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.
npx agentmods add skills/udjin-labs/mnemostack/cursornpx skills add udjin-labs/mnemostack --skill cursorgit clone --depth 1 https://github.com/udjin-labs/mnemostackWrote 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/skills/udjin-labs/mnemostack/cursor)<a href="https://agentmods.dev/skills/udjin-labs/mnemostack/cursor"><img src="https://agentmods.dev/badge/skills/udjin-labs/mnemostack/cursor.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.00496 |
| Opus 5 | $0.00000 | $0.00248 |
| Sonnet 5 | $0.00000 | $0.00099 |
| Haiku 4.5 | $0.00000 | $0.00050 |
Grade A, and why
cursor 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 4d 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
Cursor
Wire mnemostack into Cursor as an MCP server. Cursor reads MCP servers from its own settings, not from Claude Desktop's config.
Install
-
Make sure the binary and a working backend are ready:
pip install 'mnemostack[mcp]' mnemostack health --provider gemini -
Open Cursor → Settings → MCP (or edit
~/.cursor/mcp.jsondirectly). -
Add the server entry:
{ "mcpServers": { "mnemostack": { "command": "mnemostack", "args": [ "mcp-serve", "--provider", "gemini", "--collection", "my-memory" ], "env": { "GEMINI_API_KEY": "your-key-here" } } } } -
Reload Cursor (
Cmd/Ctrl+Shift+P→ Reload Window). The server should appear in the MCP panel with a green dot.
Verify
Open the Cursor chat and ask:
What MCP tools do you have from mnemostack?
Expected: health, search, answer, feedback (and graph_query plus
graph_add_triple if a Memgraph URI was set).
Quick smoke test:
Search mnemostack for "VPN failover", tier 2.
The model should invoke the tool and return short (~40 char) snippets with source ids.
Uninstall
Remove the mnemostack block from ~/.cursor/mcp.json (or toggle it off in
the Cursor MCP settings UI) and reload the window.
Troubleshooting
- Server stays red: Cursor doesn't always show stderr — run the same
command manually in a terminal to see what's wrong:
mnemostack mcp-serve --provider gemini --collection my-memory. - PATH differs in GUI: Cursor on macOS inherits a different PATH than
Terminal. Use an absolute path for
command(e.g. output ofwhich mnemostack). - Model can't find the tool: some Cursor versions gate MCP behind per-chat tool toggles. Check the tools icon in the chat input.
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.
- 4d ago First seen · 71 lines · 0 tokens per session scan A ecc693b1f455
cursor is a skill published in the GitHub repository udjin-labs/mnemostack (7 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 496 tokens. 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.
Other skills, from other repositories
memory-retrieval
Automatically retrieve relevant memories when user asks about past decisions, conventions, or patterns.
install-openviking-memory
Install and configure the OpenViking long-term memory plugin for OpenClaw via natural conversation. Once installed, the plugin automatically captures facts from chats and recalls relevant context before each reply (auto-capture + auto-recall, cross-session). Covers prerequisites, install through OpenClaw's plugin…
openclaw-plugin
This plugin is a thin adapter between OpenClaw and LycheeMem. It does not replace memory-core, does not claim plugins.slots.memory, and does not duplicate LycheeMem algorithms.
lycheemem
Forceful operating rules for using LycheeMem as the primary structured long-term memory path inside OpenClaw.
memory
Use LycheeMem as Claude Code's structured long-term memory for prior conversations, user preferences, project decisions, timelines, and durable facts.
emem-a2a-collaboration
Join the agent-to-agent collaboration running on emem's signed ledger — find the standard, verify another agent's message offline (who wrote it, not just that it was stored), announce yourself, and hand facts to other agents as tokens. Use when the user wants agents to coordinate without a shared database or shared…