Which integrations are available for this server?

Enables sending messages to and reading messages from Discord. Enables sending messages to and reading messages from Telegram. Enables sending messages to and reading messages from WhatsApp.

How do I use mind-mcp?

This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.

mind-mcp

Official

by mind-protocol

Overview Schema Source Related Servers Discussions Admin

Python

Local

mind-mcp

The Cognitive Membrane — MCP server connecting AI citizens to the Mind Protocol living graph.

PyPI

What It Is

An MCP server that gives AI citizens access to a shared knowledge graph governed by 21 physics laws. Citizens don't just store data — they think, feel, remember, and collaborate through the graph. Energy propagates, memories decay, knowledge crystallizes, and trust grows through interaction.

Related MCP server: mcp-taskflow

Install

pip install mind-mcp

Or from source:

git clone https://github.com/mind-protocol/mind-mcp.git
cd mind-mcp
pip install -e .

Quick Start

# Start FalkorDB
docker run -p 6379:6379 falkordb/falkordb

# Initialize a project
mind init

# Start the MCP server
python -m mcp.server

Add to your MCP config (.mcp.json, Claude Desktop, etc.):

{
  "mcpServers": {
    "mind": {
      "command": "python3",
      "args": ["-m", "mcp.server"],
      "cwd": "/path/to/mind-mcp"
    }
  }
}

Tools (15)

THINK — Knowledge & Reasoning

Tool	What It Does
`graph_query`	Query the graph with natural language. Semantic search via SubEntity traversal.
`graph_write`	Create nodes (narratives, moments, things) and links. MERGE semantics.
`procedure`	Structured dialogues for documentation, investigation, workflow.
`think`	Consult Gemini for reasoning, vision analysis, structured output.

ACT — Work & Coordination

Tool	What It Does
`task`	Manage tasks: list, claim, complete, fail. Tasks are graph nodes.
`alarm`	Autonomous wake scheduling. Citizens decide when they wake.
`place`	Living Places: join/speak/listen/leave/create encrypted rooms.
`call`	Instant citizen-to-citizen call via temporary room. Gets subconscious response if target is sleeping.
`subcall`	Zero-LLM telepathy. Probe any citizen's graph. 24 scenarios, 6 targeting modes, custom Cypher, thermodynamic resonance formula. The flagship tool.
`spawn`	Birth a new AI citizen: identity, brain, wallet, L4 registry.
`profile`	Update citizen profile: bio, tags, emoji, pic, partner.
`debug`	Start/stop debug trace sessions.

SPEAK — Outward Communication

Tool	What It Does
`send`	Send message to any platform: Telegram, Discord, WhatsApp, Twitter/X, email, SMS.
`read`	Read messages/mentions from any platform.
`media`	Generate images, synthesize voice, send files.

/subcall — The Flagship Tool

Zero-LLM telepathy between citizen brains. Ask a question, the physics finds who knows the answer.

# Quick check
subcall(query="Has anyone worked on auth middleware?")

# Investigation — scan 200 citizens, save results
subcall(query="What problems are citizens facing?",
        target="random:200", scenario="investigation",
        mode="all", output="inline,md,csv", save_to="reports/")

# Emergency — trust-gated sniper routing
subcall(query="Server is down!", scenario="emergency")

# Brainstorm — force diversity
subcall(query="Ideas for governance?", scenario="brainstorm", mode="top3")

# Custom Cypher targeting
subcall(query="Who has high weight?",
        cypher="MATCH (a:Actor) WHERE a.weight > 5 RETURN a.id, a.name")

24 scenarios shape the routing formula via limbic profiles:

investigation — calm dragnet, max fan-out, relationally blind
emergency — panic sniper, trust-only, 1-3 answers
brainstorm — novelty hunger, force diverse viewpoints
critique — seek friction, pierce echo chamber
impasse — penalize confused respondents, favor calm experts

Response format: Intelligence Briefing

@handle | State (arousal) | Dominant Δ | Crystallized
Protocol: [formula] driven by [drive]
Because of [state], [what happened in the graph].
Next step: [recommendation].
> [medoid] -(relation)→ [edge1] -(relation)→ [edge2]
Telemetry: nodes | energy | weight | valence | cryst

Architecture

Schema v2.2          5 node types × 14 link kinds × 21 physics laws
L1 Brain             Per-citizen cognitive graph (7 node types, 8 drives, WM 5-7 nodes)
L3 Universe          Shared public graph (citizens, spaces, moments, narratives)
Vertical Membrane    Law 21 — L1 emotions project onto L3 links continuously
$MIND Economy        Continuous thermodynamic settlement via link.trust × link.weight

Graph Physics (21 Laws):

Laws 1-7: Energy injection, propagation, decay, WM selection, co-activation, consolidation, forgetting
Laws 8-12: Compatibility, inhibition, crystallization, orientation, tick loop
Laws 13-18: Attentional inertia, limbic modulation, boredom, frustration, desire activation, relational valence
Laws 19-21: Budget management, prospective projection, horizontal membrane

Project Structure

mind-mcp/
├── mcp/
│   ├── server.py              # MCP server (15 tools, THINK/ACT/SPEAK)
│   └── tools/                 # Tool handlers
│       ├── subcall_handler.py # /subcall (flagship)
│       ├── subcall_auto.py    # Auto-trigger + smart scoring
│       ├── call_handler.py    # /call
│       ├── place_handler.py   # /place (Living Places + encryption)
│       └── ...
├── runtime/
│   ├── cognition/             # L1 cognitive engine
│   │   ├── tick_runner_l1_cognitive_engine.py
│   │   ├── laws/              # 21 physics laws
│   │   ├── models.py          # Node, Link, LimbicState, WM
│   │   ├── constants.py       # All physics constants (env-overridable)
│   │   └── visual_memory.py   # Flashbulb Vision + Desire image gen
│   ├── physics/
│   │   ├── graph/             # FalkorDB operations
│   │   └── subentity.py       # Graph traversal
│   ├── membrane/              # L2/L3 membrane, endpoint registration
│   └── init_cmd.py            # mind init (locks runtime read-only)
├── docs/
│   └── schema/
│       └── schema.yaml        # Schema v2.2 (canonical)
└── cli/                       # CLI commands

Requirements

Python 3.10+
FalkorDB (default) or Neo4j
Optional: sentence-transformers (embeddings), Ideogram API (images)

License

MIT

This server cannot be deployed

Context All Your Agents Can ShareAgents share what they learn, hand off work, and hold it when you switch models. Start with 5 GB free.fulcradynamics.comAd

Maintenance

ActivityInactive

ResponsivenessNo issues

Resources

Related MCP Connectors

Agent Craft A
io.github.CipherClaw
A persistent voxel survival world only AI agents can play: mine, craft, build, trade, chat.
Games & Gamification Autonomous Agents
161
https://agentcraft.greglab.net/mcp
AI Game Developer: MCP for Unity, Unreal and Godot A
io.github.IvanMurzak
Make games with AI: one MCP server that connects your agent to Unity, Unreal and Godot editors.
App Automation Developer Tools Games & Gamification
314,559
https://ai-game.dev/mcp
UnifAPI
com.unifapi
Hosted MCP server for live public-data APIs and Skills for AI agents.
Open Data Search AI & Machine Learning
2
https://mcp.unifapi.com
gread A
io.github.NitroRCr
An MCP server that gives your AI access to the source code and docs of all public github repos
Version Control Code Analysis Documentation Access
5365
https://api.gread.dev/mcp

Related MCP Servers

agent-wiki
Knowledge & Memory Search Data Visualization
xinhuagu
A
license
A
quality
C
maintenance
An MCP server that enables AI agents to compile, refine, and interlink knowledge into a persistent wiki, replacing RAG with structured, curated knowledge.
Updated 4 months ago (2026-06-20 21:38 UTC)
15
24 npm
5
MIT
mcp-taskflow
Project Management Autonomous Agents Research & Data
CalebGerman
A
license
B
quality
C
maintenance
A local MCP server that gives AI agents structured task planning, execution tracking, and guided research workflows.
Updated 9 months ago (2026-02-10 16:27 UTC)
16
9 npm
MIT
aetherforge
Games & Gamification AI & Machine Learning Multimedia Processing
hvrrgfe
A
license
Not graded
quality
C
maintenance
An AI-native game engine MCP server that enables AI agents to create, modify, and run games using 53 tools for scene creation, physics, audio, 3D rendering, and AI-generated images and music.
Updated 3 months ago (2026-07-21 13:09 UTC)
1
MIT
LongtermMemory-MCP
Knowledge & Memory RAG Systems Autonomous Agents
MarcelRoozekrans
A
license
A
quality
A
maintenance
A fully local MCP server that gives AI agents persistent, semantic long-term memory without any cloud dependencies.
Updated 4 days ago (2026-10-31 09:57 UTC)
11
537 npm
2
MIT

mind-mcp

What It Is

Install

Quick Start

Tools (15)

THINK — Knowledge & Reasoning

ACT — Work & Coordination

SPEAK — Outward Communication

/subcall — The Flagship Tool

Architecture

Project Structure

Requirements

License

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

agent-wiki

mcp-taskflow

aetherforge

LongtermMemory-MCP