agentmods.dev

lema

lema is an MCP server for Claude Code, Codex, Cursor, Gemini CLI, OpenCode from lemahq/lema-mcp. Its token cost is not measured, scanned A, original, MIT.

A local MCP server that records and retrieves the reasoning behind technical decisions, including options that were ruled out. It includes decision records for React, Rust, and Kubernetes and can use a repository you provide.

In plain words
What is it for?
Use it to look up past technical decisions, capture new ones, and enforce decisions marked as not to be reconsidered in a repository.
Why use it?
It helps a coding agent remember why a choice was made so the same discussion does not need to be reopened later.

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 1repo 29d ago A scan tokens not measured original MIT

Good fit Use it to look up past technical decisions, capture new ones, and enforce decisions marked as not to be reconsidered in a repository.

Compare 6 mcp servers from other repositories ↓
Install with agentmods
npx agentmods add mcp/lemahq/lema-mcp/lema
View source ↗ lemahq/lema-mcp
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/lemahq/lema-mcp

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 lema

README.md
[![agentmods](https://agentmods.dev/badge/mcp/lemahq/lema-mcp/lema.svg)](https://agentmods.dev/mcp/lemahq/lema-mcp/lema)
Your own site
<a href="https://agentmods.dev/mcp/lemahq/lema-mcp/lema"><img src="https://agentmods.dev/badge/mcp/lemahq/lema-mcp/lema.svg" alt="Measured on agentmods" 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

lema 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 7d 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.

.mcp.json · 13 lines

What it actually says

{
  "lema": {
    "command": "npx",
    "args": [
      "-y",
      "lema-mcp@latest"
    ],
    "env": {
      "LEMA_MCP_MODE": "public",
      "LEMA_PUBLIC_REPO": "react-rfcs"
    }
  }
}
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. 7d ago First seen · 13 lines scan A 000504033699

Subscribe to this mod's changes

lema is an MCP server published in the GitHub repository lemahq/lema-mcp (1 stars, last pushed 29d ago), licensed MIT. 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 CodeMemory and contextadrai-agentscursordecisionsdocumentation
Related

Other mcp servers, from other repositories

chatcrystal

Local-first AI PKM memory for coding conversations. Runs locally from the chatcrystal npm package. Needs 2 environment variables to run.

ZengLiangYi/ChatCrystal · not measured

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

engram

Ranked local code-graph context for AI coding agents. Intercepts reads + greps. Apache-2.0. Runs locally from the engramx npm package. Needs 5 environment variables to run.

NickCirv/engram · not measured

toon-memory

Offline persistent memory for AI coding agents — 35 tools, 80% fewer calls, no LLM. Runs locally from the toon-memory npm package. Needs 6 environment variables to run.

LuiggiVal08/toon-memory · not measured

tages

MCP server for persistent AI agent memory. Runs locally from the @tages/server npm package.

ryantlee25-droid/tages · not measured

contextforge-mcp

Persistent memory MCP server for Claude Code, Cursor, and GitHub Copilot. Runs locally from the contextforge-mcp npm package. Needs 2 environment variables to run.

alfredoizdev/contextforge-mcp · not measured