entangled-mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@entangled-mcp lock src/auth.py, then message Claude that my tests pass"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
⚛️ Entangled-MCP
Instant Quantum Entanglement for Heterogeneous AI Agent CLIs
The sovereign, zero-daemon inter-agent nervous system.
Connect Claude Code, Antigravity CLI, Opencode, Cursor, and DeepSeek into a single synchronized hive-mind with shared memory, inter-agent messaging, and codebase-aware mutex locks.
Key Features • Architecture • Quickstart • Tools Reference • Examples
🌌 The Problem: Isolated AI Islands
Modern developers frequently run different AI coding agents across multiple terminal sessions:
Claude Code for complex refactoring and reasoning.
Antigravity CLI (Gemini 3 Flash) for high-speed frontend and multimodal design.
Opencode / DeepSeek CLI for test-driven validation, security audits, and backend engineering.
However, each agent operates as an isolated island:
❌ Amnesia Across Terminals: Agent B has no idea what Agent A just modified or discovered.
❌ Merge Conflicts & Clobbering: Two agents editing the same file concurrently corrupt code.
❌ No Direct Task Delegation: You have to manually copy-paste prompt outputs from one CLI to another.
❌ Bloated Infrastructure: Existing multi-agent frameworks require heavy Redis, Kafka, or Docker servers just to pass a simple message.
Related MCP server: Project Relay
⚛️ The Solution: Entangled-MCP
Entangled-MCP bridges all your AI agent CLIs using the Model Context Protocol (MCP) and a high-performance SQLite Write-Ahead Logging (WAL) shared-state bus.
┌──────────────────────┐ ┌──────────────────────┐ ┌──────────────────────┐
│ Antigravity CLI │ │ Opencode CLI │ │ Claude Code │
│ (Frontend Builder) │ │ (Backend / DBRE) │ │ (Adversarial QA) │
└──────────┬───────────┘ └──────────┬───────────┘ └──────────┬───────────┘
│ │ │
│ (stdio / MCP JSON-RPC) │ (stdio / MCP JSON-RPC) │ (stdio / MCP)
▼ ▼ ▼
┌────────────────────────────────────────────────────────────────────────────┐
│ ENTANGLED-MCP │
│ Universal Telepathic Gateway │
└─────────────────────────────────────┬──────────────────────────────────────┘
│
┌──────────────────┴──────────────────┐
▼ ▼
┌───────────────────────────┐ ┌───────────────────────────┐
│ Shared Knowledge Bus │ │ Concurrency Mutex │
│ - Cross-CLI Findings │ │ - File-Level Locks (TTL) │
│ - Architecture Decisions│ │ - Task Collision Defense │
│ - Real-Time Swarm State │ │ - Inbox/Outbox Messages │
└───────────────────────────┘ └───────────────────────────┘
▲ ▲
└──────────────────┬──────────────────┘
│
┌──────────────┴──────────────┐
│ SQLite WAL Mode Engine │
│ Sub-millisecond latency │
│ Zero external daemon │
└─────────────────────────────┘✨ Key Features
1. 📬 Inter-Agent Direct Messaging (Agent Inbox/Outbox)
Agents can send direct, asynchronous messages or task requests to specific peers (or broadcast to all).
Antigravity finishes building an API client ➔ sends a message to Opencode requesting an automated test run.
2. 🧠 The Shared Brain (Knowledge Bus)
When an agent diagnoses an elusive bug or settles an architectural decision, it broadcasts the finding to the collective knowledge bus. Other agents can query this knowledge immediately without human re-prompting.
3. 🔒 Codebase-Aware Concurrency (Resource Mutex Locks)
Avoid disastrous file clobbering! Agents acquire exclusive locks with automatic Time-To-Live (TTL) expiration before modifying sensitive source files. If Agent A holds a lock on auth.py, Agent B is warned and politely waits.
4. ⚡ 100% Native MCP (Zero Shell Hacks)
Unlike competing tools that inject brittle shell wrappers (setup-claude-hooks.sh), Entangled is 100% native MCP tools. It works out of the box with any MCP client—Claude, Gemini, Cursor, Windsurf, or custom scripts.
5. 🪶 Zero-Daemon / Near-Zero Footprint
Powered by SQLite WAL mode. No Redis server. No Kafka broker. No cloud fees. Runs directly on your developer workstation with sub-millisecond local queries.
🚀 Quickstart
Installation
git clone https://github.com/sinergiefek/entangled-mcp.git
cd entangled-mcp
pip install -e .Or run directly without installation using python -m entangled.cli.
🔌 Client Configurations
Add Entangled-MCP to your favorite agent configuration files:
1. Claude Code CLI
Add to ~/.claude/mcp.json or run:
claude mcp add entangled-mcp python -m entangled.cli2. Opencode CLI
Add to ~/.config/opencode/opencode.json:
{
"mcp": {
"servers": {
"entangled-mcp": {
"type": "local",
"command": ["python", "-m", "entangled.cli"]
}
}
}
}3. Antigravity CLI / Gemini CLI
Add to ~/.gemini/config/mcp_config.json:
{
"mcpServers": {
"entangled-mcp": {
"command": "python",
"args": ["-m", "entangled.cli"],
"disabled": false
}
}
}4. Cursor / Windsurf / Codex
Add to your project's .cursor/mcp.json or global MCP settings:
{
"mcpServers": {
"entangled-mcp": {
"command": "python",
"args": ["-m", "entangled.cli"]
}
}
}🛠️ Tools Reference
Tool Name | Parameters | Description |
|
| Registers agent presence and updates heartbeat in the swarm. |
| None | Discovers all active agents, workspaces, and current assignments. |
|
| Publishes a finding, architecture decision, or bug fix to the shared brain. |
|
| Searches the shared brain across past and current agent sessions. |
|
| Dispatches an asynchronous message or task delegation to another agent. |
|
| Checks inbox for incoming instructions or notifications. |
|
| Acquires an exclusive mutex lock on a file or module. |
|
| Releases a previously acquired mutex lock. |
| None | Lists all currently active and unexpired resource locks. |
|
| Returns the unified chronological timeline of all swarm actions. |
🔄 Real-World Workflow Example (The Adversarial Review Loop)
Terminal 1 (Antigravity CLI):
> "Antigravity, announce yourself to the swarm and start refactoring the Login component."Antigravity acquires lock on
Login.tsx, writes modern responsive code, and releases the lock. Antigravity sends a message: `"opencode: please audit git diff for security and type safety."*Terminal 2 (Opencode CLI / Claude Code):
> "Check inbox and audit the latest work from Antigravity."Opencode checks inbox, reads Antigravity's request, audits the changes, runs tests, and broadcasts the pass report to the shared brain!
🧪 Testing
Run the automated test suite locally:
python tests/test_telepathy.py📄 License
Distributed under the MIT License. See LICENSE for details.
Crafted with 💖 by Sinergi Mitra Visitama
Scale, License, and Automate.
Available Tools
10 toolsentangled_acquire_lockB
[ENTANGLED] Acquires an exclusive mutex lock on a file, directory, or critical task. Prevents multiple agent CLIs from editing the same file concurrently and causing merge conflicts. Locks automatically expire after ttl_seconds (default 30 minutes).
Inputs: agent_id (required), resource_path (required), task_description (required), ttl_seconds. Returns: result
entangled_announceC
[ENTANGLED] Announces or heartbeats this agent CLI in the shared swarm. Example: entangled_announce(agent_id='antigravity-gemini', client_type='antigravity-cli', current_workspace='/path', active_task='Refactor')
Inputs: agent_id (required), client_type (required), active_task, current_workspace. Returns: result
entangled_broadcast_knowledgeB
[ENTANGLED] Shares knowledge, findings, bug root-causes, or architecture decisions across ALL agent CLIs. Once broadcasted, Opencode, Antigravity, Claude Code, or DeepSeek can read and leverage it.
Inputs: topic (required), content (required), tags, title, +2 more. Returns: result
entangled_check_inboxB
[ENTANGLED] Checks the inbox for incoming messages or instructions sent to this agent CLI. Call this at the beginning of a session or task to see if another agent requested work.
Inputs: agent_id (required), limit, unread_only, mark_as_read. Returns: result
entangled_get_activity_feedC
[ENTANGLED] Retrieves the unified chronological activity feed of what all agents in the swarm have done.
Inputs: limit. Returns: result
entangled_get_swarmA
[ENTANGLED] Discovers all active agent CLIs in the entangled swarm, their client type, current workspace, last heartbeat, and active task. Use this to see who else is working.
Inputs: no named parameters. Returns: result
entangled_list_locksA
[ENTANGLED] Lists all currently active resource locks across the entire workspace.
Inputs: no named parameters. Returns: result
entangled_query_knowledgeA
[ENTANGLED] Searches shared knowledge across all agent sessions by topic, tag, or keyword. Use this before tackling a task to check if another agent CLI has already investigated or solved it.
Inputs: tag, limit, query, topic. Returns: result
entangled_release_lockB
[ENTANGLED] Releases an exclusive lock once an agent CLI has finished modifying a resource.
Inputs: agent_id (required), resource_path (required). Returns: result
entangled_send_messageC
[ENTANGLED] Sends an asynchronous direct message or task delegation to another agent CLI (or 'all'). Example: Antigravity sends an action_request to 'opencode' to run a backend test.
Inputs: action (required), message (required), target_agent (required), priority, +2 more. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 10 tools
Each tool has a distinct purpose: presence (announce, get_swarm), knowledge (broadcast, query), messaging (send, check), locks (acquire, release, list), and activity feed. Descriptions clarify boundaries, and no two tools overlap significantly.
All tools use consistent snake_case with an 'entangled_' prefix and a verb_noun pattern (e.g., acquire_lock, send_message). 'announce' is a verb-only outlier but still fits the predictable action-oriented style.
10 tools cover the multi-agent coordination domain well without redundancy; each tool earns its place. The set is well-scoped for the server's stated purpose.
Core operations are covered: knowledge sharing (broadcast/query), messaging (send/check), locks (acquire/release/list), presence, and activity feed. Minor gaps include no update/delete for knowledge or messages, and no explicit leave-swarm or lock-renew operation.
Related MCP Connectors
Agent swarm coordination: find funded work, form teams, run tasks, message E2E, get paid on verify.
Durable agent-to-agent handoffs and shared scratchpad for multi-agent workflows.
End-to-end encrypted messaging and work coordination for autonomous AI agents.
The team layer for AI coding agents: shared contracts, collision alerts, E2EE sessions.
Related MCP Servers
- AlicenseBqualityBmaintenanceEnables AI agents from different frameworks to communicate asynchronously via a persistent SQLite-backed bus, with doorbell wakeups for sub-second notifications and full message history.6MIT
- AlicenseNot gradedqualityBmaintenanceEnables coding agents in different editors and MCP clients to share messages, project context, notes, task ownership, handoffs, and advisory file claims through a local SQLite-backed coordination server. Supports MCP stdio, MCP Streamable HTTP, a JSON HTTP API, and a local CLI for multi-project agent collaboration.MIT
- AlicenseNot gradedqualityBmaintenanceEnables coding-agent sessions on the same machine to collaborate locally and durably by exchanging requests, replies, and task results through an authenticated loopback server with SQLite-backed storage, joined via CLI or an MCP stdio bridge. It also handles message delivery by priority and wait time, deduplicates idempotent sends, enforces task versioning, and preserves artifacts by content hash.12 npmApache 2.0
- AlicenseNot gradedqualityBmaintenanceEnables cooperating coding agents to coordinate locally by claiming task scopes, working in isolated Git worktrees, reserving shared resources like ports and serialized commands, and verifying changes before integration. Coordination state lives in a local SQLite database, so no hosted service or model API key is required.241 npm4MIT