agentmods.dev

hypermnesia-mcp

A local memory system based on research in computational neuroscience, installed as a Python package that runs through the hypermnesia-mcp command.

In plain words
What is it for?
Use it when you need to run this local memory system as a Python-based service.
Why use it?
The description identifies its memory approach and local setup, but does not explain the specific information it stores or retrieves.

MCP server for Claude CodeCodexCursorGemini CLIOpenCode

71 4d ago A scan tokens not measured original MIT
View the source file cdeust/Cortex
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.

agentmods
npx agentmods add mcp/cdeust/cortex/hypermnesia-mcp
Clone the repo
git clone --depth 1 https://github.com/cdeust/Cortex

Made for: Claude Code, Codex, Cursor, Gemini CLI, OpenCode.

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. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

hypermnesia-mcp 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 2d 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 · 9 lines

What it actually says

{
  "hypermnesia-mcp": {
    "command": "uvx",
    "args": [
      "hypermnesia-mcp"
    ],
    "env": {}
  }
}
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. 2d ago First seen · 9 lines scan A 8fd150f9c68b

Subscribe to this mod's changes

hypermnesia-mcp is an MCP server published in the GitHub repository cdeust/Cortex (71 stars, last pushed 4d 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 2026-08-30.

Memory and contextagent-memory-systemcausal-inferenceclaude-codecognitive-architecturemcp-servermodel-context-protocol
Related

Other mcp servers, from other repositories

zikkaron

Biologically-inspired persistent memory engine for Claude Code. Runs locally from the zikkaron Python package.

amanhij/Zikkaron · not measured

dagstudio-mcp

Causal DAG analysis: backdoor paths, adjustment sets, bias simulation. Validated against dagitty. Remote server at dagstudio-mcp.blackswancausallabs.com.

Black-Swan-Causal-Labs/dagstudio-mcp · not measured

teamcity

MCP server exposing JetBrains TeamCity CI/CD workflows to AI coding assistants. Runs locally from the @daghis/teamcity-mcp npm package. Needs 3 environment variables to run.

Daghis/teamcity-mcp · not measured

claude-octopus

Spawn multiple specialized Claude Code agents as MCP servers, each independently configured. Runs locally from the claude-octopus npm package. Needs 7 environment variables to run.

xiaolai/claude-octopus · not measured

mcp-seedance

MCP Server for ByteDance Seedance AI Video Generation via AceDataCloud API. Runs locally from the mcp-seedance Python package. Needs 1 environment variable to run.

AceDataCloud/SeedanceMCP · not measured

mcp-pve

Manage Proxmox VE through AI assistants. Runs locally from the @samik081/mcp-pve npm package. Needs 3 environment variables to run.

Samik081/mcp-pve · not measured