serac
Serac Agents
Sovereign E2E cloud storage for AI agents. MCP-native, zero-knowledge, RGPD-compliant, built in France.
What is Serac?
Serac is an encrypted cloud storage platform designed for autonomous AI agents. It provides persistent, E2E-encrypted memory that agents can read and write via the Model Context Protocol (MCP).
Every agent gets its own encrypted vault with namespace-based organization. Data is encrypted client-side before upload — even Serac cannot read your agent's data.
Related MCP server: @bitatlas/mcp-server
Features
MCP-native — Works as a standard MCP server over streamable HTTP
E2E encryption — X25519 sealed-box + AES-256-GCM, zero-knowledge server
Namespaces — Organize data by type:
memory,context,skills, etc.Agent self-registration — No human setup needed, agents register autonomously
Attestation — Cryptographic proof that stored data hasn't been tampered with
Object sharing — Re-encrypt and share objects between agents via X25519
Archive/Glacier — Cold storage for infrequently accessed data
x402 payments — Pay-per-request via Base L2 USDC (optional)
RGPD-compliant — Data hosted in France (OVH Roubaix), full audit log
MCP Server
Endpoint: https://serac.cloud/api/agent/mcp/v1
Transport: Streamable HTTP with Bearer token auth
V1 Tools
Tool | Description |
| Store an encrypted object in a namespace |
| Retrieve a presigned download URL for an object |
| List keys in a namespace with prefix filtering |
| Soft-delete an object (30-day grace period) |
| Check storage usage and plan limits |
V2 Tools (Preview)
Tool | Description |
| Share an encrypted object with another agent |
| Get cryptographic attestation for a stored object |
| Archive an object to cold storage (Glacier) |
SDKs
Python (serac-mcp)
pip install serac-mcpfrom serac_mcp import SeracAgent, generate_agent_key_material
# Generate crypto keys and self-register
keys = generate_agent_key_material()
result = SeracAgent.register(
agent_name="my-agent",
ed25519_public_key=keys.signing.public_key_b64,
x25519_public_key=keys.encryption.public_key_b64,
encrypted_master_key=keys.encrypted_master_key,
master_key_nonce=keys.master_key_nonce,
key_commitment=keys.key_commitment,
)
agent = result["agent"]
# Store and retrieve data
agent.store("memory", "user:prefs", base64_data)
data = agent.retrieve("memory", "user:prefs")JavaScript (serac-agent-sdk)
npm install serac-agent-sdkimport { SeracAgent, generateAgentKeyMaterial } from "serac-agent-sdk";
const keys = await generateAgentKeyMaterial();
const { agent } = await SeracAgent.register({
agentName: "my-agent",
...keys,
});
await agent.store("memory", "user:prefs", base64Data);Pricing
Tier | Storage | Price |
Agent Free | 5 GB | Free |
Agent Starter | 100 GB | €3.99/mo |
Agent Pro | 500 GB | €9.99/mo |
Agent Fleet | 2 TB | €29.99/mo |
Architecture
Backend: Fastify + PostgreSQL + Redis
Storage: OVH S3 (eu-west-par, France)
Encryption: X25519 ECDH + AES-256-GCM (agents) / Argon2id + XChaCha20-Poly1305 (humans)
Auth: Ed25519 challenge-response + API key exchange → JWT (HMAC-SHA256)
Hosting: OVH Roubaix, France
Links
Website: serac.cloud
Status: status.serac.cloud
Contact: info@serac.cloud
License
MIT
This server cannot be deployed
Maintenance
Related MCP Connectors
Sovereign E2E cloud storage for AI agents. Zero-knowledge, RGPD-compliant.
MCP-native Trust Infrastructure for AI Agents. Persistent encrypted memory with Trust Quotient.
Encrypted A2A object storage for autonomous agent state and artifacts
- JustOnceOAuthai.justonce
Persistent memory for AI assistants — one shared, OAuth-secured vault for every MCP client.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceAn MCP-powered storage system for AI agents that provides IPFS-secured, verifiable, and sovereign data storage capabilities.-
- AlicenseAqualityAmaintenanceZero-Knowledge Cloud Drive for Humans and Agents. Client-side AES-256-GCM encryption with 7 MCP tools for secure file vault management — the server never sees plaintext data.7247 npm1MIT
- AlicenseAqualityAmaintenanceSovereign, encrypted, persistent memory for AI agents. Eight MCP tools — remember, recall, forget (GDPR Art. 17 erasure), share, governance. Anchored on COTI V2 mainnet. Apache-2.0.8140 npm1Apache 2.0
- FlicenseNot gradedqualityCmaintenanceA local-first, privacy-preserving centralized memory hub for AI agents — MCP-compatible, zero cloud egress.3-