Advertise
MCP.so
Sign In
G

Grantai MCP Server

@solonai-com

Repository

Basic information

Category

Other

Transports

stdio

Author

solonai-com

Submitted by

Lawrence Grant

About Grantai MCP Server

Fast, sub millisecond, local on device long term memory for LLMs, Coding Tools and AI Agents. Recall exact details from yesterday of five years ago. Install in 5 minutes.

#long-term-memory-continued-context-agentic-collaboration-secure-local-memory

Grantai MCP Server config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "grantai": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "GRANTAI_LICENSE_KEY",
        "ghcr.io/solonai-com/grantai-memory:1.8.7"
      ],
      "env": {
        "GRANTAI_LICENSE_KEY": "<YOUR_LICENSE_KEY>"
      }
    }
  }
}

Grantai MCP Server tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is GrantAi?

GrantAi is a shared memory layer for AI agents that provides persistent, local, and encrypted memory. It solves the problem of agents losing context when sessions end by allowing knowledge to survive across sessions and be shared among multiple AI tools. It is designed for developers using coordination frameworks like CrewAI, AutoGen, or LangGraph.

How to use GrantAi?

Install GrantAi via native macOS/Linux (run ./install.sh YOUR_LICENSE_KEY) or Docker for all platforms. Add it as an MCP server to your Claude Desktop config or any MCP-compatible client. GrantAi exposes tools such as grantai_teach, grantai_infer, grantai_learn, and others for storing and querying memory.

Key features of GrantAi

  • Persistent memory that survives sessions and accumulates over time
  • Shared across multiple AI agents with no configuration needed
  • Sub-12ms recall regardless of memory size
  • 100% local — data never leaves your machine
  • AES-256 encrypted at rest with zero data egress
  • MCP tools for storing, querying, and importing memory

Use cases of GrantAi

  • Maintain continuous context for a single AI agent across multiple sessions
  • Enable multiple agents (e.g., researcher and coder) to share a common knowledge base
  • Hand off information between agents with optional speaker attribution for role‑based retrieval
  • Import large codebases or git history for agent‑assisted development

Frequently asked questions

1

What makes GrantAi different from other memory solutions?

GrantAi offers persistent memory shared across agents, sub‑second recall, 100% local storage, and AES‑256 encryption. It works with any MCP‑compatible client and requires no external services.

2

How do multiple agents share memory with GrantAi?

All agents that point to the same GrantAi instance automatically read from and write to the same memory pool. Optionally, use the `speaker` parameter to attribute stored content and `from_agents` to filter retrieval.

3

Is my data secure with GrantAi?

Yes. GrantAi runs 100% locally, encrypts all data at rest with AES‑256, and guarantees zero data egress from your machine.

4

What are the system requirements for GrantAi?

Native support for macOS (Apple Silicon) and Linux (x64). All platforms are supported via Docker.

5

How much does GrantAi cost?

GrantAi offers a 30‑day free trial with no credit card required. Paid plans start at $29/month or $299/year for Personal, and $25/seat/month for Team.

Comments

More Other MCP servers

EverArt

modelcontextprotocol

Model Context Protocol Servers

88.1K

Glasswarp

Glasswarp

See and control a real Windows PC you own — from any MCP client, locally or remotely. Observe (UIA + screenshots), click/type/drag/scroll, launch apps, owner Live View. BYOH: your machine, your key.

The Living Bread

The Living Bread

A free remote MCP server for The Living Bread. Bible passages read word for word from a stored public domain text with an evidence label, keyword search and cross references, real churches, gatherings and prayer groups w

Handl

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.

Screenpipe

screenpipe

YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context

22.0K
Advertise