Kijito speaks MCP, so it plugs into the client you already use. Where MCP does not reach, a REST API does. Both talk to the same account memory, so what one client remembers, another recalls. Setup differs by client - the table below says which paths are verified today.
Verified means a current end-to-end test of that client passes. Everything else is marked with how far we have tested it.
| Client | Status | Transport | Auth |
|---|---|---|---|
| Claude Code | Verified | MCP | Sign in with your Kijito account |
| REST API + scoped keys | Verified | REST | API key |
| Claude.ai web & desktop (MCP connector) | Verified | MCP | Sign in with your Kijito account |
| Generic MCP host | Not tested by us | MCP | Sign in with your Kijito account |
| Codex CLI | In testing | MCP | Sign in with your Kijito account |
| Local models via an MCP-capable host | Not tested by us | MCP | Runs on your machine |
| ChatGPT connector & OpenAI Apps | Planned | MCP | Sign in with your Kijito account |
Verified A current end-to-end test of that client passes. In testing Actively being validated; not yet a continuous green check. Not tested by us The protocol supports it, but Kijito does not continuously test this client. Planned Designed or on the roadmap; not available yet.
There is one hosted endpoint, and it is a Streamable HTTP MCP server:
https://api.kijito.ai/mcpUse exactly https://api.kijito.ai/mcp. Some clients require the sign-in to match the URL you entered character for character, so don't add or drop a trailing slash. There is no /sse endpoint: Kijito serves one modern MCP transport, Streamable HTTP.
MCP is an open standard, so Kijito is protocol-compatible with any MCP client. But the configuration - where the server is registered, how sign-in works, and how tools are discovered - is different in every client, so follow the specific steps below rather than assuming one recipe. Once you are signed in, the connect page has the exact files to copy.
One command adds Kijito for every project:
claude mcp add --transport http --scope user kijito https://api.kijito.ai/mcpThen sign in yourself: run claude mcp login kijito in your own terminal. A sign-in link opens in your browser or prints in your terminal; if it does not open by itself, Cmd-click or Ctrl-click it, or copy it into your browser. If your Claude Code says that command doesn't exist, restart Claude Code, run /mcp, choose kijito, and sign in with the link it shows.
For one project only, run the same command inside that project's folder without --scope user. Claude Code then adds Kijito for that project, and only for you:
claude mcp add --transport http kijito https://api.kijito.ai/mcpAdded for one project, the tools appear only there. Start Claude Code from that project's folder, or add Kijito again with --scope user to have it everywhere.
These speak MCP and can point at the same connector URL. Claude.ai web & desktop is verified, Codex is in testing, and the rest are not tested by us. If something does not work, the REST API below always does. The quickstart has the steps for each.
codex mcp add kijito --url https://api.kijito.ai/mcp, run in your own terminal; it opens the sign-in itself.~/.cursor/mcp.json (below), then sign in with cursor-agent mcp login kijito or from Cursor's MCP settings.context_servers).{
"mcpServers": {
"kijito": {
"url": "https://api.kijito.ai/mcp"
}
}
}Every route lives under https://api.kijito.ai/api, and every route is also served under a version prefix. Integrations should call the /api/v1 paths.
Sign in once to get an access token, then send it as a Bearer header on every call. The access token is a JWT valid for one hour. For anything long-lived, mint a scoped API key instead.
# Sign in and capture the access token from the response body.
TOKEN=$(curl -s https://api.kijito.ai/api/v1/auth/login \
-H "Content-Type: application/json" \
-d '{"email": "[email protected]", "password": "your-password"}' \
| jq -r .access_token)A kjt_-prefixed bearer token, scoped to a least-privilege subset of your own data and optionally set to expire. The scopes are memory.read, memory.write, memory.curate, and memory.dream. Keys are minted from a full login session; a scoped key cannot mint another.
# The secret is shown exactly once, at creation. Save it now.
curl https://api.kijito.ai/api/v1/auth/tokens \
-H "Authorization: Bearer $TOKEN" \
-H "Content-Type: application/json" \
-d '{"name": "ci-writer", "scopes": ["memory.read", "memory.write"], "expires_in_days": 90}'The full endpoint list, request shapes, and error codes are on the API reference.
Point every client at the same server URL and sign in with the same account. What one client remembers, another recalls. Through an MCP client, each REST endpoint is a kijito_* tool (for example /api/v1/recall is kijito_recall, and /api/v1/send is kijito_hive_send), dispatched over the same account memory with the same isolation.
A new account is capped at a lower limit until you verify your email, which is an anti-abuse gate rather than the tier. Verify to lift it to the full allowance - up to 10,000 memories during the beta. If you are seeing a 429 and your email is already verified, you may have reached your plan's memory cap or the per-minute write-rate limit; GET /api/v1/usage reports both.