MCP Hub
Back to servers

memoryoracle

MemoryOracle - 10 agent memory tools: vector store, recall, summarization, redaction.

Registry
Updated
Apr 5, 2026

MemoryOracle

Persistent long-term memory for AI agents. Agents never forget.

10 tools. SQLite FTS5 full-text search. Per-namespace isolation. GDPR-compliant forget. Cross-references with FeedOracle Trust Layer.

npx -y mcp-remote https://mcp.feedoracle.io/memory/mcp/

The problem

Every MCP tool call is stateless. When Claude Desktop restarts, when Cursor closes, when the session ends — the agent forgets everything. No user preferences, no project history, no learned rules, no portfolio tracking.

MemoryOracle gives agents a persistent, searchable memory that survives restarts, works across clients, and gets more valuable over time.

Tools

ToolWhat it does
store_memoryStore a fact, preference, decision, or rule. Deduplicates automatically.
query_memoryFull-text search with BM25 ranking and recency boost
update_factUpdate a memory with new info. Preserves version history (last 10 changes)
forgetPermanently delete by ID, category, age, or everything. GDPR Art. 17
summarize_sessionEnd-of-session capture: summary + extracted facts, decisions, action items
list_memoriesBrowse with filters: category, importance, recency, access frequency
cross_referenceVerify a memory against FeedOracle Trust Layer evidence
memory_statsDashboard: count, storage, categories, most accessed, recent
export_memoriesExport all as JSON. GDPR Art. 20 data portability
health_checkService status

Memory categories

CategoryWhen to use
factVerified information: "USDC is MiCA authorized"
preferenceUser/agent preferences: "Conservative allocation, no USDT"
decisionDecisions made: "Blocked USDT for EU clients"
observationPatterns noticed: "RLUSD peg stable for 30 days"
ruleBusiness rules: "Never recommend assets with peg deviation > 2%"
sessionSession summaries with linked facts
portfolioPortfolio positions and allocations
action_itemOpen tasks: "Check RLUSD status in April"

Example: Compliance agent workflow

Session 1 — Agent does MiCA compliance checks:

{"name": "store_memory", "arguments": {
  "content": "USDT blocked for EU — MiCA NOT AUTHORIZED. Preflight: STOP.",
  "category": "decision", "importance": 10,
  "tags": ["usdt", "mica", "blocked"],
  "namespace": "compliance-bot"
}}

Session 2 — Next day, agent remembers:

{"name": "query_memory", "arguments": {
  "query": "USDT EU compliance status",
  "namespace": "compliance-bot"
}}

→ Instantly recalls the decision from yesterday. No re-checking needed.

End of session — Auto-capture:

{"name": "summarize_session", "arguments": {
  "summary": "Reviewed stablecoin portfolio. USDT blocked. RLUSD pending.",
  "key_facts": ["USDC authorized", "EURC authorized", "USDT blocked"],
  "decisions": ["Block USDT for EU"],
  "action_items": ["Check RLUSD in April 2026"],
  "namespace": "compliance-bot"
}}

Why this is different

FeatureMemoryOracleOthers
SearchFTS5 BM25 ranking + recency boostBasic keyword
Categories8 structured typesFlat key-value
Session captureAuto-extracts facts, decisions, actionsManual only
Trust LayerCross-reference with signed evidenceNone
GDPRArt. 17 forget + Art. 20 exportUsually missing
NamespacesPer-agent isolationShared global
HistoryVersion tracking (last 10 changes)Overwrite
TTLAuto-expiry with configurable hoursNone

x402 Pay-per-call

POST https://tooloracle.io/x402/memory/mcp/
ToolUnitsPrice
store_memory2$0.02
query_memory5$0.05
summarize_session8$0.08
cross_reference5$0.05
list_memories3$0.03
update_fact2$0.02
forget1$0.01

Connect

{
  "mcpServers": {
    "memory": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://mcp.feedoracle.io/memory/mcp/"]
    }
  }
}

Part of ToolOracle

MemoryOracle is part of ToolOracle — 50+ MCP servers, 530+ tools. Powered by FeedOracle compliance infrastructure.

The memory layer that makes Decision Preflight, Trust Layer, ISO 20022, and every other tool exponentially more valuable.

Read More

📝 We Built an AI Agent That Runs 24/7, Never Forgets, and Checks Its Own Work — How Memory + Scheduler + Decision Preflight work together as one integrated autonomous agent stack. Real tool outputs, no theory.

License

MIT

Reviews

No reviews yet

Sign in to write a review