agentmods.dev

core

core is an MCP server for Claude Code, Codex, Cursor, Gemini CLI, OpenCode from adshaa/mempalacejs. Its token cost is not measured, scanned A, original, ISC.

A locally running memory system and MCP server for AI agents, provided as an npm package. It uses LanceDB, a database designed for storing and searching data, and does not use a language model itself.

In plain words
What is it for?
Use it when configuring an agent to run the @mempalace/core package as a local MCP server. The available input does not describe the memory operations it provides.
Why use it?
It gives an agent a local memory service without requiring a separate hosted system or an extra language model in this component.

MCP server for Claude CodeCodexCursorGemini CLIOpenCode

Written for no agent in particular: it speaks MCP, so any client can run it.

not rated 6repo 6mo ago A scan tokens not measured original ISC

Good fit Use it when configuring an agent to run the @mempalace/core package as a local MCP server. The available input does not describe the memory operations it provides.

Compare 6 mcp servers from other repositories ↓
Install with agentmods
npx agentmods add mcp/adshaa/mempalacejs/core
View source ↗ adshaa/mempalacejs
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/adshaa/mempalacejs

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 core

README.md
[![agentmods](https://agentmods.dev/badge/mcp/adshaa/mempalacejs/core/github.svg)](https://agentmods.dev/mcp/adshaa/mempalacejs/core)
Your own site
<a href="https://agentmods.dev/mcp/adshaa/mempalacejs/core"><img src="https://agentmods.dev/badge/mcp/adshaa/mempalacejs/core/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 core

Your own site · 80×15
<a href="https://agentmods.dev/mcp/adshaa/mempalacejs/core"><img src="https://agentmods.dev/badge/mcp/adshaa/mempalacejs/core.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

core 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

  • mcp-hub — 86% identical, 4 lines differ
listed in the official MCP registry · 9 lines

What it actually says

{ "core": { "command": "npx", "args": [ "-y", "@mempalace/core" ] } }

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 · 9 lines scan A 51f9614a3086

Subscribe to this mod's changes

core is an MCP server published in the GitHub repository adshaa/mempalacejs (6 stars, last pushed 6mo ago), licensed ISC. 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.

Claude CodeDatabasesMemory and contextagentic-memoryclaudeknowledge-graphlancedbllm-memory
Related

Other mcp servers, from other repositories

waggle

MCP server "waggle" as configured in Abhigyan-Shekhar/Waggle-mcp. Runs ./plugins/waggle/bin/waggle-server-launcher.js with node. Needs 6 environment variables to run.

Abhigyan-Shekhar/Waggle-mcp · not measured

Waggle-mcp

MCP server that gives LLMs persistent graph-structured memory. Runs locally from the waggle-mcp Python package. Needs 5 environment variables to run.

Abhigyan-Shekhar/Waggle-mcp · not measured

mcp-memory-sqlite

SQLite-based persistent memory tool for MCP with text search. Runs locally from the mcp-memory-sqlite npm package.

spences10/mcp-memory-sqlite · not measured

myco-brain

Self-hosted, source-traceable memory layer and MCP server for AI agents, on your own Postgres. Runs locally from the @mycobrain/mcp-server npm package.

thegoodguysla/myco-brain · not measured

same

Persistent memory for AI coding agents. Local-first SQLite + vector search, 12 MCP tools. Runs locally from the @sgx-labs/same npm package. Needs 1 environment variable to run.

sgx-labs/statelessagent · not measured

knowledge-master

Local-first knowledge graph for developers. Your AI agent's permanent memory. Runs locally from the knowledge-master Python package.

subzone/knowledge-master · not measured