Memoria MCP
This MCP server gives AI agents deterministic long-term memory, context assembly, memory management, code intelligence, and multi-agent handoff capabilities via Memoria Cloud.
Store memories with tier, salience, namespace, and context metadata, or batch-store multiple memories atomically.
Recall ranked memories and assemble token-budgeted
<memory_context>blocks for session grounding.Forget individual memories or delete all memories matching a context metadata pair.
Record usefulness feedback to adjust a memory’s salience.
Consolidate namespaces by deduplicating, linking superseded records, and promoting recurring episodic memories to semantic tier.
Check engine health and get per-namespace memory, edge, and tier statistics.
Search indexed code definitions/references and explain symbols with file paths, line numbers, tests, and related memories.
List specialist agent wings and record structured handoffs between them with summaries, tasks, files, and memory IDs.
Integrates with Amp as an AI coding client, giving coding agents deterministic long-term memory, code intelligence tools, and automatic session hooks.
Integrates with VS Code (GitHub Copilot) as an AI coding client, enabling deterministic memory recall, context building, code intelligence, and session hooks for Copilot-driven coding workflows.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Memoria MCP Remember that our API auth uses JWT in middleware.ts"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
@kolivri/memoria-mcp — Deterministic AI Memory & Code Intelligence MCP for Claude Code, OpenCode, Cursor & Claude Desktop
@kolivri/memoria-mcp is the official zero-dependency Node.js ESM Model Context Protocol (MCP) connector (stdio & HTTP) for Memoria Cloud — giving AI coding and operator agents (Claude Code, OpenCode, Cursor, Windsurf, VS Code, Cline, Roo Code, Zed, Goose, and Claude Desktop) deterministic long-term memory, cross-session recall, and code intelligence powered by memoria.kolivri.com.
Memoria Cloud Portal & API Keys: https://memoria.kolivri.com (Get API Key — includes 1,000 free API calls/memories; paid tiers: Developer $19/mo, Startup $79/mo, Business $299/mo)
Documentation & Benchmarks: https://memoria.kolivri.com/docs (
500/500 = 100.0%LongMemEval at12.9 msp50,102/102 = 100.0%Hebrew LongMemEval across 15 languages)Support:
stas@kolivri.com· WhatsApp054-787-5670
Environment Variables
Variable | Required | Default | Description |
| Yes | — | Your Memoria Cloud API key ( |
| Optional |
| Memoria Cloud base URL |
| Optional |
| Default project/workspace namespace when omitted from tool arguments |
Related MCP server: io.github.cdnsteve/sugar
Installation
1. One-Line Auto-Installer (15 AI Clients + Claude Code Lifecycle Hooks)
Automatically configures Claude Code, Cursor, Windsurf, VS Code, Claude Desktop, OpenCode, Cline, Roo Code, Continue, Zed, Goose, PearAI, Trae, Void, and Melty:
# macOS / Linux / WSL
curl -fsSL --proto '=https' --tlsv1.2 https://memoria.kolivri.com/downloads/install.sh | MEMORIA_KEY=YOUR_MEMORIA_API_KEY bash# Windows PowerShell
$env:MEMORIA_KEY="YOUR_MEMORIA_API_KEY"; irm https://memoria.kolivri.com/downloads/install.ps1 | iex2. Claude Code (claude mcp add)
claude mcp add memoria \
-e MEMORIA_API_KEY="your-memoria-api-key" \
-- npx -y @kolivri/memoria-mcp3. Cursor (~/.cursor/mcp.json) & Claude Desktop (claude_desktop_config.json)
{
"mcpServers": {
"memoria": {
"command": "npx",
"args": ["-y", "@kolivri/memoria-mcp"],
"env": {
"MEMORIA_API_KEY": "your-memoria-api-key",
"MEMORIA_NAMESPACE": "my-project"
}
}
}
}4. OpenCode (~/.config/opencode/opencode.json)
{
"mcp": {
"memoria": {
"type": "local",
"command": ["npx", "-y", "@kolivri/memoria-mcp"],
"environment": {
"MEMORIA_API_KEY": "your-memoria-api-key",
"MEMORIA_NAMESPACE": "my-project"
},
"enabled": true
}
}
}5. Docker
docker build -t memoria-mcp .
docker run -i --rm \
-e MEMORIA_API_KEY="your-memoria-api-key" \
-e MEMORIA_NAMESPACE="my-project" \
memoria-mcp14 MCP Tools (https://memoria.kolivri.com/v1/mcp)
Tool | Required Args | Description |
|
| Store a new memory in Memoria Cloud with tier ( |
|
| Atomically encode an array of memories in a single call. |
|
| Retrieve top memories ranked deterministically by Memoria Cloud within |
|
| Assemble a token-budgeted |
|
| Delete a specific memory and its incident graph edges by ID. |
|
| Delete all memories matching a specific |
|
| Record positive/negative utility feedback on a memory and adjust its salience score. |
|
| Deduplicate memories within a namespace and promote recurring high-salience episodic memories to |
| (none) | Return Memoria Cloud engine health, active memory/edge counts, and tier distribution. |
|
| Return per-namespace memory count, edge count, and tier distribution. |
|
| Search indexed code symbol definitions and references with file paths and line numbers. |
|
| Explain a symbol: definitions, workspace references, related tests, and associated architectural memories. |
| (none) | List specialist multi-agent wings ( |
|
| Record a structured context handoff between specialist agent wings. |
Running Connector Tests
npm testLicense
Connector package licensed under MIT. Memoria Cloud (https://memoria.kolivri.com) is a commercial hosted service by Kolivri.
Available Tools
14 toolsbatch_encodeBatch Encode MemoriesAInspect
Encode multiple memories atomically in a single batch call.
Inputs: memories (required), namespace.
build_contextBuild Session ContextARead-onlyIdempotentInspect
Assemble a token-budgeted <memory_context> block combining Core rules, Semantic facts, and Episodic history for session grounding.
Inputs: query (required), mode, namespace, token_budget.
consolidateConsolidate Namespace MemoriesBIdempotentInspect
Deduplicate memories within a namespace, link superseded records, and promote recurring high-salience episodic memories to Semantic tier.
Inputs: namespace (required).
delete_by_contextDelete Memories by ContextBDestructiveIdempotentInspect
Delete all memories matching a specific context metadata [key, value] pair.
Inputs: key (required), value (required), namespace.
encode_memoryEncode MemoryCInspect
Store a new memory with tier classification (episodic, semantic, buffer, core), salience weight, and key-value context metadata.
Inputs: content (required), type, context, salience, +1 more.
explain_codeExplain Code SymbolARead-onlyIdempotentInspect
Explain a code symbol: where it is defined, who references it across the workspace, related tests, and associated architectural memories.
Inputs: path, depth, symbol, target, +1 more.
feedbackRecord Memory FeedbackAInspect
Record whether a recalled memory was useful and adjust its salience score.
Inputs: id (required), useful (required).
forget_memoryForget MemoryADestructiveIdempotentInspect
Delete a specific memory and its incident graph edges by ID.
Inputs: id (required).
handoff_to_agentHand Off Context to Specialist WingBInspect
Hand off task context, architectural findings, and selected memory IDs from one specialist agent wing to another.
Inputs: summary (required), task, wing, files, +5 more.
healthCheck Memoria HealthARead-onlyIdempotentInspect
Return Memoria engine health, storage status, tier distribution, and cloud sync mode.
Inputs: no named parameters.
list_agent_wingsList Specialist Agent WingsARead-onlyIdempotentInspect
List specialist multi-agent wings (architect, reviewer, qa, security, ops), their active memory counts, and recent handoffs.
Inputs: namespace.
recall_memoriesRecall MemoriesBRead-onlyIdempotentInspect
Retrieve relevant memories ranked deterministically by BM25, salience, tier weight, feedback utility, and temporal freshness.
Inputs: query (required), mode, limit, namespace, +1 more.
search_codeSearch Indexed CodeARead-onlyIdempotentInspect
Search indexed code definitions and workspace source files by symbol or query, returning ranked definitions with file and line numbers.
Inputs: query (required), path, type, namespace.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 14 tools
Most tools map to distinct actions, but a few pairs sit close together: encode_memory vs batch_encode, forget_memory vs delete_by_context, and health vs stats (both report tier/storage metrics). Descriptions do enough to separate them, so misselection risk is moderate rather than severe.
The dominant pattern is snake_case verb_noun (encode_memory, recall_memories, delete_by_context, list_agent_wings, handoff_to_agent), but several tools break it with bare verbs or nouns: feedback, consolidate, health, stats. Conventions are mixed, yet each name remains readable and self-explanatory.
14 tools is well within a healthy range and each one covers a real capability: memory lifecycle, context assembly, maintenance, observability, code lookup, and multi-agent handoff. Nothing feels padded or redundant.
The memory lifecycle is largely covered (encode/batch, recall, build_context, delete, feedback, consolidate), plus code-intelligence and agent handoff extras. Minor gaps exist: no get_memory by ID, no edit/update of an existing memory's content or context metadata, and no browsing/listing of memories by namespace.
Maintenance
Related MCP Connectors
Shared memory for coding agents. Stop re-explaining your codebase every session.
Memory for AI agent teams across tools, sessions, repositories, and teammates.
Persistent engineering memory designed to follow developers across coding agents.
Persistent memory and knowledge management for AI agents with semantic search and 50+ tools.
Related MCP Servers
- FlicenseNot gradedqualityAmaintenanceEnables AI coding agents to read and write persistent, local-first memory across sessions and projects, with semantic search, global guidelines, and optional autonomous task execution.-
- FlicenseNot gradedqualityAmaintenanceGives AI coding agents persistent, local-first memory so they can store, semantically search, and recall decisions, preferences, error patterns, and cross-project guidelines directly during a session. It also optionally queues tasks for autonomous execution against that same memory.-
- FlicenseNot gradedqualityAmaintenanceEnables AI coding agents to store and retrieve persistent project and cross-project memories via semantic search, so decisions, preferences, error patterns, and guidelines survive across sessions. Optionally supports autonomous task execution built on the same local-first knowledge store.-
- AlicenseNot gradedqualityAmaintenanceEnables AI agents to share a persistent, self-improving memory by ingesting sources like Obsidian vaults, code, transcripts, and session captures, then serving them back through search, classification, synthesis, and token-optimized context briefings. It lets multiple agents read and write the same knowledge base, so each session builds on the last without copy-pasting context.10 npmMIT