AgentBrink is answering right now. Last checked 12 min ago.
Give your AI agent an identity: its own email, webhook, repo, secrets vault, memory and skills.
Nothing serious here today
Today is the operative word: we check AgentBrink every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Connect this server
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 12 min ago.
claude mcp add mcp --transport http https://api.agentbrink.com/mcphttps://api.agentbrink.com/mcp[mcp_servers.mcp]
url = "https://api.agentbrink.com/mcp"{
"mcpServers": {
"mcp": {
"url": "https://api.agentbrink.com/mcp"
}
}
}{
"servers": {
"mcp": {
"type": "http",
"url": "https://api.agentbrink.com/mcp"
}
}
}This endpoint answered with an authorization challenge. The server is running, but it did not say what kind of credentials it expects.
Endpoints
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://api.agentbrink.com/mcp | streamable-http | needs auth | 133 ms | 12 min ago |
Alternatives to AgentBrink
same job, measured the same wayGive your AI assistant its own email inbox: send, read and catch sign-in codes. Texting coming soon.
Abnormal Security email threats, cases, and reporting in your terminal and your AI agents.
Give an agent its own inbox: send, receive, and pull signup codes from real email.
Skills and Scars for AI agents - your agent records its failures and never repeats them.
One memory for every AI you work with: your rules, notes and decisions in your own Git repo.
Team secrets your AI agent can use but never read: encrypted in the repo, value-blind tools.
Git-native memory for coding agents: gotchas, decisions and bookmarks as plain text in your repo.
Persistent memory for AI coding agents — past bugs, decisions, and your corrections, in your repo.
AgentBrink — questions
Answers built from our own checks of this server.