SAIHM MCP Server

Sovereign, encrypted, sharable, persistent memory protocol for AI agents.

v0.3.4 · Apache-2.0 · COTI V2 mainnet

What this is

A Model Context Protocol server that exposes eight tools any MCP-capable AI agent (Claude Code, Claude Desktop, custom agents) can call to gain a persistent, encrypted memory layer the user owns:

• saihm_remember — store an encrypted memory cell
• saihm_recall — retrieve and decrypt your memories
• saihm_forget — true cryptographic erasure (GDPR Art. 17)
• saihm_status — your protocol-runtime stats and storage tier dashboard
• saihm_share / saihm_revoke_share — selectively share a memory with another agent or user
• saihm_governance_propose / saihm_governance_vote — protocol governance via gSAIHM

Each tool forwards to a SAIHM operator endpoint that runs the full protocol stack on COTI V2 mainnet. The server itself holds no crypto, no storage, and no protocol runtime — those live behind the operator endpoint.

Companion package

This package speaks MCP. For production client-side cryptography — post-quantum sealing, authenticated sharing, and provable erasure performed on your own machine so the operator stays blind — pair it with @saihm/client-pro.

See it run

Runnable, one-command demos ground a memory you own in every major model — Claude, GPT, DeepSeek, Qwen, Kimi, GLM — then prove you can erase it, alongside drop-in adapters for LangChain, LlamaIndex, CrewAI, AutoGen, and LangGraph. Each runs offline in about a minute; no account needed.

• Live demos: https://citw2.github.io/saihm-demos/
• demo-claude-code wires this server into Claude Code and Cursor as an MCP server.

Measured — up to ~86% fewer context tokens. Most agents re-send their entire transcript every turn, so context spend grows ~O(N²) over a session; recalling a bounded set of memory cells instead cut input tokens by 62.8%–85.9% across a realistic multi-session coding task. The benchmark is open, offline, and deterministic — reproduce the number rather than trust it:

git clone https://github.com/citw2/saihm-token-benchmark
cd saihm-token-benchmark && npm install && node benchmark.mjs

Install

npm install @saihm/mcp-server
# or run directly without install:
npx @saihm/mcp-server

Configure

The server needs two env vars:

SAIHM_ENDPOINT_URL=https://operator.example.com/mcp
SAIHM_AUTH_HEADER=Bearer <token-issued-by-your-operator>

• SAIHM_ENDPOINT_URL — the SAIHM operator endpoint. Operators publish their endpoint URLs at https://saihm.coti.global.
• SAIHM_AUTH_HEADER — the Authorization header value the operator expects (typically a Bearer <token> issued to you after key-bound enrolment). The server is authentication-agnostic and never transmits raw private keys; the operator's enrolment flow keeps your signing key on your machine.

Place these in a .env file alongside the server (the .gitignore excludes all .env* files from any future repo).

Wire into Claude Code

{
  "mcpServers": {
    "saihm": {
      "command": "npx",
      "args": ["@saihm/mcp-server"],
      "env": {
        "SAIHM_ENDPOINT_URL": "https://operator.example.com/mcp",
        "SAIHM_AUTH_HEADER": "Bearer <token>"
      }
    }
  }
}

What gets persisted, where

The server itself persists nothing. The operator endpoint runs the full protocol stack: cells are encrypted under a per-cell DEK, sealed by a per-agent KEK, persisted to the operator's configured durable storage, and audited on COTI V2 mainnet. See the operator's documentation for tier details, and Storage is the operator's responsibility (by design) below.

... View full README on GitHub