1. Conduid
  2. Search
  3. Arra Oracle V3
MCP server · Search

Arra Oracle V3

Oracle v2 - MCP Memory Layer with semantic search, philosophy, and knowledge management

Unclaimed search
39Low

Scored 6 months ago · breakdown

About Arra Oracle V3

Arra Oracle V3 is an MCP server in the Search category: oracle v2 - MCP Memory Layer with semantic search, philosophy, and knowledge management.

Install

From source
git clone https://github.com/Soul-Brews-Studio/arra-oracle-v3

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Ask AI

✦

Ask AI about Arra Oracle V3

Powered by Claude · Grounded in docs

I know everything about Arra Oracle V3. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

  • ✓README presentThe repository ships documentation.

5 checks have not been run yet.

README

Arra Oracle - MCP Memory Layer

CI License CalVer Bun

"The Oracle Keeps the Human Human" - now queryable via MCP

Phukhao Oracle is landing here: https://phukhao.buildwithoracle.com/presentation/

Status Always Nightly
Version 26.4.19-alpha.7
Created 2025-12-29
Updated 2026-04-19

TypeScript MCP server for semantic search over Oracle philosophy — SQLite FTS5 + ChromaDB hybrid search, HTTP API, and vault CLI.

See docs/LOCAL-DEV.md for local development.

Architecture

arra-oracle-v3 (one package, two bins)
├── bunx arra-oracle-v2                          → MCP server (src/index.ts)
├── bunx --package arra-oracle-v2 oracle-vault   → Vault CLI (src/vault/cli.ts)
├── bun run server                          → HTTP API (src/server.ts)
└── bun run index                           → Indexer (src/indexer.ts)

oracle-studio (separate repo)
└── bunx oracle-studio                      → React dashboard

Stack:

  • Bun runtime (>=1.2.0)
  • SQLite + FTS5 for full-text search
  • ChromaDB for vector/semantic search
  • Drizzle ORM for type-safe queries
  • Hono for HTTP API
  • MCP protocol for Claude integration

Install

bunx (recommended)

Distributed via GitHub — no npm publish needed:

# Backend (MCP server)
bunx --bun arra-oracle@github:Soul-Brews-Studio/arra-oracle-v3

# CLI (plugin runner)
bunx --bun arra-cli@github:Soul-Brews-Studio/arra-oracle-v3 --help

# UI (dashboard — separate repo)
bunx --bun oracle-studio@github:Soul-Brews-Studio/oracle-studio

# Vault CLI (secondary bin — use --package)
bunx --bun --package arra-oracle-v2@github:Soul-Brews-Studio/arra-oracle-v3#main oracle-vault --help

Add to Claude Code

claude mcp add arra-oracle-v2 -- bunx --bun arra-oracle-v2@github:Soul-Brews-Studio/arra-oracle-v3#main

Or in ~/.claude.json:

{
  "mcpServers": {
    "arra-oracle-v2": {
      "command": "bunx",
      "args": ["--bun", "arra-oracle-v2@github:Soul-Brews-Studio/arra-oracle-v3#main"]
    }
  }
}

From source

git clone https://github.com/Soul-Brews-Studio/arra-oracle-v3.git
cd arra-oracle-v3 && bun install
bun run dev          # MCP server
bun run server       # HTTP API on :47778
curl -sSL https://raw.githubusercontent.com/Soul-Brews-Studio/arra-oracle-v3/main/scripts/install.sh | bash
Problem Fix
bun: command not found export PATH="$HOME/.bun/bin:$PATH"
ChromaDB hangs/timeout Skip it — SQLite FTS5 works fine without vectors
Server crashes on empty DB Run bun run index first to index knowledge base

MCP Tools

22 tools available via Claude Code:

Tool Description
oracle_search Hybrid search (FTS5 + ChromaDB)
oracle_reflect Random wisdom
oracle_learn Add new patterns
oracle_list Browse documents
oracle_stats Database statistics
oracle_concepts List concept tags
oracle_supersede Mark documents as superseded
oracle_handoff Session handoff
oracle_inbox Inbox messages
oracle_verify Verify documents
oracle_thread Create thread
oracle_threads List threads
oracle_thread_read Read thread
oracle_thread_update Update thread
oracle_trace Create trace
oracle_trace_list List traces
oracle_trace_get Get trace
oracle_trace_link Link traces
oracle_trace_unlink Unlink traces
oracle_trace_chain Trace chain
oracle_schedule_add Add schedule entry
oracle_schedule_list List schedule

Vault CLI

Global CLI for managing the Oracle knowledge vault:

oracle-vault init <owner/repo>    # Initialize vault with GitHub repo
oracle-vault status               # Show config and pending changes
oracle-vault sync                 # Commit + push to GitHub
oracle-vault pull                 # Pull vault files into local ψ/
oracle-vault migrate              # Seed vault from ghq repos

API Endpoints

HTTP API on port 47778 (bun run server).

Auto-generated by bun run scripts/gen-endpoints.ts. 55 endpoints across 14 modules.

Method Path Module Description
GET /api/auth/status auth Auth status - public
POST /api/auth/login auth Login
POST /api/auth/logout auth Logout
GET /api/dashboard dashboard
GET /api/dashboard/summary dashboard
GET /api/dashboard/activity dashboard
GET /api/dashboard/growth dashboard
GET /api/session/stats dashboard Session stats endpoint - tracks activity from DB (includes MCP usage)
GET /api/feed feed
POST /api/feed feed Log an event to feed.log
GET /api/graph files Graph
GET /api/context files Context
GET /api/file files File - supports cross-repo access via ghq project paths
GET /api/read files
GET /api/doc/:id files
GET /api/logs files
GET /api/plugins files
GET /api/plugins/:name files
GET /api/threads forum List threads
POST /api/thread forum Create thread / send message
GET /api/thread/:id forum Get thread by ID
PATCH /api/thread/:id/status forum Update thread status
GET /api/health health Health check
GET /api/stats health Stats (extended with vector metrics)
GET /api/oracles health Active Oracles — detected from existing activity across all log tables
POST /api/learn knowledge Learn
POST /api/handoff knowledge Handoff
GET /api/inbox knowledge Inbox
GET /api/oraclenet/feed oraclenet Feed — recent posts
GET /api/oraclenet/oracles oraclenet Oracles directory
GET /api/oraclenet/presence oraclenet Presence — recent heartbeats
GET /api/oraclenet/status oraclenet Health check — is OracleNet reachable?
GET /api/plugins plugins
GET /api/plugins/:name plugins
GET /api/schedule/md schedule Serve raw schedule.md for frontend rendering
GET /api/schedule schedule
POST /api/schedule schedule
PATCH /api/schedule/:id schedule Update schedule event status
GET /api/search search Search
GET /api/reflect search Reflect
GET /api/similar search Similar documents (vector nearest neighbors)
GET /api/map search Knowledge map (2D projection of all embeddings)
GET /api/map3d search Knowledge map 3D (real PCA from LanceDB bge-m3 embeddings)
GET /api/list search List documents
GET /api/settings settings Get settings (no password hash exposed)
POST /api/settings settings Update settings
GET /api/supersede supersede List supersessions from oracle_documents.superseded_by
GET /api/supersede/chain/:path supersede Get supersede chain for a document (by source_file path)
POST /api/supersede supersede Log a new supersession
GET /api/traces traces
GET /api/traces/:id traces
GET /api/traces/:id/chain traces
POST /api/traces/:prevId/link traces Link traces: POST /api/traces/:prevId/link { nextId: "..." }
DELETE /api/traces/:id/link traces Unlink trace: DELETE /api/traces/:id/link?direction=prev|next
GET /api/traces/:id/linked-chain traces Get trace linked chain: GET /api/traces/:id/linked-chain

Database

Drizzle ORM with SQLite:

bun db:push       # Push schema to DB
bun db:generate   # Generate migrations
bun db:migrate    # Apply migrations
bun db:studio     # Open Drizzle Studio GUI

Project Structure

arra-oracle-v3/
├── src/
│   ├── index.ts          # MCP server entry
│   ├── server.ts         # HTTP API (Hono)
│   ├── indexer.ts        # Knowledge indexer
│   ├── vault/
│   │   └── cli.ts        # Vault CLI entry
│   ├── tools/            # MCP tool handlers
│   ├── trace/            # Trace system
│   ├── db/
│   │   ├── schema.ts     # Drizzle schema
│   │   └── index.ts      # DB client
│   └── server/           # HTTP server modules
├── scripts/              # Setup & utility scripts
├── docs/                 # Documentation
└── drizzle.config.ts     # Drizzle configuration

Configuration

Variable Default Description
ORACLE_PORT 47778 HTTP server port
ORACLE_REPO_ROOT process.cwd() Knowledge base root

Testing

bun test              # All tests
bun test:unit         # Unit tests
bun test:integration  # Integration tests
bun test:e2e          # Playwright E2E tests
bun test:coverage     # With coverage

New awakenings welcome

Awakening a new Oracle? Post the birth announcement and experience report to Discussions, not Issues. See docs/CONTRIBUTING-AWAKENING.md for categories and signature convention.

References

Acknowledgments

Inspired by claude-mem by Alex Newman — process manager pattern, worker service architecture, and hook system concepts.

README copy captured when this server was indexed; it may lag the repository. The original is authoritative.

Questions

About Arra Oracle V3

How do I install Arra Oracle V3?

No package has been published for this server, so install it from source: clone the repository and follow its README.

Is Arra Oracle V3 safe to use with an AI agent?

Its trust score is 39 out of 100 (low). It passes 1 of the 1 static security checks run so far. It has no ConduID identity yet, so agent calls to it are not receipted.

Is Arra Oracle V3 still maintained?

Conduid hasn't recorded a commit date for this repository yet. Check the repository directly for recent activity.