saihm

saihm is an MCP server for Claude Code, Codex, Cursor, Gemini CLI, OpenCode from SAIHM-Admin/saihm-mcp. Its token cost is not measured, scanned A, original, Apache-2.0.

A local MCP server that provides encrypted memory for AI agents. The memory can be shared and permanently erased, and the server connects to an operator using an address and authentication token.

In plain words
What is it for?
Use it when agents need shared long-term memory or controlled deletion of stored information. Configure the operator address and authentication header to connect it.
Why use it?
It gives agents a place to keep information between interactions without putting memory handling in every agent separately. Encryption, sharing, and provable erasure address common concerns about stored agent data.

MCP server for Claude CodeCodexCursorGemini CLIOpenCode

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add mcp/saihm-admin/saihm-mcp/saihm
Clone the repo
git clone --depth 1 https://github.com/SAIHM-Admin/saihm-mcp

Made for: Claude Code, Codex, Cursor, Gemini CLI, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for saihm

README.md
[![agentmods](https://agentmods.dev/badge/mcp/saihm-admin/saihm-mcp/saihm.svg)](https://agentmods.dev/mcp/saihm-admin/saihm-mcp/saihm)
Your own site
<a href="https://agentmods.dev/mcp/saihm-admin/saihm-mcp/saihm"><img src="https://agentmods.dev/badge/mcp/saihm-admin/saihm-mcp/saihm.svg" alt="Measured on agentmods" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

saihm scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.mcp.json · 13 lines

What it actually says

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

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago First seen · 13 lines scan A 4bdd5768bd67

Subscribe to this mod's changes

saihm is an MCP server published in the GitHub repository SAIHM-Admin/saihm-mcp (1 stars, last pushed 2d ago), licensed Apache-2.0. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other mcp servers, from other repositories

prism-coder

Session memory for coding agents: local-first recall, drift detection, on-device inference. Runs locally from the prism-mcp-server npm package. Needs 8 environment variables to run.

dcostenco/prism-coder · not measured

prism-mcp

Persistent session memory for AI coding agents that never leaves your machine — including the on-device model that reasons over it. Restores your prior decisions, open TODOs, and changed files across sessions; adds associative recall of related past work. Runs locally from the prism-mcp-server npm package. Needs 1…

dcostenco/prism-coder · not measured

inspeximus

MCP server "inspeximus" as configured in DanceNitra/inspeximus. Runs locally from the inspeximus[mcp] Python package. Needs 1 environment variable to run.

DanceNitra/inspeximus · not measured

engrava

Model Context Protocol server for Engrava — expose an agent memory database to any MCP client over stdio. Runs locally from the engrava-mcp Python package.

sovantica/engrava-mcp · not measured

inkwell-memory

MCP server "inkwell-memory" as configured in veronchenko/inkwell-memory. Runs in Docker (docker.io/foreigndmitryi/inkwell-memory:0.14.0). Needs 2 environment variables to run.

veronchenko/inkwell-memory · not measured

context-keeper

MCP server that maintains project context (decisions, pipelines, constraints) across Claude conversations. Runs locally from the context-keeper-mcp Python package. Needs 1 environment variable to run.

jarmstrong158/context-keeper · not measured