Agentaddress
Remote MCP server giving short-lived agents a callback URL, email address and event queue
- Pricing
- Free
- Platforms
- API, CLI, Web
- Runs
- Remotely
- Version
- 0.2.0
- Listing updated
- 1 day ago
About Agentaddress
Agentaddress is a free MCP server for developer tools. It runs as a hosted remote server, so there is nothing to install locally.
An AgentAddress is a task-scoped resource that outlives the agent run that made it. It bundles a write-only HTTPS inbox for webhooks, an inbound email address, a private ordered queue of everything received, and a read token a later run uses to fetch and acknowledge events. No account or API key is needed to create one.
A typical flow saves the token and events URL, hands the callback URL or email to the responder, exits, and polls the queue later with a long-poll wait. Small JSON values can also be saved behind the same token so context carries between runs. The README labels every returned email and webhook body as untrusted data.
Free limits are 1,000 retained events per address kept for 30 days, 32 JSON keys of 64 KB total, and up to 20 outbound emails a day. A $17 monthly tier is planned but not available.
Install
Run in a terminal
claude mcp add --transport http agentaddress https://agentaddress.dev/api/mcpAdd to Settings → Connectors → Add custom connector
https://agentaddress.dev/api/mcpAdd to ~/.cursor/mcp.json
{
"mcpServers": {
"agentaddress": {
"url": "https://agentaddress.dev/api/mcp"
}
}
}Add to .vscode/mcp.json
{
"servers": {
"agentaddress": {
"type": "http",
"url": "https://agentaddress.dev/api/mcp"
}
}
}Add to ~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"agentaddress": {
"serverUrl": "https://agentaddress.dev/api/mcp"
}
}
}Add to your client's MCP settings (most use this shape)
{
"mcpServers": {
"agentaddress": {
"type": "http",
"url": "https://agentaddress.dev/api/mcp"
}
}
}What it does
- Callback URL
- A public write-only HTTPS inbox that receives webhooks without your own server.
- Inbound email
- An address where people or services can reply after the run ends.
- Ordered event queue
- HTTP and email events share one private, sequenced feed with acknowledgements.
- Task context storage
- Stores small JSON values behind the same read token.
- Skill and CLI helper
- Installable helper keeps the read token in owner-only storage outside model context.
- Human inbox viewer
- A person with the token can inspect the same events.
Good for
- Give an API a webhook URL when you have no public server
- Wait for a human email reply after an agent run exits
- Collect a deployment or code review webhook for a later run
- Handle browser verification or approval emails
Pricing
Free
Free today; paid tier planned at $17/month, not yet available
Prices change. Check agentaddress.dev before you buy.
Agentaddress FAQ
Does it need an account?
No account or API key is required for provisioning.
How long are events kept?
Up to 1,000 per address for 30 days.
Is delivery exactly once?
No. The README says delivery is at least once and acknowledgement records handling.
What will it cost?
It is free today; a $17 per month tier is planned with allowances still being finalized.
Is Agentaddress free?
Yes. Agentaddress is free to use.
How do I add Agentaddress to Claude Code?
Run this command in your terminal: claude mcp add --transport http agentaddress https://agentaddress.dev/api/mcp
What are the best alternatives to Agentaddress?
The closest alternatives to Agentaddress are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.
Alternatives to Agentaddress

REA
MCP serverCLI and MCP server that lets coding agents reverse engineer apps and binaries
Runs locally- Open source
- 464K GitHub stars
- Developer tools

Codebase Memory
MCP serverLocal MCP server that builds a code knowledge graph for AI coding agents
Runs locally- Open source
- 48.7K GitHub stars
- Knowledge and memory

GitHub
MCP serverOfficial MCP server connecting AI assistants to GitHub repos, issues and workflows
Not checked yet- Remote
- Open source
- 34.5K GitHub stars
- Developer tools

Serena MCP: the IDE for your agent
MCP serverMCP toolkit giving coding agents symbol-level code retrieval and editing
Runs locally- Open source
- 31.5K GitHub stars
- Developer tools

XERJ
MCP serverLocal search engine for AI agents with cited answers over your code and docs
Runs locally- Open source
- 19.2K GitHub stars
- Knowledge and memory

Ouroboros
MCP serverSpec-first layer that pins requirements and verifies results of AI coding agent work
Runs locally- Open source
- 6.4K GitHub stars
- Developer tools