# GreatArrow.ai MCP server
> Keep one private memory shared across Claude, ChatGPT, Cursor and other AI clients, with sources named in answers.
- Listing: https://mcp.tc/i/greatarrow-ai
- Connect: use the server's own URL `https://www.greatarrow.ai/api/mcp` (OAuth sign-in at the server); clients connect to it directly. The listing link is a page, not an MCP endpoint.
- Type: remote (Streamable HTTP)
- Auth: OAuth sign-in
- Category: [AI & Machine Learning](https://mcp.tc/c/ai-ml)
- Vendor: GreatArrow.ai (Manito AI)
- Homepage:
## About
GreatArrow.ai is a persistent memory service that stores decisions, people and projects once and makes them available to every connected AI client, including Claude, ChatGPT, Cursor, Claude Code and Codex. Answers name the sources they read. The wider product adds a morning brief, tasks, goals, money and meetings.
The server runs as a hosted streamable HTTP endpoint at https://www.greatarrow.ai/api/mcp. Web clients sign in with OAuth 2.1 and dynamic client registration; file-based clients use a personal Bearer API token. It is a paid service with a 14-day free trial.
## What it can do
- Save notes and decisions to a memory shared across AI clients
- Recall saved context with named sources
- Organize memory in separate workspaces per client or project
- Reach tasks, goals and money data when those features are enabled
## Example prompts
- "Save to Great Arrow: we chose Postgres for the billing service."
- "What did we decide about the Acme project last week?"
- "Remind me what I saved about my client onboarding process."
- "Search my memory for notes on pricing decisions."
## Install
### Claude Code
1. Run this in a terminal, in your project folder:
```bash
claude mcp add --transport http greatarrow-ai https://www.greatarrow.ai/api/mcp
```
2. Start Claude Code, type `/mcp`, pick **greatarrow-ai** and choose **Authenticate**. A browser window opens for the GreatArrow.ai (Manito AI) sign-in.
Add `--scope user` to make it available in every project, not just this one.
### Claude Desktop
1. Open **Customize → Connectors**, click **+ Add**, then **Add custom connector**.
2. Name it **GreatArrow.ai** and paste this URL:
```url
https://www.greatarrow.ai/api/mcp
```
3. Click **Add**, then **Connect**, and sign in when GreatArrow.ai (Manito AI) asks.
Claude Desktop’s JSON config file only starts local servers. Remote servers go through Connectors, and connectors you add on claude.ai show up here too.
### claude.ai
1. Open the connector form on claude.ai. This button fills in the name and URL for you:
[Add to claude.ai]() (opens connector settings)
2. Check that the URL reads `https://www.greatarrow.ai/api/mcp` and click **Add**.
3. Click **Connect** and sign in when GreatArrow.ai (Manito AI) asks.
Free plans allow one custom connector. On Team and Enterprise plans an owner adds it under **Organization settings → Connectors**.
### ChatGPT
1. On chatgpt.com, open **Settings → Security and login** and turn on **Developer mode**.
2. Go to `chatgpt.com/plugins` and click **+** to create an app for a remote MCP server.
3. Paste `https://www.greatarrow.ai/api/mcp` as the server URL and choose **OAuth**. ChatGPT sends you to GreatArrow.ai (Manito AI) to sign in.
Developer mode is available on the web for Plus, Pro, Business, Enterprise and Education accounts.
### Cursor
[Add to Cursor]() (opens Cursor)
Or add it by hand to `~/.cursor/mcp.json` (all projects) or `.cursor/mcp.json` (this project):
`mcp.json`:
```json
{
"mcpServers": {
"greatarrow-ai": {
"url": "https://www.greatarrow.ai/api/mcp"
}
}
}
```
Cursor shows **Needs authentication** next to the server. Click the button beside it to sign in.
### VS Code
[Install in VS Code]() (opens VS Code)
Or from a terminal:
```bash
code --add-mcp '{"name":"greatarrow-ai","type":"http","url":"https://www.greatarrow.ai/api/mcp"}'
```
Or commit it to the repo in `.vscode/mcp.json`:
`.vscode/mcp.json`:
```json
{
"servers": {
"greatarrow-ai": {
"type": "http",
"url": "https://www.greatarrow.ai/api/mcp"
}
}
}
```
VS Code asks you to sign in the first time the server starts.
### Devin Desktop
1. Add it to `~/.config/devin/mcp_config.json` (macOS and Linux) or `%APPDATA%\devin\mcp_config.json` (Windows):
`mcp_config.json`:
```json
{
"mcpServers": {
"greatarrow-ai": {
"serverUrl": "https://www.greatarrow.ai/api/mcp"
}
}
}
```
2. Refresh the MCP server list in Cascade and sign in when asked.
Devin Desktop is the new name for Windsurf. It reads `serverUrl` (or `url`) for remote servers.
### Codex
```bash
codex mcp add greatarrow-ai --url https://www.greatarrow.ai/api/mcp
codex mcp login greatarrow-ai
```
Or edit `~/.codex/config.toml` directly:
`config.toml`:
```toml
[mcp_servers.greatarrow-ai]
url = "https://www.greatarrow.ai/api/mcp"
```
### Gemini CLI
```bash
gemini mcp add --transport http greatarrow-ai https://www.greatarrow.ai/api/mcp
```
Then, inside Gemini CLI, run `/mcp auth greatarrow-ai` to sign in.
This adds it to the current project. Add `-s user` to use it everywhere.
### Any client
Most clients accept this shape. Some name the URL field differently: `serverUrl` in Devin Desktop, `httpUrl` in Gemini CLI’s settings file.
```json
{
"mcpServers": {
"greatarrow-ai": {
"type": "http",
"url": "https://www.greatarrow.ai/api/mcp"
}
}
}
```
Zed puts servers under `context_servers` in its settings. Cline needs `"type": "streamableHttp"`, or it assumes SSE.
Client only starts local servers? Bridge it with `npx -y mcp-remote https://www.greatarrow.ai/api/mcp`.
## Details
- Last checked: 2026-10-24 (reachable, asks for credentials)
- Listed: 2026-10-15
- Updated: 2026-10-15
---
Source: https://mcp.tc/i/greatarrow-ai (mcp.tc is an independent directory, not affiliated with this server's publisher). Corrections: https://mcp.tc/report