Skip to main content
Glama
deenesjakoruzh
utakatano

mcp-server-sample

by utakatano
OverviewSchemaRelated ServersScoreDiscussions
JavaScript
Local

mcp-server-sample — Minimal MCP Server for Saving and Searching Notes

A minimal MCP server that only saves and searches notes. It does not connect to any external systems. The only storage is a single notes.json file in the same folder.

It includes one of each of the three MCP primitives.

Primitive

Decided by

Contents in this server

Tools

Model decides

add_note (add a note) / search_notes (search notes)

Resources

AI app fetches and passes

notes://all (all saved notes)

Prompts

User explicitly selects

weekly_review (weekly review)

Requirements

  • Node.js 24 or higher (LTS. Check with node --version)

  • git

Related MCP server: Notes MCP Server

Setup

git clone https://github.com/utakatano/mcp-server-sample.git
cd mcp-server-sample
npm install

Once npm install completes successfully, you are ready. Do not start it at this point. The MCP server is started by the AI app, so you do not need to run it manually from the terminal.

Connect to the AI App

Claude Code

claude mcp add notes -- node /絶対パス/mcp-server-sample/index.js

If claude mcp list shows ✔ Connected, it is connected.

Claude Desktop

Go to Settings → Developer → "Edit Config" to open claude_desktop_config.json and add the following.

{
  "mcpServers": {
    "notes": {
      "command": "node",
      "args": ["/絶対パス/mcp-server-sample/index.js"]
    }
  }
}

After saving, fully quit Claude Desktop and restart it (closing the window alone is not enough).

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

  • Windows: %APPDATA%\Claude\claude_desktop_config.json

Verification

「来週までにネットワーク構成を確認する」とメモして
「ネットワーク」を含むメモを探して

You can confirm that notes.json is created and its contents increase.

Changing the Storage Location

Pass an absolute path to the environment variable NOTES_FILE to change the storage location.

{
  "mcpServers": {
    "notes": {
      "command": "node",
      "args": ["/絶対パス/mcp-server-sample/index.js"],
      "env": { "NOTES_FILE": "/絶対パス/my-notes.json" }
    }
  }
}

When It Does Not Connect

First, check the log. The cause is usually there.

tail -20 ~/Library/Logs/Claude/mcp-server-notes.log   # macOS
# Windows: %APPDATA%\Claude\logs\mcp-server-notes.log

Look to see if there are any errors after Server started and connected successfully.

What appears in the log

Cause

Remedy

Cannot find module '/.../index.js'

The path in args is wrong

Run pwd in the repository root and paste its output + /index.js

spawn node ENOENT

The AI app cannot find node. Occurs when PATH is only in the shell config (e.g., nvm / volta)

Write the output of which node (absolute path) directly into command

Cannot find package '@modelcontextprotocol/server'

Dependencies are not installed

Run npm ci in the repository root

Log is empty or not updating

The configuration is not loaded

Check JSON syntax (commas, brackets) and fully quit Claude Desktop (macOS: ⌘Q) before restarting

To determine whether the issue is on the server side or the AI app side, it is fastest to run the server directly from your terminal.

printf '{"jsonrpc":"2.0","id":1,"method":"tools/list","params":{"_meta":{"io.modelcontextprotocol/protocolVersion":"2026-07-28"}}}\n' \
  | node /絶対パス/mcp-server-sample/index.js

If a JSON containing add_note and search_notes is returned, the server is working correctly. In that case, suspect the AI app's configuration (path, JSON formatting, restart).

Supply Chain Countermeasures

Settings to guard against npm package hijacking are included in .npmrc. They take effect every time npm install / npm ci is run.

Setting

What it does

ignore-scripts=true

Does not execute lifecycle scripts (e.g., postinstall) of dependency packages during installation. Blocks the first execution path a hijacked package would use. npm start / npm run still work as usual (only pre/post scripts are disabled)

save-exact=true

npm install <pkg> writes exact versions to package.json without ^

min-release-age=7

Only installs versions published more than 7 days ago. npm converts this to before=<date 7 days ago> when resolving dependencies

Dependencies are fully pinned in package.json (@modelcontextprotocol/server is 2.0.0, zod is 4.4.3), and recorded with integrity hashes in package-lock.json. To install exactly as specified in the lock file, use npm ci instead of npm install.

When updating dependencies, upgrade them one at a time intentionally.

npm outdated
npm install @modelcontextprotocol/server@2.1.0   # save-exact により完全固定で書かれる
npm ls --all                                      # 増えた依存を目で確認する

License

MIT

Available Tools

2 tools
add_noteメモを追加するA

メモを1件保存する。打ち合わせの決定事項や、あとで思い出したいことを記録するときに使う。

ParametersJSON Schema
NameRequiredDescriptionDefault
tagsNo分類用のタグ（任意）
textYes保存する本文

TDQS

A4/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It states '保存する' which implies mutation, but it does not disclose potential side effects, permissions, or behavior on duplicates. For a simple create operation, this is minimally adequate.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with the essential action. No wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple tool with 2 parameters, no output schema, and no annotations, the description is fairly complete. It explains the primary use case and differentiates from the sibling. It could mention the return value but is not required.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% with both parameters described. The tool's description adds no new information about the parameters; it only restates the purpose. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb '保存する' (save) and resource 'メモ' (note), and it is distinct from the sibling tool 'search_notes' which is for retrieval.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It provides explicit context for when to use: '打ち合わせの決定事項や、あとで思い出したいことを記録するときに使う' (use when recording meeting decisions or things you want to remember later). It does not explicitly exclude other scenarios, but the purpose is clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

search_notesメモを検索するB

保存済みのメモをキーワードで検索する。本文とタグの両方を対象にする。

ParametersJSON Schema
NameRequiredDescriptionDefault
keywordYes検索キーワード

TDQS

B3.2/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must fully disclose behavioral traits. It states search targets both body text and tags, but lacks details on whether searches are case-sensitive, support partial matches, or have rate limits. It does not mention return format or pagination. The description adds modest value but is insufficient for a tool lacking annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence with no wasted words. It is concise and front-loaded with the action and target, then expands on scope. Every phrase adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool is simple (1 parameter, no output schema, no nested objects), the description is minimally adequate. It covers the search target and scope. However, it omits any mention of results behavior (e.g., whether it returns full notes or summaries) and does not compensate for missing annotations, but the low complexity reduces the burden.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with one parameter 'keyword'. The description adds meaningful context by specifying that keyword searches both body and tags, which the schema description ('検索キーワード') does not convey. This enriches the semantic understanding beyond the schema alone.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly specifies the action (検索する), the target (保存済みのメモ), and the search scope (本文とタグの両方). It distinguishes from add_note, which creates notes. However, it does not explicitly contrast the two, leaving a slight gap in sibling differentiation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for keyword search but gives no guidance on when to use this vs. add_note, nor does it mention any context or prerequisites for searching. No exclusion criteria or alternative scenarios are provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. 2 tool updatesv1.0.0
    • First observedadd_note
    • First observedsearch_notes
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A3.5/5.0
Disambiguation5/5

The two tools have completely distinct purposes: one creates/ stores a note, the other retrieves notes via search. There is no overlap or ambiguity between writing and searching.

Naming Consistency5/5

Both tool names follow a consistent verb_noun pattern (add_note, search_notes) using lowercase with underscores. The naming is predictable and clear.

Tool Count3/5

With only 2 tools, the set feels minimal. While the tools cover basic create and read/search operations, the server's purpose (saving and retrieving notes) could reasonably include more tools (e.g., update, delete, list tags) to avoid being overly thin.

Completeness2/5

The domain is a personal note-taking system, but only add and search operations are provided. Missing critical operations like update, delete, and get all notes (without search) create significant gaps that would frustrate or block a typical agent workflow.

Maintenance

ActivityMaintained
ResponsivenessNo issues

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

  • approveit MCP Server

    HJH0924
    -
    license
    Not graded
    quality
    Not graded
    maintenance
    A simple notes system that allows creating, storing, and accessing text notes through MCP resources and tools, with built-in prompt support for generating summaries of stored notes.
    -

  • Notes MCP Server

    prem2230
    F
    license
    B
    quality
    D
    maintenance
    A simple server for saving, listing, and searching notes persisted to a local JSON file. It enables users to manage their personal notes using natural language via the Model Context Protocol.
    3
    -

  • pdf-reader-server

    TomCN0803
    F
    license
    Not graded
    quality
    D
    maintenance
    A Model Context Protocol server for managing text notes, with resources (note:// URIs), tools (create_note), and prompts (summarize_notes).
    -

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/utakatano/mcp-server-sample'

If you have feedback or need assistance with the MCP directory API, please join our Discord server