agentmods.dev

lians_memory

lians_memory is an MCP server for Claude Code, Codex, Cursor, Gemini CLI, OpenCode from Lians-ai/Lians. Its token cost is not measured, scanned A, original, Apache-2.0.

A memory connection for an AI assistant using the Model Context Protocol, a standard way for assistants to call external tools. It provides tools to save information and retrieve it later, and requires an API key to run.

In plain words
What is it for?
Use it when an assistant needs to remember facts with `remember` and retrieve them with `recall`. It is configured through the listed environment variables and API key.
Why use it?
It gives the assistant a separate place to store and recall information instead of relying only on the current conversation. The connection is optional and only exposes the listed memory actions.

MCP server for Claude CodeCodexCursorGemini CLIOpenCode

Written for no agent in particular: it speaks MCP, so any client can run it. Also seen: listed in a Claude config.

not rated 16repo 2d ago A scan tokens not measured original Apache-2.0

Good fit Use it when an assistant needs to remember facts with remember and retrieve them with recall. It is configured through the listed environment variables and API key.

Compare 6 mcp servers from other repositories ↓
Install with agentmods
npx agentmods add mcp/lians-ai/lians/lians-memory-lians_memory

Installing this writes the configuration, not the program: `lians-memory-mcp` has to be on your PATH already, or the server will not start.

View source ↗ Lians-ai/Lians lians.ai
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.

Clone the repo
git clone --depth 1 https://github.com/Lians-ai/Lians

Installing this writes the configuration, not the program: `lians-memory-mcp` has to be on your PATH already, or the server will not start.

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 lians_memory

README.md
[![agentmods](https://agentmods.dev/badge/mcp/lians-ai/lians/lians-memory-lians_memory/github.svg)](https://agentmods.dev/mcp/lians-ai/lians/lians-memory-lians_memory)
Your own site
<a href="https://agentmods.dev/mcp/lians-ai/lians/lians-memory-lians_memory"><img src="https://agentmods.dev/badge/mcp/lians-ai/lians/lians-memory-lians_memory/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for lians_memory

Your own site · 80×15
<a href="https://agentmods.dev/mcp/lians-ai/lians/lians-memory-lians_memory"><img src="https://agentmods.dev/badge/mcp/lians-ai/lians/lians-memory-lians_memory.svg" alt="Reviewed on agentmods" width="80" 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. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

lians_memory 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 1mo 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.

plugins/lians-memory/.mcp.json · 30 lines

What it actually says

{
  "lians_memory": {
    "command": "lians-memory-mcp",
    "startup_timeout_sec": 300,
    "tool_timeout_sec": 120,
    "required": false,
    "env_vars": [
      "LIANS_API_KEY"
    ],
    "enabled_tools": [
      "remember",
      "recall"
    ],
    "default_tools_approval_mode": "writes",
    "cwd": ".",
    "env": {
      "LIANS_MEMORY_HOME": "",
      "PYTHONPATH": "",
      "PYTHONHOME": "",
      "PYTHONNOUSERSITE": "1",
      "PYTHONSAFEPATH": "1",
      "LIANS_MCP_CODEX_DYNAMIC_SCOPE": "true",
      "LIANS_MCP_ENABLED_TOOLS": "remember,recall",
      "LIANS_MCP_SCHEMA_PROFILE": "compact",
      "LIANS_MCP_RECALL_K": "20",
      "LIANS_MCP_CONTEXT_MAX_TOKENS": "768",
      "LIANS_MCP_PREWARM": "off"
    }
  }
}
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. 1mo ago First seen · 30 lines scan A f6b311583f45

Subscribe to this mod's changes

lians_memory is an MCP server published in the GitHub repository Lians-ai/Lians (16 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.

Memory and contextPythonai-agentscodexcursorlocal-firstmcp
Related

Other mcp servers, from other repositories

local-memory-mcp

Persistent local AI memory. SQLite + FTS5 + vector search, knowledge graph. No cloud, no API keys. Runs locally from the @studiomeyer/local-memory-mcp npm package. Needs 4 environment variables to run.

studiomeyer-io/local-memory-mcp · not measured

turbo-quant-memory

Local-first MCP memory server for AI coding agents with compact retrieval and project/global scopes. Runs locally from the turbo-quant-memory Python package. Needs 4 environment variables to run.

Lexus2016/turbo_quant_memory · not measured

piia-engram

Local-first personal AI identity and memory for MCP-compatible coding tools — lessons, decisions, playbooks, and project context you can see, edit, and override. Runs locally from the piia-engram Python package. Needs 3 environment variables to run.

Patdolitse/piia-engram · not measured

sovseal-memory

Local-first, zero-knowledge AI memory across Claude, Cursor, and every MCP client. 0 RTT reads. Runs locally from the @sovseal/mcp-server npm package.

sovseal/core · not measured

agent-memory-control-plane

MCP server "agent-memory-control-plane" as configured in AlekseiUL/agent-memory-control-plane. Runs locally from the agent-memory-control-plane Python package.

AlekseiUL/agent-memory-control-plane · not measured

obsidian-bridge

MCP server "obsidian-bridge" as configured in dkdottk/obsidian-bridge. Runs locally from the obsidian-bridge npm package.

dkdottk/obsidian-bridge · not measured