cursor

cursor is a skill for Claude Code, Codex from udjin-labs/mnemostack. It costs 0 tokens per session (496 once invoked), scanned A, original, Apache-2.0.

A setup guide for connecting mnemostack, a searchable memory service, to Cursor, a code editor with an AI assistant. It configures the connection through Cursor’s MCP settings.

In plain words
What is it for?
Use it to install and connect mnemostack, choose its memory collection and provider, verify available tools, and remove the connection later.
Why use it?
It removes the guesswork of putting the server in the right configuration file and checking whether Cursor can use it. It also provides a quick way to test the connection.

Skill for Claude CodeCodex

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 skills/udjin-labs/mnemostack/cursor
Any agent
npx skills add udjin-labs/mnemostack --skill cursor
Clone the repo
git clone --depth 1 https://github.com/udjin-labs/mnemostack

Made for: Claude Code, Codex.

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 cursor

README.md
[![agentmods](https://agentmods.dev/badge/skills/udjin-labs/mnemostack/cursor.svg)](https://agentmods.dev/skills/udjin-labs/mnemostack/cursor)
Your own site
<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>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 496 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 4d ago against content hash ecc693b1f455, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

integrations/cursor/SKILL.md · 71 lines

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

  1. Make sure the binary and a working backend are ready:

    pip install 'mnemostack[mcp]'
    mnemostack health --provider gemini
    
  2. Open Cursor → Settings → MCP (or edit ~/.cursor/mcp.json directly).

  3. Add the server entry:

    {
      "mcpServers": {
        "mnemostack": {
          "command": "mnemostack",
          "args": [
            "mcp-serve",
            "--provider", "gemini",
            "--collection", "my-memory"
          ],
          "env": {
            "GEMINI_API_KEY": "your-key-here"
          }
        }
      }
    }
    
  4. Reload Cursor (Cmd/Ctrl+Shift+PReload 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 of which 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.
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. 4d ago First seen · 71 lines · 0 tokens per session scan A ecc693b1f455

Subscribe to this mod's changes

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.

Related

Other skills, from other repositories