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., "@MCP Playground propose a team of 5 for a new mobile app development project"
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.
Python 3.13
uv package manager
SQLite3
Related MCP server: DB MCP (HR CSV → SQLite)
Clone the repository
git clone <repository-url>
cd mcp_playgroundInstall dependencies with uv
uv syncSetup the SQLite database
Create a new SQLite database file using the provided schema.
cd dbsqlite3 database.db < schema.sqlInsert dummy data into the database.
sqlite3 database.db < insert_data.sqlStart the venv (if you want to start the server manually)
source .venv/bin/activateThe server currently uses IO for communication. It is not meant to be started manually, instead it should be accessed through an MCP client.
The following functions are implemented in the server:
db_schema (resource)
Returns the database schema by reading the schema.sql file.
get_users (tool)
Fetches a list of all user names from the users table in the database.
get_all_employee_profiles (tool)
Retrieves all employee profiles
send_email (tool)
Sends an email using mailtrap.
Requires API-key in .env file:
MAILTRAP_API_TOKEN=your_mailtrap_api_keypropose_team_for_project (prompt)
Given a project description and team size, proposes a team of employees best suited for the project based on their skills and experience.
Add the following configuration to your MCP client (e.g., Claude Desktop):
Settings → Developer → Edit config → claude_desktop_config.json
mcpServers: The server name, in this case not-solita-corp.
command: The ABSOLUTE path to the uv executable on your system.
args: The arguments to start the MCP server, including the ABSOLUTE path to the mcp_playground directory.
Note: Windows paths use backslashes (\).
{
"mcpServers": {
"mcp_demo": {
"command": "/path/to/user/.local/bin/uv",
"args": [
"--directory",
"/path/to/user/mcp_playground",
"run",
"server.py"
]
}
}
}| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
| Name | Required | Description | Default |
|---|---|---|---|
| body | Yes | ||
| subject | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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.
v0.1.0get_all_employee_profilesget_userssend_emailScored across 3 tools
get_users and get_all_employee_profiles likely serve similar purposes, potentially causing confusion. Without descriptions, an agent may select the wrong tool.
All tools follow a verb_noun pattern (get_, send_), but the noun forms are inconsistent: 'users' versus 'all_employee_profiles' and 'email'.
With only 3 tools, the set is small but might be adequate for a simple playground. The count is borderline but not extreme.
Missing basic CRUD operations for users/employees (create, update, delete) and limited email functionality (only send). Significant gaps for a typical management domain.
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
Hosted MCP server for live public-data APIs and Skills for AI agents.
MCP server unifying ERPs, CRMs, APIs and knowledge base for Claude, ChatGPT and Gemini.
MCP server exposing klokin time-tracking operations (employees, time entries, stores) to AI clients.
