Sgraal Memory Governance MCP Server

@sgraal-ai

リポジトリ

基本情報

カテゴリ

メモリとナレッジ

トランスポート

stdio

作者

sgraal-ai

投稿者

peterzsob

Sgraal Memory Governance MCP Server について

Deterministic pre-action verdict gate for agent memory — USE/WARN/ASK/BLOCK before an agent acts on a stored memory. Governs your existing store, doesn't replace it.

#memory #governance #ai-agents #security #preflight #agent-memory #llm-security

Sgraal Memory Governance MCP Server の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "sgraal": {
      "command": "npx",
      "args": [
        "@sgraal/mcp"
      ],
      "env": {
        "SGRAAL_API_KEY": "sg_demo_playground"
      }
    }
  }
}

Sgraal Memory Governance MCP Server のツール

Check if AI agent memory is reliable enough to act on. Call this BEFORE making any decision based on stored memory. Returns USE_MEMORY (safe), WARN (proceed with caution), or BLOCK (do not proceed).

概要

What is Sgraal Memory Governance?

Sgraal Memory Governance is a deterministic preflight gate for AI-agent memory. Before an agent acts on a stored memory, it returns a USE / WARN / ASK / BLOCK verdict, catching poisoned or stale memory at the read boundary. It is non-LLM and deterministic: identical input yields identical verdict. It governs whatever memory store you already use, not another store.

How to use Sgraal Memory Governance?

A demo key is provided: sg_demo_playground — no signup needed. The README does not specify further install, configure, or invoke steps.

Key features of Sgraal Memory Governance

Pre-action verdict on every memory read: USE / WARN / ASK / BLOCK
Blocks unsafe memory before an agent acts on it
Four deterministic detection layers: timestamp, identity, consensus, provenance
Multi‑tenant containment limits poisoned memory propagation
Tested against an internal adversarial corpus of 1,190+ cases

Use cases of Sgraal Memory Governance

Preventing an agent from acting on poisoned or stale memories
Adding a deterministic safety gate to any existing memory store
Containing the spread of compromised memories across tenants
Enforcing memory provenance and identity checks in multi‑agent systems

よくある質問

What verdicts does Sgraal Memory Governance return?

It returns one of four deterministic verdicts: USE, WARN, ASK, or BLOCK.

Does it replace my existing memory store?

No. It governs whatever memory store you already use; it is not another store.

Is Sgraal Memory Governance LLM‑based?

No, it is deterministic and non‑LLM; identical input yields identical verdict.

How was it tested?

Tested against an internal adversarial corpus of over 1,190 cases; independent third‑party evaluation is in progress.

How can I try it?

Use the demo key `sg_demo_playground` — no signup required.

「メモリとナレッジ」の他のコンテンツ

OpenLore

aakarim

Serve your docs to AI agents over SSH and MCP. Agents use ls, cat, grep, find, and pipes against a virtual filesystem backed by your documentation. Identity-scoped access, governed writing with human approval, and portab

UmmahAPI

Yousuf Kazmi

Islamic source data for assistants: Quran, hadith, tafsir, duas, prayer times and qibla. Answers come from real sources with citations instead of recalled text, so verses and hadith are not hallucinated. 36,000+ hadiths

M1K3

Round-Tower

Local AI agent for your Mac with a built-in MCP server: 18 tools for your notes and PDFs, a temporal memory graph, an on-device LLM and a neural voice. No account, no telemetry. No data centers required.

Agimem

Persistent memory for AI agents. Hosted MCP server with capsule-scoped key/value storage, tags, TTL expiration, bulk ops, and RBAC.

Code Graph Rag

vitali87

The ultimate RAG for your monorepo. Query, understand, and edit multi-language codebases with the power of AI and knowledge graphs

5.3K