Memori MCP server

Memori MCP

Persistent AI memory for any MCP-compatible agent — no SDK required.

memori-mcp is the official Memori MCP server. Connect it to your AI agent to give it long-term memory: recall relevant facts, retrieve broad state summaries, restore working state after context compaction, store durable preferences after responding, and maintain context across sessions.

Why Memori MCP?

Memori turns stateless agents into stateful systems by providing structured, persistent memory that works across sessions and workflows.

1. Persistent state beyond prompts — Most agents rely on prompt context and lose state between runs. Memori provides durable, structured memory so agents can retain facts, decisions, and outcomes over time.
2. Memory from execution (not just natural language) — Traditional systems extract memory from chat. Memori builds memory from agent execution itself — including tool calls, decisions, and results. This enables true agent-native memory, not just conversational recall.
3. Lower cost, higher accuracy — Instead of expanding prompt context, Memori retrieves only what matters.

• Significantly reduced token usage
• Faster responses
• Improved accuracy vs long-context approaches

1. Works with any MCP client and production-ready - No SDK, no code changes, just config

Memori is state infrastructure for production agents — enabling persistent memory, efficient retrieval, and structured context across both natural language and agent execution.

LoCoMo Benchmark

Memori was evaluated on the LoCoMo benchmark for long-conversation memory and achieved 81.95% overall accuracy while using an average of 1,294 tokens per query. That is just 4.97% of the full-context footprint, showing that structured memory can preserve reasoning quality without forcing large prompts into every request.

Compared with other retrieval-based memory systems, Memori outperformed Zep, LangMem, and Mem0 while reducing prompt size by roughly 67% vs. Zep and lowering context cost by more than 20x vs. full-context prompting.

Read the benchmark overview or download the paper.

How It Works

The server exposes seven tools:

Example Agent Flow

Given the user message: "I prefer Python and use uv for dependency management."

1. Agent calls memori_recall with the user message as query
2. Agent composes a response using any returned facts
3. Agent sends the response to the user
4. Agent calls memoriadvancedaugmentation with the usermessage and assistantresponse

On a later turn like "Write a hello world script", the agent recalls the Python + uv preference and personalizes its response.

Prerequisites

Shortened. The full README is on GitHub.