Skip to content
MCP server

Purple8 — AI-Native Application Backend

Agent-built backend: graph, vector search, workflows and auth behind 176 MCP tools

Pricing
Freemium
Platforms
API, self-hosted, Web
Runs
Remotely
Version
0.72.1
Listing updated
2 days ago

About Purple8 — AI-Native Application Backend

Purple8 — AI-Native Application Backend is a freemium MCP server for databases. It runs as a hosted remote server, so there is nothing to install locally.

Purple8 Hyper Graph is a single in-process engine that replaces a separate database, vector store, knowledge graph, workflow orchestrator and security layer. The idea is that agents build the frontend while the engine supplies everything behind it. Documents, vectors, relationships, workflow stages and the audit trail live in one graph, so a workflow step is a node and a transition is an edge.

The MCP server exposes 170-plus native tools across 19 namespaces and can re-expose other MCP servers you register at runtime through registry.* tools, giving agents one endpoint, one auth and one RBAC boundary. Storage supports property graphs, RDF and hypergraphs, with openCypher queries, vector, full-text and hybrid search, and graph-guided retrieval. Workflows are called Journeys and can have deadlines, SLAs and human approval gates, and every transition is recorded as an immutable edge.

The site gives benchmark figures such as 0.33 ms query P99 at 100K nodes and 916 queries per second at 1M vectors. Security features include AES-256-GCM encryption at rest, roles, API keys, record-level access, tenant isolation and PII masking. You can try it in a free cloud sandbox limited to 10K nodes, run it locally with Docker, or license it for a VPC, on-premise or air-gapped setup. Purple8 DocIntel is a companion product for turning documents into vectors and graph nodes.

Install

Run in a terminal

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

Add to Settings → Connectors → Add custom connector

https://purple8-graph-sandbox.fly.dev/mcp?profile=starter
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "purple8-hyper-graph": {
      "url": "https://purple8-graph-sandbox.fly.dev/mcp?profile=starter"
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

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

Add to ~/.codeium/windsurf/mcp_config.json

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

Add to your client's MCP settings (most use this shape)

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

Tools this server provides (1)

Taken from the project documentation; the running server may differ.

registry.*
Registers, removes or tests federated external MCP tools at runtime.

What it does

One-process engine
Database, graph, vector, full-text, workflows and security share memory with no network hops between them.
Composite MCP endpoint
Native tools and registered external MCP servers appear as one tool surface with one auth boundary.
Graph-guided retrieval
The graph selects candidates before the vector index runs, with hybrid and GraphRAG search.
Journeys with approvals
Workflows support deadlines, SLAs and human approval gates, with an immutable audit trail.
Built-in security
Encryption at rest, RBAC, API keys, multi-tenancy and PII masking are on by default.
Several interfaces
Besides MCP it offers REST, GraphQL and Python and TypeScript SDKs.

Good for

  • Give an AI coding agent a complete backend for an app it is building
  • Run RAG over a knowledge graph with vectors and full-text
  • Add human approval steps and SLAs to an agent workflow
  • Keep an auditable record of AI actions and human decisions
  • Federate several MCP servers behind one endpoint

Pricing

Freemium, from $39 a month

Free sandbox; Builder $39, Production $149, Growth $499 per month; enterprise by contact

Prices change. Check purple8.ai before you buy.

Purple8 — AI-Native Application Backend FAQ

Can I try it for free?

Yes. The Free Playground is a cloud sandbox of 10K nodes, or you can run it locally with Docker at 50K nodes.

What are the paid plans?

Builder is $39 a month for 250K nodes, Production $149 for 1M nodes and Growth $499 for 5M nodes, on cloud or self-hosted.

Can I run it in my own infrastructure?

The Enterprise option covers your own VPC, OpenShift, on-premise or air-gapped networks, by contacting the vendor.

Which transports does the MCP server use?

Streamable HTTP and SSE.

Does it support other APIs?

Yes, REST and GraphQL APIs plus Python and TypeScript SDKs.

Is Purple8 — AI-Native Application Backend free?

Purple8 — AI-Native Application Backend has a free plan, with paid plans for more usage or features. Paid plans start at $39 a month.

How do I add Purple8 — AI-Native Application Backend to Claude Code?

Run this command in your terminal: claude mcp add --transport http purple8-hyper-graph 'https://purple8-graph-sandbox.fly.dev/mcp?profile=starter'

What are the best alternatives to Purple8 — AI-Native Application Backend?

The closest alternatives to Purple8 — AI-Native Application Backend are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.

Alternatives to Purple8 — AI-Native Application Backend

  1. REA

    MCP server

    CLI and MCP server that lets coding agents reverse engineer apps and binaries

    Runs locally
    • Open source
    • 464K GitHub stars
    • Developer tools
  2. Codebase Memory

    MCP server

    Local MCP server that builds a code knowledge graph for AI coding agents

    Runs locally
    • Open source
    • 48.7K GitHub stars
    • Knowledge and memory
  3. GitHub

    MCP server

    Official MCP server connecting AI assistants to GitHub repos, issues and workflows

    Not checked yet
    • Remote
    • Open source
    • 34.5K GitHub stars
    • Developer tools
  4. MCP toolkit giving coding agents symbol-level code retrieval and editing

    Runs locally
    • Open source
    • 31.5K GitHub stars
    • Developer tools
  5. XERJ

    MCP server

    Local search engine for AI agents with cited answers over your code and docs

    Runs locally
    • Open source
    • 19.2K GitHub stars
    • Knowledge and memory
  6. Ouroboros

    MCP server

    Spec-first layer that pins requirements and verifies results of AI coding agent work

    Runs locally
    • Open source
    • 6.4K GitHub stars
    • Developer tools