A
licenseB
qualityD
maintenanceA simple template for creating custom tools for Cursor IDE using Model Context Protocol, deployable via Heroku, Docker, or directly within Cursor IDE.
2
5
MIT
MCP Server Template for Cursor IDE
This MCP server for Cursor IDE provides several functionalities through the Model Context Protocol:
Fetch Website Content: Retrieve content from specified URLs using the
mcp_fetchfunction.Mood Query: Ask the server about its mood - it always responds cheerfully with a heart ❤️ via the
moodfunction.Image Generation: Create images using DALL-E 3 based on textual prompts, with options for size, quality, and quantity (up to 1) through the
generate_imagefunction.Figma Design Access: Obtain design data from Figma, including structure and images, using the
figma_designfunction.
Allows deploying the MCP server directly to Heroku with a one-click 'Deploy to Heroku' button
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 Server Template for Cursor IDEcheck the server mood and give me a cheerful update"
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.
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.
Quick Start
Click "Deploy to Heroku" button
After deployment, configure Cursor:
Open Cursor Settings → Features
Add new MCP server
Use your Heroku URL with
/ssepath (e.g.,https://<your-app-name>.herokuapp.com/sse)
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:
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 .envBuild 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 downThe server will be available at:
SSE endpoint: http://localhost:8000/sse
Quick test:
# Test the server endpoint
curl -i http://localhost:8000/sseConnect 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 uvStart 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 -vAfter installation, you can connect the server directly to Cursor IDE:
Right-click on the
cursor-run-mcp-server.shfile in CursorSelect "Copy Path" to copy the absolute path
Open Cursor Settings (gear icon)
Navigate to Features tab
Scroll down to "MCP Servers"
Click "Add new MCP server"
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.shthat 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 onMCP_SERVER_HOST(default: 0.0.0.0) - Host to bind the server toDEBUG(default: false) - Enable debug modeMCP_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 claudeGlama server review
Available Tools
4 toolsfigma_designC
Get Figma design data including structure and images
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | The full Figma design URL |
TDQS
C2.9/5.0
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool retrieves data but lacks details on permissions, rate limits, error handling, or what 'structure and images' entails (e.g., format, size). This is a significant gap for a tool with no annotation coverage.
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 with zero waste. It is front-loaded with the core purpose and includes essential details ('structure and images') without redundancy. Every word earns its place, making it highly concise and well-structured.
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 no annotations and no output schema, the description is incomplete. It doesn't explain what 'Figma design data' includes beyond 'structure and images', how results are returned, or behavioral aspects like authentication needs. For a data retrieval tool with rich context (Figma API), more detail is warranted.
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 schema description coverage is 100%, with the single parameter 'url' fully documented in the schema as 'The full Figma design URL'. The description adds no additional meaning beyond this, such as URL format examples or constraints. 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 tool's purpose with a specific verb ('Get') and resource ('Figma design data'), specifying what data is retrieved ('structure and images'). It distinguishes from sibling tools like 'generate_image' (creation vs retrieval) and 'mcp_fetch' (generic vs Figma-specific), though it doesn't explicitly mention these distinctions.
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. It doesn't mention prerequisites (e.g., needing a valid Figma URL), exclusions, or comparisons to siblings like 'mcp_fetch' for general fetching or 'generate_image' for image creation. Usage is implied only by the purpose statement.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
generate_imageC
Generate an image using DALL-E 3
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| prompt | Yes | The description of the image you want to generate | |
| size | No | Image size (1024x1024, 1024x1792, or 1792x1024) | 1024x1024 |
| quality | No | Image quality (standard or hd) | standard |
| n | No | Number of images to generate |
TDQS
C2.9/5.0
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the action ('generate') but doesn't disclose traits like whether it's a read-only or destructive operation, authentication needs, rate limits, response format, or error handling. For a tool with no annotation coverage, this leaves significant gaps in understanding its 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?
The description is a single, efficient sentence with zero waste. It front-loads the core purpose ('Generate an image') and specifies the method ('using DALL-E 3'), making it easy to understand quickly without unnecessary details.
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 tool's complexity (image generation with 4 parameters) and lack of annotations and output schema, the description is incomplete. It doesn't explain what the tool returns (e.g., image URL, binary data), error conditions, or behavioral traits. For a tool with no structured support, the description should provide more context to be fully helpful.
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%, so the schema fully documents all parameters (prompt, size, quality, n). The description adds no additional meaning beyond what the schema provides, such as examples or usage tips. Baseline score of 3 is appropriate since the schema handles parameter documentation effectively.
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 verb 'generate' and the resource 'image', specifying it uses DALL-E 3. This distinguishes it from sibling tools like figma_design, mcp_fetch, and mood, which don't involve image generation. However, it doesn't explicitly mention what type of images (e.g., AI-generated, artistic) or differentiate further from potential unseen tools.
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. It doesn't mention any prerequisites, constraints (e.g., rate limits, costs), or compare it to sibling tools. Usage is implied only by the tool's name and description, with no explicit context or exclusions provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
mcp_fetchC
Fetches a website and returns its content
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | URL to fetch |
TDQS
C2.9/5.0
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool fetches and returns content, but lacks details on error handling, rate limits, authentication needs, or response format. For a tool with no annotations, this is a significant gap in transparency about its operational 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?
The description is extremely concise and front-loaded, consisting of a single, clear sentence: 'Fetches a website and returns its content'. Every word earns its place, with no redundant or unnecessary information, making it efficient and easy to parse.
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 tool's complexity (a fetch operation with potential behavioral nuances), lack of annotations, and no output schema, the description is incomplete. It doesn't explain what 'content' includes (e.g., HTML, text), error cases, or limitations, leaving gaps in understanding how the tool behaves in practice.
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 schema description coverage is 100%, with the parameter 'url' fully documented in the schema. The description adds no additional meaning beyond the schema, such as URL format constraints or examples. With high schema coverage, the baseline score of 3 is appropriate, as the description doesn't enhance parameter understanding.
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 resource ('a website'), specifying what the tool does. It distinguishes from most siblings (e.g., 'apply_prompt_' tools, 'mood') by focusing on web content retrieval, though it doesn't explicitly differentiate from 'fetch_railway_docs' tools. The purpose is specific but lacks sibling comparison.
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. It doesn't mention scenarios for usage, prerequisites, or exclusions, and offers no comparison to sibling tools like 'fetch_railway_docs' or 'fetch_railway_docs_optimized'. Usage is implied only by the action 'fetches', with no explicit context.
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
| Name | Required | Description | Default |
|---|---|---|---|
| question | Yes | Ask 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
A3.5/5.0
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 key traits: the tool queries the server's mood, the server is 'always happy', and responses include 'a cheerful message and a heart ❤️'. This covers the interactive nature and predictable output style, though it lacks details like response format or error handling. No contradiction with annotations exists.
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 (one sentence) and front-loaded with the core purpose. Every word earns its place: 'Ask the server about its mood' defines the action, and 'it's always happy!' adds essential behavioral context. There's zero redundancy or fluff, making it highly efficient for an agent to parse.
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 (single parameter, no output schema, no annotations), the description is reasonably complete for its purpose. It explains what the tool does and the expected response behavior. However, it lacks output details (e.g., response structure) and doesn't address potential edge cases, leaving some gaps in full contextual understanding for an agent.
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 parameter 'question' fully documented in the schema itself (including examples like 'How are you?'). The description adds no additional parameter semantics beyond what the schema provides, such as formatting tips or constraints. According to rules, with high schema coverage (>80%), the baseline is 3 even without param info in the description.
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: to ask the server about its mood, with the specific behavioral outcome that it 'always responds with a cheerful message and a heart ❤️'. It distinguishes from sibling tools (all related to prompt application or documentation fetching) by focusing on a conversational interaction rather than functional operations. However, it doesn't explicitly contrast with specific alternatives for mood-checking, keeping it at 4 rather than 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. While it implies usage for checking server mood, it doesn't specify contexts (e.g., after errors, during idle time) or exclusions (e.g., not for functional queries). With sibling tools focused on practical tasks, the lack of when/when-not guidance leaves the agent guessing about appropriate use cases.
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.
4 tool updates
v1.0.0- Added
figma_design - Added
generate_image - Added
mcp_fetch - Added
mood
TDQS
B3/5.0
Scored across 4 tools
Disambiguation5/5
Each tool has a clearly distinct purpose with no overlap: figma_design retrieves design data, generate_image creates new images, mcp_fetch fetches web content, and mood is a whimsical status check. The descriptions make it impossible to confuse one tool for another.
Naming Consistency2/5
The naming is inconsistent with mixed conventions: figma_design uses snake_case, generate_image uses snake_case, mcp_fetch uses snake_case but with an acronym prefix, and mood is a single lowercase word. There's no consistent verb_noun pattern, and the styles vary enough to cause confusion.
Tool Count3/5
With 4 tools, the count is borderline thin for a server template aimed at Cursor IDE, which might imply broader utility. While each tool is distinct, the set feels minimal and may not cover enough ground for typical development workflows, suggesting it's slightly under-scoped.
Completeness2/5
For a Cursor IDE template, there are significant gaps: no code-related tools (e.g., edit, lint, debug), no project management features, and no integration with common IDE functions. The tools are disparate (design, image generation, web fetch, mood) without a cohesive domain, making it incomplete for practical use.
Maintenance
ActivityInactive
ResponsivenessNo issues
Related MCP Connectors
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
A Model Context Protocol server for Wix AI tools
The OpenRouter MCP server plugs OpenRouter into the AI tools you already use. Once connected, your assistant can pull live OpenRouter data (models, prices, your credits, rankings, and docs) and send quick test messages, all without leaving your editor.
Generate PDFs from templates via AI chat. Works with Claude, ChatGPT, Cursor, and any MCP client.
Related MCP Servers
- AlicenseBqualityDmaintenanceA template for creating custom tools for Cursor IDE using Model Context Protocol that allows users to deploy their own MCP server to Heroku and connect it to Cursor IDE.22MIT
- AlicenseCqualityDmaintenanceA template for creating custom tools for Cursor IDE using Model Context Protocol (MCP), allowing developers to extend Cursor's functionality with their own server-based tools.122MIT
- AlicenseCqualityDmaintenanceA starter template for building Model Context Protocol servers that can be integrated with Cursor or Claude Desktop, allowing developers to create custom tools and extensions for AI assistants.111 npm14MIT