) to approve, reject, or escalate before the journey
• journey.resolve_hitl Resolve a Human-In-The-Loop (HITL) task — approve, reject, or escalate it. On approval the journey automatically advances to the next stage if advance_to_stage
• data.ingest_file Send a document file (PDF, DOCX, PPTX, XLSX, HTML, IFC, CSV, …) to Purple8 DocIntel for parsing, entity extraction, and graph ingestion. The document is fetche
• graph.assert_statement Idempotently assert one native RDF quad with exact lexical terms, explicit blank-node scope and optional graph name. Uses existing node/edge create and read per
• graph.semantic_query Read-only indexed RDF/LPG pattern query with policy-filtered evidence. Use tagged rdf, lpg and lpg_edge patterns. Returns unified bindings and evidence or, with
• graph.counts Return the total number of nodes in the graph, optionally filtered by label. A cheap situational-awareness call an agent can make before deciding how to query
• graph.labels List every node type (label) in the graph with how many nodes carry it, largest first. Cheap — O(types), not O(nodes). Call this first to learn what the graph
• schema.validate Validate the tenant's live graph data against the defined schema. Reports missing required properties, type/enum violations, edge source/target-type violations
• schema.define_node_type Define a new node type — the primitive that lets an agent build the data model itself. The type_name becomes the canonical label for nodes of this type. Set a
• schema.define_edge_type Define a new edge (relationship) type. Constrain which node types may be the source/target, declare edge properties, and set cardinality (one_to_one | one_to_m

Details

• Version: 0.72.1
• Transports: streamable-http, sse
• Uptime (7 days): 100%
• Median latency: 7163 ms
• First indexed: 2026-11-06T09:17:11.122Z
• Last seen in registry: 2026-11-06T09:17:11.137Z
• Website: https://www.purple8.ai/products/hyper-graph/

Badge for your README

Shows this live status and links here; updates hourly.

[![lookupd status](https://lookupd.com/badge/ai.purple8.www/purple8-hyper-graph.svg)](https://lookupd.com/servers/ai.purple8.www/purple8-hyper-graph)

• 62033 servers
• Last crawl: 2026-11-11T15:38:39.561Z
• API base: https://api.lookupd.com
• MCP URL: https://api.lookupd.com/mcp