serac
Sovereign E2E cloud storage for AI agents. MCP-native, zero-knowledge, RGPD-compliant, built in France.
README
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.
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 |
|---|---|
serac_store |
Store an encrypted object in a namespace |
serac_retrieve |
Retrieve a presigned download URL for an object |
serac_list |
List keys in a namespace with prefix filtering |
serac_delete |
Soft-delete an object (30-day grace period) |
serac_quota |
Check storage usage and plan limits |
V2 Tools (Preview)
| Tool | Description |
|---|---|
serac_share |
Share an encrypted object with another agent |
serac_attest |
Get cryptographic attestation for a stored object |
serac_archive |
Archive an object to cold storage (Glacier) |
SDKs
Python (serac-mcp)
pip install serac-mcp
from 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-sdk
import { 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
- PyPI: pypi.org/project/serac-mcp
- npm: npmjs.com/package/serac-agent-sdk
- Contact: info@serac.cloud
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.