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.
git clone --depth 1 https://github.com/28naem-del/mnemosyneWrote 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.
[](https://agentmods.dev/mcp/28naem-del/mnemosyne/claude-code-mnemosyne)<a href="https://agentmods.dev/mcp/28naem-del/mnemosyne/claude-code-mnemosyne"><img src="https://agentmods.dev/badge/mcp/28naem-del/mnemosyne/claude-code-mnemosyne/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.
<a href="https://agentmods.dev/mcp/28naem-del/mnemosyne/claude-code-mnemosyne"><img src="https://agentmods.dev/badge/mcp/28naem-del/mnemosyne/claude-code-mnemosyne.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket warn
Grade A, and why
mnemosyne 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.
What it actually says
{
"mnemosyne": {
"command": "npx",
"args": [
"-y",
"-p",
"mnemosy-ai@next",
"mnemosy",
"mcp",
"--db",
"${CLAUDE_PROJECT_DIR}/.mnemosyne/memory.sqlite",
"--workspace",
"default",
"--agent",
"claude-code"
]
}
}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.
- 2d ago First seen · 18 lines scan A a3e0bbf9d5f3
mnemosyne is an MCP server published in the GitHub repository 28naem-del/mnemosyne (154 stars, last pushed 3d 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 2026-10-30.
Other mcp servers, from other repositories
vision-memory-mcp
MCP server "vision-memory-mcp" as configured in putervision/state-memory-mcp. Launched with vision-memory-mcp run. Needs 1 environment variable to run.
state-memory-mcp
MCP server "state-memory-mcp" as configured in putervision/state-memory-mcp. Launched with state-memory-mcp run.
cpersona
CPersona — persistent memory for AI agents over MCP. One SQLite file you own, hybrid vector + full-text + keyword search, no LLM in the loop, and honest reporting when recall degrades. MIT licensed. Runs locally from the cpersona Python package. Needs 4 environment variables to run.
engrava
Model Context Protocol server for Engrava - expose an agent memory database to any MCP client over stdio. Runs locally from the engrava-mcp Python package. Needs 3 environment variables to run.
munin-memory
MCP server "munin-memory" as configured in Magnus-Gille/munin-memory. Runs locally from the munin-memory npm package.
n-memory
MCP server "n-memory" as configured in menot-you/n-memory. Launched with https://github.com/menot-you/n-memory/releases/download/v0.1.2/nmemory-linux-x86.