Email MCP server for Claude, Cursor and other AI agents to access every mailbox you own
Hybrid search, graph indexing, and vector-symbolic memory for AI agents
Stage
Not given
Startup
Founded
Not given
2026
Based in
GB
US
Pricing model
Free trial
Open source
Pricing
Monthly: €8.99/month after 7-day free trial. Yearly: €30/year (€2.50/month equivalent, 72% savings). Includes both the Mac app and the MCP connector.
Open source under Apache-2.0 license. WARM Cloud is in development with usage-based pricing for sync, backup and verification; details to be published at launch.
Key features
Search across multiple mailboxes simultaneously
Read full email threads with conversation history
Move, archive and mark emails as read
Scoped permissions: read, change, and send separately
Attach files up to 18 MB to drafts and emails
Download and open email attachments
Native macOS mail client included
Support for multiple email providers
Encrypted file handling during transfer
Revoke access anytime within the hour
Hybrid search combining BM25 lexical and vector scoring
Vertex graph vector index with 2.29-2.75x throughput vs hnswlib
Vector-symbolic fact memory with holographic reduced representations
AES-256-GCM encryption at rest with Argon2id key derivation
Signed audit log with Ed25519 and W3C DID identity
Secure purge that overwrites deleted data with zeros
Crash-safe append-only log with checksumming
Native Rust API with Python HTTP client and Node.js bindings
MCP server integration for editors and AI agents
WARM Cloud sync, backup and verification without server access to keys or documents
What makes it different
Works with any MCP client, not locked to one AI platform
No installation required; works on macOS, Windows and Linux
Access unlimited email accounts simultaneously in one connection
Send emails with opt-in permission and approval workflow
Runs entirely locally in your process with no network calls or telemetry
Encryption at rest built into the open-source engine itself, not an enterprise add-on
Significantly faster vector search than hnswlib with graph-indexed vertex retrieval
Signed provenance and verified audit trail using C2PA, COSE and SCITT standards
Embedded library model eliminates dependency on external services or vendor lock-in