Claude Code
Codex
Cursor
Sourcery MCP
Let your coding agent request Sourcery reviews and fix the comments and security findings itself
Postfleet
Email for AI agents, screened for prompt injection
About
An inbox that treats incoming mail as untrusted input
Postfleet is email infrastructure for agents that puts a trust boundary between the wire and the model. Every inbound message is verified, cleaned, stripped of hidden text, zero-width characters and homoglyphs, spam and virus gated, and scanned for prompt injection before it is extracted to your JSON Schema with a confidence score. Risky mail never reaches extraction. Agents connect over a hosted MCP server or the open-source `@postfleet/mcp` package (16 tools, including `wait_for_email` and a draft approval flow where a human signs off before a send).
Features
- Agent-provisioned mailboxes over REST or MCP
- Prompt injection scan and sanitization report
- Schema extraction to typed JSON
- Draft approval gate and wait_for_email
Install
- Claude Code
- Codex
- Cursor
- Grok Bot
Related skills
All skillsRelated articles
All articlesHow to Give Your AI Agent Email, Memory and a Sandbox
Six building blocks that turn a chat model into an agent that can work on its own: an inbox, memory, a safe place to run code, app access, background jobs and tracing.
7 Best MCP Servers for Solo Founders (2026)
Official MCP servers that let your agent read your bank, CRM, database, deployments and designs, so you can run the business by asking.
Grok Bot vs Claude Code and Codex: What Each One Is For
How Grok Bot, a persistent personal agent, differs from coding agents like Claude Code and Codex, and when it makes sense to use each one or both together.
