Skip to main content
Glama
enesjakozh
chrisboden

MCP Server Template for Cursor IDE

by chrisboden
OverviewSchemaRelated ServersScoreDiscussions
Python
Hybrid

MCP Server Template for Cursor IDE

A simple template for creating custom tools for Cursor IDE using Model Context Protocol (MCP). Create your own repository from this template, modify the tools, and connect them to your Cursor IDE.

Server Mood Response

Quick Start

  1. Click "Deploy to Heroku" button

    Deploy to Heroku

  2. After deployment, configure Cursor:

    • Open Cursor Settings → Features

    • Add new MCP server

    • Use your Heroku URL with /sse path (e.g., https://<your-app-name>.herokuapp.com/sse)

  3. Test your agent's mood in Cursor:

    • Ask your agent "Please ask about our server mood and let me know how it is."

    • The server will respond with a cheerful message and a heart ❤️

Related MCP server: MCP Server Template for Cursor IDE

Alternative Setup Methods

You can run the server in three ways: using Docker, traditional Python setup, or directly in Cursor IDE.

Docker Setup

The project includes Docker support for easy deployment:

  1. Initial setup:

# Clone the repository
git clone https://github.com/kirill-markin/weaviate-mcp-server.git
cd weaviate-mcp-server

# Create environment file
cp .env.example .env

  1. Build and run using Docker Compose:

# Build and start the server
docker compose up --build -d

# View logs
docker compose logs -f

# Check server status
docker compose ps

# Stop the server
docker compose down

  1. The server will be available at:

  2. Quick test:

# Test the server endpoint
curl -i http://localhost:8000/sse

  1. Connect to Cursor IDE:

    • Open Cursor Settings → Features

    • Add new MCP server

    • Type: Select "sse"

    • URL: Enter http://localhost:8000/sse

Traditional Setup

First, install the uv package manager:

# Install uv on macOS
brew install uv
# Or install via pip (any OS)
pip install uv

Start the server using either stdio (default) or SSE transport:

# Install the package with development dependencies
uv pip install -e ".[dev]"

# Using stdio transport (default)
uv run mcp-simple-tool

# Using SSE transport on custom port
uv run mcp-simple-tool --transport sse --port 8000

# Run tests
uv run pytest -v

After installation, you can connect the server directly to Cursor IDE:

  1. Right-click on the cursor-run-mcp-server.sh file in Cursor

  2. Select "Copy Path" to copy the absolute path

  3. Open Cursor Settings (gear icon)

  4. Navigate to Features tab

  5. Scroll down to "MCP Servers"

  6. Click "Add new MCP server"

  7. Fill in the form:

    • Name: Choose any name (e.g., "my-mcp-server-1")

    • Type: Select "stdio" (not "sse" because we run the server locally)

    • Command: Paste the absolute path to cursor-run-mcp-server.sh that you copied earlier. For example: /Users/kirillmarkin/weaviate-mcp-server/cursor-run-mcp-server.sh

Environment Variables

Available environment variables (can be set in .env):

  • MCP_SERVER_PORT (default: 8000) - Port to run the server on

  • MCP_SERVER_HOST (default: 0.0.0.0) - Host to bind the server to

  • DEBUG (default: false) - Enable debug mode

  • MCP_USER_AGENT - Custom User-Agent for website fetching

Additional options

Installing via Smithery

To install MCP Server Template for Cursor IDE for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @kirill-markin/example-mcp-server --client claude

Glama server review

Available Tools

2 tools
mcp_fetchC

Fetches a website and returns its content

ParametersJSON Schema
NameRequiredDescriptionDefault
urlYesURL to fetch

TDQS

C2.9/5.0
Behavior2/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions fetching and returning content, but lacks details on error handling, timeouts, authentication needs, rate limits, or what happens with invalid URLs. This is a significant gap for a tool that interacts with external resources.

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, efficient sentence that front-loads the core functionality without any wasted words. It's appropriately sized for a simple tool with one parameter.

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

Completeness2/5

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

Given the lack of annotations and output schema, the description is incomplete. It doesn't explain the return format (e.g., HTML, text, status codes), error conditions, or behavioral traits like network dependencies. For a fetch tool, this leaves critical gaps in understanding its operation.

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?

The input schema has 100% description coverage, with the 'url' parameter clearly documented. The description adds no additional meaning beyond what the schema provides, such as URL format requirements or examples. Baseline 3 is appropriate when the schema does the heavy lifting.

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?

The description clearly states the action ('fetches') and target ('a website'), and specifies the outcome ('returns its content'), which provides a specific verb+resource+result. However, it doesn't differentiate from the sibling tool 'mood', so it doesn't reach the highest score of 5.

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 provides no guidance on when to use this tool versus alternatives, such as the sibling tool 'mood', or any context about prerequisites, limitations, or typical use cases. It merely states what the tool does without indicating when it's appropriate.

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

moodA

Ask the server about its mood - it's always happy!

ParametersJSON Schema
NameRequiredDescriptionDefault
questionYesAsk this MCP server about its mood! You can phrase your question in any way you like - 'How are you?', 'What's your mood?', or even 'Are you having a good day?'. The server will always respond with a cheerful message and a heart ❤️

TDQS

A3.7/5.0
Behavior4/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively describes the tool's behavior: the server will 'always respond with a cheerful message and a heart ❤️', indicating a predictable, positive output. However, it doesn't cover aspects like rate limits, error handling, or authentication needs, which are relevant for a tool with no 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 extremely concise and front-loaded: one sentence states the purpose and behavior clearly, with no wasted words. Every part earns its place by conveying essential information efficiently.

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's low complexity (one parameter, no annotations, no output schema), the description is minimally complete. It explains what the tool does and the expected response, but lacks details on output format or error cases. For a simple tool, this is adequate but leaves some contextual gaps.

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?

The input schema has 100% description coverage, so the schema already documents the single parameter 'question' thoroughly. The description adds no additional parameter information beyond what's in the schema, meeting the baseline of 3 for high schema coverage without extra value.

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?

The description clearly states the tool's purpose: 'Ask the server about its mood' with a specific verb ('ask') and resource ('server'), though it doesn't distinguish from the sibling tool 'mcp_fetch' (which likely has a different function). The phrase 'it's always happy!' adds character but doesn't obscure the core purpose.

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?

The description implies usage context ('ask the server about its mood') but doesn't explicitly state when to use this tool versus alternatives like 'mcp_fetch'. It provides no exclusions or prerequisites, leaving usage guidance at an implied level without clear differentiation from siblings.

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

Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

B3/5.0
Disambiguation5/5

The two tools have completely distinct purposes: one fetches website content, while the other returns a static mood response. There is no overlap or ambiguity between them.

Naming Consistency2/5

The naming is inconsistent: 'mcp_fetch' uses a prefix and verb_noun pattern, while 'mood' is a single noun with no verb. This mixed convention lacks a predictable pattern.

Tool Count2/5

With only two tools, the server feels thin and under-scoped for a template intended for Cursor IDE, suggesting it might not cover enough functionality for typical IDE use cases.

Completeness2/5

The tool surface is severely incomplete for an IDE template, lacking core operations like file manipulation, code analysis, or project management. The existing tools do not form a coherent workflow.

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

Appeared in Searches

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/chrisboden/mcp_template'

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