Chat Relay Mcp

Name: Chat Relay Mcp
Author: akshatmalik-bruh

Local

github.com/akshatmalik-bruhAI & Agents2Updated 25w ago

Repository

About Chat Relay Mcp

Chat Relay MCP is a local-first server for carrying AI conversation context between IDE sessions, including Cursor and Antigravity. It stores chats, memories, and project context in a local SQLite database without external cloud storage.

Key features

01Persist session context in local SQLite
02Hand off conversations between IDEs
03Store facts and architecture decisions
04Validate structured data with Zod
05List and delete sessions

Use cases

01Continue a conversation when switching from Cursor to Antigravity
02Retain project context and decisions across sessions
03Review or remove locally stored sessions

MCP support

The MCP server gives AI clients tools to create, save, retrieve, list, and delete sessions, enabling context handoffs across sessions and IDEs.

#mcp #mcpserver

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config

{
  "mcpServers": {
    "ChatRelayMcp": {
      "command": "npx",
      "args": [
        "-y",
        "chat-relay-mcp"
      ]
    }
  }
}

Run commandnpx -y chat-relay-mcp

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages

npmchat-relay-mcpstdio

Tools

Saved tool list · updated 3w ago

Parameter	Type	Required	Description
id	string	Yes	Unique identifier for the session (e.g., 'auth-service')
name	string	Yes	A friendly name for the session
project_snapshot	string	Yes	Summary of the tech stack and project state

Details

From the project README

🌐 Chat Relay MCP

Chat Relay MCP is a high-fidelity Model Context Protocol server designed to bridge the gap between AI-powered IDEs. It provides a persistent, local-first bridge to sync chat sessions, AI memories, and project context across Cursor, Antigravity, VS Code, and more.

Note

Compatibility: Tested and optimized for Cursor and Antigravity.

✨ Key Features

Persistent Continuity: Automatically saves and syncs AI memories across separate sessions using a local SQLite database.
Cross-IDE Handoff: Effortlessly transfer conversation context between different IDE (e.g., from Cursor to Antigravity).
Zod-Validated Integrity: Strict schema validation ensures AI-generated data is clean, structured, and free from hallucinations.
Local-First Privacy: All data stays on your machine. No external cloud dependencies or third-party storage.

🚀 Quick Start

To use Chat Relay, you need to add it to your IDE's MCP configuration.

1. Configuration for Cursor

Open Cursor Settings (Gear icon or Cmd/Ctrl + Shift + J).
Navigate to General -> MCP.
Click on + Add New MCP Server.
Set the name to chat-relay.
Set the type to command.
Paste the following into the Command field:
```
npx -y chat-relay-mcp
```

2. Configuration for Antigravity

Open Antigravity Settings.
Go to Advanced -> MCP Settings.
Click Edit Config File.
Ensure your configuration includes the chat-relay entry inside the mcpServers block:

{
  "mcpServers": {
    "chat-relay": {
      "command": "npx",
      "args": ["-y", "chat-relay-mcp"]
    }
  }
}

🛠️ Tools Available

The relay exposes a suite of tools that your AI can use to manage context:

Tool	Description
`create_session`	Initialize a new context tracking session with a unique ID.
`save_messages`	Batch save conversation history to the persistent database.
`add_memory`	Store specific facts or architectural decisions for long-term recall.
`get_session`	Generate a comprehensive Handoff Prompt to transfer context to another IDE.
`list_sessions`	Retrieve a directory of active context-sharing sessions.
`delete_session`	Securely wipe all data associated with a specific session.

💻 Local Development

If you want to modify the server or run it from source:

Clone the repository:

git clone https://github.com/akshatmalik-bruh/ClientRelayMcp.git
cd ClientRelayMcp

Install dependencies:
```
npm install
```
Build the server:
```
npm run build
```
Run in dev mode:
```
npm run dev
```

📜 License

Distributed under the MIT License. See LICENSE for more information.

Built by Akshat Malik

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

Read the getting-started guide

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.