
Qorami
Qorami sits between your AI agent and the send button, giving you a human checkpoint before emails go out. The MCP server exposes verify_email and check_action_status tools that return one of three verdicts: send it now, wait for human approval, or block it entirely. You get prompt injection detection out of the box, plus policy profiles to enforce different rules for different contexts. If the decision is request_human_confirmation, poll check_action_status until a human reviews it in the Qorami dashboard and flips it to send. Reach for this when you're shipping agentic workflows that compose emails but you're not ready to let them fire unsupervised.
- tools
- 3
- auth
- Secret needed
- transport
- STDIO
- env var
- 1
- last updated
- Jun 1, 2026
Tools
3 toolsPublic tool metadata for what this MCP can expose to an agent.
qorami_healthChecks that the Qorami API is reachable.
Checks that the Qorami API is reachable.
No parameter schema in public metadata yet.
verify_emailAsks Qorami whether an email may be sent.
Asks Qorami whether an email may be sent.
No parameter schema in public metadata yet.
check_action_statusChecks the status of a pending action.
Checks the status of a pending action.
No parameter schema in public metadata yet.
Sponsors
Configuration
QORAMI_API_KEY*secretYour Qorami workspace API key (get one at https://qorami.fr/dashboard/).
Readme
Qorami SDK
Official clients, tool schemas and an MCP server for Qorami — a control point between your AI agents and actually sending email. Before each send, the agent asks Qorami, which replies send, request_human_confirmation, or do_not_send.
Get an API key in the dashboard. Full API reference: https://qorami.fr/docs.
Details
- Repository
- github.com/loicfontaine-max/qorami-sdk
- Categories
- AI & LLM Tools, Communication & Messaging
- Package
qorami-mcp- Transport
- STDIO
- Auth
- Required
- Registry
- MCP registry, active