agentmods.dev

lethe

lethe is an MCP server for Claude Code, Codex, Cursor, Gemini CLI, OpenCode from JesusGarcia9009/lethe-engineering. Its token cost is not measured, scanned A, original, Unlicense.

A local tool for storing away older conversation context and bringing it back when needed. It connects to Claude Code and Codex through MCP, a standard way for tools to communicate with AI agents.

In plain words
What is it for?
Use it to offload and recall context during extended Claude Code or Codex sessions. It runs locally through a Python package and uses the LETHE_DB environment variable for its database.
Why use it?
Long-running agents can fill their usable context with old information and spend tokens carrying it forward. This tool helps keep that context smaller while retaining access to stored material.

MCP server for Claude CodeCodexCursorGemini CLIOpenCode

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

not rated 0repo 2mo ago A scan tokens not measured original Unlicense

Good fit Use it to offload and recall context during extended Claude Code or Codex sessions. It runs locally through a Python package and uses the LETHE_DB environment variable for its database.

Compare 6 mcp servers from other repositories ↓
Install with agentmods
npx agentmods add mcp/jesusgarcia9009/lethe-engineering/lethe
View source ↗ JesusGarcia9009/lethe-engineering pypi.org
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/JesusGarcia9009/lethe-engineering

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 lethe

README.md
[![agentmods](https://agentmods.dev/badge/mcp/jesusgarcia9009/lethe-engineering/lethe/github.svg)](https://agentmods.dev/mcp/jesusgarcia9009/lethe-engineering/lethe)
Your own site
<a href="https://agentmods.dev/mcp/jesusgarcia9009/lethe-engineering/lethe"><img src="https://agentmods.dev/badge/mcp/jesusgarcia9009/lethe-engineering/lethe/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 lethe

Your own site · 80×15
<a href="https://agentmods.dev/mcp/jesusgarcia9009/lethe-engineering/lethe"><img src="https://agentmods.dev/badge/mcp/jesusgarcia9009/lethe-engineering/lethe.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

lethe 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 9d 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.

server.json · 11 lines

What it actually says

{
  "lethe": {
    "command": "uvx",
    "args": [
      "lethe-llm-context"
    ],
    "env": {
      "LETHE_DB": ""
    }
  }
}
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. 9d ago First seen · 11 lines scan A 33eedb02ae45

Subscribe to this mod's changes

lethe is an MCP server published in the GitHub repository JesusGarcia9009/lethe-engineering (0 stars, last pushed 2mo ago), licensed Unlicense. 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 contextai-agentsanthropiccodexcontext-managementcontext-window
Related

Other mcp servers, from other repositories

ccrecall

AI memory service for Claude Code — on-demand context injection with metacognition. Runs locally from the @tznthou/ccrecall npm package.

tznthou/ccRecall · not measured

agentfit

Token-aware message truncation: fit a chat history into your model's context budget. Runs locally from the @mukundakatta/agentfit-mcp npm package.

MukundaKatta/agentfit-mcp · not measured

context-guardian-mcp

MCP server + proxy that cuts cloud LLM costs 36-42% by indexing context locally with Ollama and giving agents precision retrieval tools instead of raw dumps. Runs locally from the context-guardian-mcp npm package.

Ar5en1c/context-guardian · not measured

linggen

MCP server "linggen", hosted remotely, as configured in linggen/linggen-memory.

linggen/linggen-memory · not measured

ling-mem

MCP server "ling-mem", hosted remotely, as configured in linggen/linggen-memory.

linggen/linggen-memory · not measured

mem-search

MCP server "mem-search" as configured in maxritter/pilot-shell. Launched with sh -c bun run ~/.pilot/scripts/mcp-server.cjs.

maxritter/pilot-shell · not measured