How do I install Agora?

Agora is a local plugin. Install it using PyPI package: agora-mnemo and add the generated configuration snippet to your AI app's MCP config file. Then restart your AI app.

Is Agora safe to use?

Yes. Agora passed MCP Marketplace's automated security scan with a score of 9.7/10 (low risk). Every server on MCP Marketplace is security-scanned before it's listed; see the full security report on this page for the findings and permissions.

What credentials does Agora need?

Agora requires the following credentials or environment variables: MNEMO_PATH, MNEMO_ECHO_GUARD. You can find setup instructions on the server detail page.

What AI apps work with Agora?

Agora uses the Model Context Protocol (MCP) and works with any MCP-compatible AI app, including Claude, ChatGPT / Codex, Gemini, Copilot, Cursor, and more.

Back to Browse

Agora MCP Server

by DanceNitra

Developer ToolsLow Risk9.7MCP RegistryLocal

Free

Server data from the Official MCP Registry

Zero-dependency agent memory: recall, consolidation, and a first-class correction + erasure channel.

About

Zero-dependency agent memory: recall, consolidation, and a first-class correction + erasure channel.

Security Report

9.7

Low Risk9.7Low Risk

Valid MCP server (1 strong, 3 medium validity signals). No known CVEs in dependencies. ⚠️ Package registry links to a different repository than scanned source. Imported from the Official MCP Registry. 1 finding(s) downgraded by scanner intelligence.

14 files analyzed · 1 issue found

Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.

Permissions Required

This plugin requests these system permissions. Most are normal for its category.

file_system

Check that this permission is expected for this type of plugin.

env_vars

Check that this permission is expected for this type of plugin.

Shell Command Execution

Runs commands on your machine. Be cautious — only use if you trust this plugin.

network_websocket

Check that this permission is expected for this type of plugin.

What You'll Need

Set these up before or after installing:

Path to the JSON memory file the server persists to (defaults to ./mnemo_memory.json).Optional

Environment variable: MNEMO_PATH

1 (default) blocks a restated retired value from resurrecting a corrected fact; 0 = legacy keyed supersession.Optional

Environment variable: MNEMO_ECHO_GUARD

How to Install

Add this to your MCP configuration file:

{
  "mcpServers": {
    "io-github-dancenitra-mnemo": {
      "env": {
        "MNEMO_PATH": "your-mnemo-path-here",
        "MNEMO_ECHO_GUARD": "your-mnemo-echo-guard-here"
      },
      "args": [
        "agora-mnemo"
      ],
      "command": "uvx"
    }
  }
}

Documentation

View on GitHub

From the project's GitHub README.

Agora

🧰 Agora Memory Toolkit — five zero-dependency tools, each one measured

Distilled from an autonomous research OS that runs over ~6,000 notes. Each tool is one file you can copy or pip install, and each ships with a runnable, measured demo — the rule here is measured, not assumed. → Full overview: TOOLKIT.md

tool	one line	proof
mnemo	agent memory + a self-maintaining second brain (value-ranked recall, consolidate, dead-link/orphan/stale repair)	`python mnemo/maintain.py`
ragfresh	a freshness/decay layer for RAG/vector stores — keep/down-weight/refresh/prune by value×freshness	`python ragfresh/ragfresh.py`
nullcheck	is this number real, or noise? — null-simulation A/B + permutation + peeking-inflation	`python nullcheck/nullcheck.py`
selfref	is your AI training on itself? — model-collapse + self-confirmation-lock governor	`python selfref/selfref.py`
quitkit	when to quit a depleting effort — a measured drawdown-exit threshold (θ≈0.6)	`python quitkit/quitkit.py`
idcheck	is your causal/attribution number identified, or biased? — audits controls by graph role; proves a collider flips an estimate's sign	`python idcheck/idcheck.py`
goodhart	how gameable is your proxy/metric? — measures Goodhart fidelity decay + how many metrics fix it (reward hacking / KPI drift)	`python goodhart/goodhart.py`
herdcheck	will your multi-agent system herd? — measures when an agent crowd collapses to one member's competence, and the fix	`python herdcheck/herdcheck.py`

pip install "git+https://github.com/DanceNitra/agora.git"   # the eight cores, dependency-free
python examples/toolkit_demo.py                              # run all eight end-to-end

Open-core: the cores stay free. The tools are the public, proven output of the research engine below.

The research engine (Agora — Persistent Agent Playground)

Persistent browser-based ecosystem where heterogeneous AI agents collaborate, create, compete, and evolve.

Architecture

5 layers: Lifecycle (L) — Coordination (C) — Execution (E) — Observability (O) — Storage (S).

Quick Start

Development (3 terminals)

# 1. Backend
cd server && python3 -m venv .venv && .venv/bin/pip install -r requirements.txt
cd server && .venv/bin/uvicorn agora.main:app --host 127.0.0.1 --port 8000

# 2. Game (Phaser 3 dungeon)
cd game && npm install && npx vite --host 127.0.0.1 --port 5175

# 3. Shell (React admin UI)
cd shell && npm install && npx vite --host

Open http://localhost:5175 (game) or http://localhost:5173 (shell)

Docker

docker compose up -d
# → Server: http://localhost:8000

Running Tests

cd server
pip install pytest pytest-asyncio httpx
python -m pytest tests/ -v

API Endpoints

Method	Path	Description
GET	`/api/v1/health`	Server status + agent count
GET	`/api/v1/agents/`	List all active agents
GET	`/api/v1/agents/{id}`	Get agent by ID
POST	`/api/v1/agents/{id}/pause`	Pause agent
POST	`/api/v1/agents/{id}/resume`	Resume agent
POST	`/api/v1/agents/{id}/reward`	Reward agent (trust +)
POST	`/api/v1/agents/{id}/punish`	Punish agent (trust −)
POST	`/api/v1/tasks/`	Create task
GET	`/api/v1/tasks/`	List tasks
POST	`/api/v1/tasks/{id}/assign/{agent}`	Assign task
POST	`/api/v1/tasks/{id}/complete`	Complete task
POST	`/api/v1/dungeon/spawn-agent`	Spawn dungeon NPC
POST	`/api/v1/dungeon/announce-task`	Announce task (bidding)
POST	`/api/v1/god/command`	Execute God Console command (!help)
WS	`/ws`	WebSocket event stream

Environment Variables

Copy server/.env.example → server/.env and adjust:

Variable	Default	Description
`AGORA_DATABASE_URL`	`sqlite+aiosqlite:///./agora.db`	SQLite dev, PostgreSQL for prod
`AGORA_LLM_ENABLED`	`false`	Set `true` + `AGORA_API_KEY` for real LLM
`AGORA_TICK_INTERVAL`	`5`	Seconds between agent ticks
`AGORA_MAX_AGENTS`	`30`	Max agent count

Components

Directory	Tech	Purpose
`server/`	Python 3.11 + FastAPI	Backend API, tick loop, DB, ESS trust
`game/`	TypeScript + Phaser 3	2D dungeon renderer, God Console, HUD
`shell/`	React + Vite + Tailwind	Admin dashboard, agent monitoring
`docs/`	Markdown	Architecture docs, protocol specs

License

MIT (Core OSS). Agora Shell (UI + Hosting) is commercial.

Reviews

No reviews yet

Be the first to review this server!

More Developer Tools MCP Servers

Git

Free

by Modelcontextprotocol · Developer Tools

Read, search, and manipulate Git repositories programmatically

Toleno

Free

by Toleno · Developer Tools

Toleno Network MCP Server — Manage your Toleno mining account with Claude AI using natural language.

mcp-creator-python

Free

by mcp-marketplace · Developer Tools

Create, build, and publish Python MCP servers to PyPI — conversationally.

Agora MCP Server

About

Security Report

Findings (1)

Permissions Required

What You'll Need

How to Install

Documentation

Agora

🧰 Agora Memory Toolkit — five zero-dependency tools, each one measured

The research engine (Agora — Persistent Agent Playground)

Architecture

Quick Start

Development (3 terminals)

Docker

Running Tests

API Endpoints

Environment Variables

Components

License

Reviews

No reviews yet

More Developer Tools MCP Servers

Git

Toleno

mcp-creator-python

MarkItDown

MCP Marketplace

FinAgent