Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@mindpad MCP Save a note about today's meeting agenda"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Save notes to your mindpad account directly from AI assistants.
mindpad is a privacy-first, European note-taking app where notes are end-to-end encrypted on your device before they ever leave it — meaning even mindpad can't read them. No tracking, no ads, no AI training on your content. Fully GDPR-compliant and hosted within the EU.
1. Generate a Personal Access Token
Go to your mindpad account settings and generate a Personal Access Token.
2. Add to your AI assistant
Add the following to your MCP client config (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"mindpad": {
"command": "npx",
"args": ["-y", "@mindpad/mcp"],
"env": {
"MINDPAD_PAT": "your-pat-here"
}
}
}
}3. Restart your AI assistant
That's it. You can now ask your assistant to save notes to your mindpad account.
Related MCP server: second-brain-mcp
Just talk to your assistant naturally:
"Save a note about today's meeting"
"Jot this down for me: pick up groceries !errand"
"Remember that the API key expires on Friday !work"
Tags can be added inline using !tagname.
Your notes are end-to-end encrypted on your device before they sync. mindpad cannot read them — by design, not by policy. If you lose your encryption key, your notes are gone. No exceptions.
Built in Europe. Hosted in Europe. Protected by GDPR.
MIT
Saves a note to the user's mindpad account. Use this when the user wants to capture, remember, or jot something down.
| Name | Required | Description | Default |
|---|---|---|---|
| content | Yes | The note content. Supports markdown. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description bears the full burden of behavioral disclosure. It clearly conveys that this is a persistent write operation targeting the user's mindpad account. However, it does not disclose whether it creates a new note or overwrites an existing one, whether any permissions are needed, or what the result of a save looks like, which are relevant details for a mutation tool without annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two short sentences with no fluff. The action and destination are front-loaded in the first sentence, and the second sentence gives clear usage context. Every word earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a single-parameter tool with no output schema, the description is nearly complete: it states the action, destination, and when to use it. It could be more complete by describing what happens after saving, such as whether a new note is created or an existing note is replaced, but the low complexity keeps the gap minor.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents the content parameter, including markdown support. The description adds no additional parameter-level information, and the baseline of 3 is appropriate because the schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('saves') with a clear resource ('a note') and destination ('the user's mindpad account'). It also paraphrases the use case as capturing, remembering, or jotting something down, making the purpose unambiguous even without sibling tools to compare against.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly says when to use the tool: when the user wants to capture, remember, or jot something down. It does not provide exclusions or alternatives, but with no sibling tools, when-not guidance is less necessary; still, a small gap remains around when this tool would not be appropriate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.1.0save_noteScored across 1 tool
Only one tool exists, so there is no possibility of confusion. The purpose of save_note is clear and distinct from any other potential tools.
The single tool uses a consistent verb_noun pattern (save_note). With only one tool, there are no inconsistencies to evaluate.
A single tool is insufficient for a note-taking service. The scope clearly requires at least retrieval and deletion capabilities, making this too few.
The server only supports saving notes, with no way to read, list, update, or delete them. This is a severely incomplete surface for a note management domain.
Save notes in seconds. Your AI can then search, read, write and tag them over MCP.
Securely search, create, and organize your Mem notes and collections from AI assistants.
Persistent memory layer for AI tools. Save and recall notes across Claude and other MCP clients.
MCP-native notes and memory for ChatGPT, Claude, and other AI tools.
