Skip to main content
Glama
ejoliet

mcp-starter

by ejoliet
OverviewSchemaRelated ServersScoreDiscussions
Python
Local

mcp-starter

A minimal MCP (Model Context Protocol) server that demonstrates the three core capability types — Tools, Resources, and Prompts — through a simple notes app.

Use this as a learning template or starting point for building your own MCP server.

What's inside

Capability

Name

What it does

Tool

add_note

Save a note with a title and body

Tool

list_notes

List all note IDs and titles

Tool

delete_note

Delete a note by ID

Resource

notes://all

Read full content of all notes as JSON

Prompt

summarize_notes

Ask Claude to summarize all notes as bullet points

Notes are persisted to notes.json alongside server.py.

Related MCP server: MCP Notepad Server

Install

One-liner (bash)

Requires uv and Claude Code.

curl -fsSL https://raw.githubusercontent.com/ejoliet/mcp-starter/main/install.sh | bash

This clones the repo to ~/mcp-starter, installs dependencies, and registers the server with Claude Code automatically. Start a new Claude Code session and it's ready.

To install to a custom path:

MCP_STARTER_DIR=~/dev/mcp-starter curl -fsSL https://raw.githubusercontent.com/ejoliet/mcp-starter/main/install.sh | bash

Docker

Requires Docker.

git clone https://github.com/ejoliet/mcp-starter.git
cd mcp-starter
docker compose up --build

Notes are persisted in a named Docker volume (notes-data). Register the containerized server with Claude Code:

claude mcp add mcp-starter -- docker compose -f ~/mcp-starter/docker-compose.yml run --rm mcp-starter

Manual setup

Requirements: Python 3.12+, uv, Claude Code.

git clone https://github.com/ejoliet/mcp-starter.git ~/mcp-starter
cd ~/mcp-starter
uv sync
claude mcp add mcp-starter -- uv --directory ~/mcp-starter run server.py

Then start a new Claude Code session — the server will be available automatically.

Usage in Claude

Once registered, Claude can call tools directly:

"Add a note titled 'standup' with body 'review PR #42'"
"List my notes"
"Delete note #1"

Or read the resource and prompt via the MCP panel (/mcp).

CLI development & testing

See DEV_GUIDE.md for how to iterate on the server from the terminal without relying on Claude Code.

Quick test:

uv run python test_resource.py

Project structure

mcp-starter/
├── server.py          # MCP server implementation
├── test_resource.py   # CLI test harness
├── install.sh         # Bash one-liner installer
├── Dockerfile         # Container image
├── docker-compose.yml # Compose config
├── pyproject.toml     # Dependencies
└── DEV_GUIDE.md       # Developer iteration guide

Extending

Add a new tool in server.py:

  1. Append a types.Tool(...) entry in list_tools()

  2. Handle name == "your_tool" in call_tool()

  3. Test with test_resource.py before restarting Claude Code

Available Tools

3 tools
add_noteA

Save a new note with a title and body.

ParametersJSON Schema
NameRequiredDescriptionDefault
titleYesShort title
bodyYesNote content

TDQS

A3.6/5.0
Behavior2/5

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

No annotations provided, so description carries full burden. It only states 'save a new note,' which implies a write operation, but does not disclose whether updates are possible, if there are limits, or what the response looks like. Behavioral traits beyond creation are missing.

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, front-loaded sentence with no wasted words: action verb 'Save', target 'new note', and parameters 'with a title and body'. Efficient and clear.

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 create tool with two parameters and no output schema, the description captures the core functionality. It could optionally mention that it creates a new note (not updates) or hint at the response, but it is largely adequate for the tool's simplicity.

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 coverage is 100% with descriptions 'Short title' and 'Note content.' The description adds marginal value by naming the parameters ('title and body') but does not provide additional constraints or formatting beyond what the schema already offers. 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?

Description clearly states 'Save a new note with a title and body,' specifying the action (save) and resource (note). It distinguishes from siblings 'delete_note' and 'list_notes' by implying creation vs. deletion and listing.

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

Usage Guidelines3/5

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

Usage is implied (creating new notes), but no explicit guidance on when to use this tool versus alternatives like 'delete_note' or 'list_notes'. No when-not scenarios or prerequisites mentioned.

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

delete_noteA

Delete a note by its numeric ID.

ParametersJSON Schema
NameRequiredDescriptionDefault
idYesNote ID to delete

TDQS

A3.6/5.0
Behavior2/5

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

Description only says 'delete' without elaborating on side effects (e.g., permanent removal, return value, permission requirements). With no annotations, the description should provide more behavioral context but is minimal.

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?

Single, direct sentence with no wasted words. Front-loaded with the action and resource, followed by parameter method. Efficient and to the point.

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 delete tool with one parameter and no output schema, the description is sufficient. It explains what the tool does and the required input. Could mention whether deletion is permanent or confirmable, but not necessary for basic understanding.

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 covers the single parameter 'id' with description 'Note ID to delete'. The description adds 'numeric' which aligns with integer type. Schema description coverage is 100%, so baseline is 3; description adds minimal extra meaning.

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?

Description clearly states the action (delete) and resource (note) with the method (by numeric ID). It distinguishes from sibling tools add_note and list_notes, which serve different purposes.

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

Usage Guidelines3/5

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

Description implies usage when a specific note needs to be deleted, but does not explicitly state when not to use it or mention alternatives. No exclusions or context for when this tool is appropriate over others.

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

list_notesA

Return all note IDs and titles.

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

TDQS

A3.7/5.0
Behavior2/5

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

No annotations exist, so description bears full burden. It only states returns IDs and titles but does not disclose read-only nature, potential performance concerns, or pagination behavior.

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?

Single sentence with no wasted words. Concise and front-loaded.

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?

No output schema exists, description hints at return structure (IDs and titles) but lacks details like format or array wrapping. Minimally adequate for a simple tool.

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?

No parameters exist, schema coverage is 100%. Description does not need to add parameter info; baseline is 4.

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?

Description clearly states action ('Return') and resource ('all note IDs and titles'). Distinguishes from sibling tools add_note and delete_note by being a read operation.

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

Usage Guidelines3/5

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

No explicit guidance on when to use or when not to use. While context implies it's for listing notes, no exclusions or comparisons with siblings 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. 3 tool updatesv0.1.0
    • First observedadd_note
    • First observeddelete_note
    • First observedlist_notes
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A3.7/5.0
Disambiguation5/5

Each tool has a distinct purpose: create, delete, and list notes. There is no overlap or ambiguity.

Naming Consistency5/5

All tools follow a consistent verb_noun pattern: add_note, delete_note, list_notes.

Tool Count4/5

Three tools is reasonable for a simple note-taking starter, though missing get/update operations keeps it from being fully scoped.

Completeness2/5

Missing essential operations like fetching a single note by ID and updating notes. Only create, delete, and list are provided, leaving significant gaps.

Maintenance

ActivityInactive
ResponsivenessSyncing

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

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/ejoliet/mcp-starter'

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