The Unofficial dubco-mcp-server enables AI assistants to manage Dub.co short links via the Model Context Protocol (MCP). With this server, you can:
Create short links: Generate custom short links with optional slugs, domains, and external IDs
Update short links: Modify existing links by changing their destination URL, domain, or slug
Delete short links: Remove links by specifying their ID
AI integration: Seamlessly integrate with AI assistants like Claude through MCP for automated link management
Configuration: Works with Cursor IDE and supports environment-based API key setup
Allows users to create, update, and delete short links through the Dub.co API using npm packages
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., "@Unofficial dubco-mcp-server create a short link for my blog post about MCP servers"
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.
A Model Context Protocol (MCP) server for creating and managing Dub.co short links (unofficial). This server enables AI assistants to create, update, and delete short links through the Dub.co API.
Create custom short links with your Dub.co domains
Update existing short links
Delete short links
Seamless integration with AI assistants through the Model Context Protocol
Related MCP server: MCP API Server
Node.js 16.0.0 or higher
A Dub.co account with API access
An API key from the Dub.co dashboard
To install Dub.co MCP Server for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @Gitmaxd/dubco-mcp-server-npm --client claudenpm install -g dubco-mcp-servernpm install dubco-mcp-servernpx dubco-mcp-serverThis MCP server requires a Dub.co API key to function. You can get your API key from the Dub.co dashboard.
Set the API key as an environment variable:
export DUBCO_API_KEY=your_api_key_hereFor persistent configuration, add this to your shell profile (e.g., .bashrc, .zshrc):
echo 'export DUBCO_API_KEY=your_api_key_here' >> ~/.zshrcCursor IDE provides native support for MCP servers. Follow these steps to set up the dubco-mcp-server in Cursor:
If you haven't already, download and install Cursor IDE (version 0.4.5.9 or later).
Open Cursor IDE
Click on the gear icon in the bottom left corner, or use the keyboard shortcut Cmd+, (Mac) or Ctrl+, (Windows/Linux)
Navigate to the Features section
Scroll down to find the "MCP Servers" section
Click on "+ Add new MCP server"
In the dialog that appears:
Name: Enter "Dub.co MCP Server" (or any name you prefer)
Type: Select "command" from the dropdown
Command: Enter env DUBCO_API_KEY=your_api_key_here npx -y dubco-mcp-server
(Replace your_api_key_here with your actual Dub.co API key)
Click "Save" to add the server
After adding the MCP server, you should see a green status indicator next to the server name. If it shows a red or yellow status, try:
Checking that your API key is correct
Restarting Cursor IDE
Verifying that Node.js (16.0.0+) is properly installed
The dubco-mcp-server provides tools that can be used with Cursor's AI features:
Open Cursor's Composer or Agent mode (MCP only works in these modes)
Explicitly instruct the AI to use the Dub.co tools (create_link, update_link, delete_link)
Accept the tool usage prompts when they appear
This server provides tools that can be used by AI assistants through the Model Context Protocol. To use it with an MCP-compatible AI assistant, add it to your MCP configuration.
{
"mcpServers": {
"dubco": {
"command": "npx",
"args": ["-y", "dubco-mcp-server"],
"env": {
"DUBCO_API_KEY": "your_api_key_here"
},
"disabled": false,
"autoApprove": []
}
}
}Create a new short link on Dub.co.
Parameters:
{
"url": "https://example.com",
"key": "optional-custom-slug",
"externalId": "optional-external-id",
"domain": "optional-domain-slug"
}Example:
{
"url": "https://github.com/gitmaxd/dubco-mcp-server-npm",
"key": "dubco-mcp"
}Update an existing short link on Dub.co.
Parameters:
{
"linkId": "link-id-to-update",
"url": "https://new-destination.com",
"domain": "new-domain-slug",
"key": "new-custom-slug"
}Example:
{
"linkId": "clwxyz123456",
"url": "https://github.com/gitmaxd/dubco-mcp-server-npm/releases"
}Delete a short link on Dub.co.
Parameters:
{
"linkId": "link-id-to-delete"
}Example:
{
"linkId": "clwxyz123456"
}The server connects to the Dub.co API using your API key and provides a standardized interface for AI assistants to interact with Dub.co through the Model Context Protocol. When a tool is called:
The server validates the input parameters
It sends the appropriate request to the Dub.co API
It processes the response and returns it in a format that the AI assistant can understand
git clone https://github.com/gitmaxd/dubco-mcp-server-npm.git
cd dubco-mcp-server-npm
npm install
npm run buildnpm run devThis project is licensed under the ISC License - see the LICENSE file for details.
Dub.co - The URL shortener service
Model Context Protocol - Learn more about MCP
Contributions are welcome! Please feel free to submit a Pull Request.
Fork the repository
Create your feature branch (git checkout -b feature/amazing-feature)
Commit your changes (git commit -m 'Add some amazing feature')
Push to the branch (git push origin feature/amazing-feature)
Open a Pull Request
This unofficial Dub.co MCP Server was created by GitMaxd (@gitmaxd on X).
This project was developed as a learning exercise to understand the Model Context Protocol and how to build MCP servers. I chose Dub.co as the integration target because of its straightforward API and practical utility, making it an ideal candidate for a learning project.
While I have no official affiliation with Dub.co, I highly recommend their service for both manual and automated short link creation. Their API is well-documented and easy to work with, making it perfect for this kind of integration.
If you find this project helpful or have suggestions for improvements, feel free to reach out or contribute to the repository. Happy link shortening!
Create a new short link on dub.co, asking the user which domain to use
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | The destination URL to shorten | |
| key | No | Optional custom slug for the short link. If not provided, a random slug will be generated. | |
| externalId | No | Optional external ID for the link | |
| domain | No | Optional domain slug to use. If not provided, the primary domain will be used. |
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 mentions domain selection but fails to describe key traits like authentication requirements, rate limits, error handling, or what happens on success (e.g., returns a short URL). For a creation tool with zero annotation coverage, this is a significant gap in transparency.
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?
The description is a single, efficient sentence that front-loads the core purpose. It avoids unnecessary words, though it could be slightly more structured by explicitly mentioning the required 'url' parameter or output expectations.
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?
Given the complexity of a creation tool with 4 parameters, no annotations, and no output schema, the description is incomplete. It doesn't explain the return value (e.g., the generated short link), error conditions, or behavioral nuances like idempotency. This leaves gaps for an AI agent to invoke the tool correctly.
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?
Schema description coverage is 100%, so the schema already documents all parameters thoroughly. The description adds minimal value beyond the schema by hinting at domain selection ('asking the user which domain to use'), but doesn't provide additional syntax, format details, or context for parameters like 'key' or 'externalId'. 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.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Create a new short link') and the resource ('on dub.co'), with a specific verb+resource combination. It distinguishes from siblings like 'delete_link' and 'update_link' by focusing on creation, though it doesn't explicitly contrast with 'upsert_link' which might have overlapping functionality.
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?
The description implies usage when creating a short link on dub.co, with a hint about domain selection ('asking the user which domain to use'). However, it lacks explicit guidance on when to use this tool versus alternatives like 'upsert_link' or 'update_link', and doesn't mention prerequisites or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Delete a short link on dub.co
| Name | Required | Description | Default |
|---|---|---|---|
| linkId | Yes | The ID of the link to delete |
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 states the tool deletes a link, implying a destructive mutation, but doesn't mention whether this action is reversible, what permissions are required, how it affects associated data, or what happens on success/failure. For a destructive operation, this lack of detail is a significant gap, leaving the agent with insufficient information about behavioral traits.
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?
The description is a single, direct sentence that efficiently conveys the core action without unnecessary words. It's front-loaded with the key verb 'Delete' and specifies the resource clearly. There's zero waste, making it easy for an agent to parse quickly while still being informative enough for basic understanding.
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?
Given the tool's destructive nature (deletion), no annotations, and no output schema, the description is incomplete. It doesn't address critical context like what 'delete' entails (permanent vs. soft delete), error handling, or return values. For a mutation tool with zero annotation coverage, the description should provide more behavioral and outcome details to be sufficiently complete for safe agent use.
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?
The input schema has 100% description coverage, with the single parameter 'linkId' clearly documented as 'The ID of the link to delete'. The description doesn't add any additional meaning beyond this, such as format examples or sourcing instructions. Given the high schema coverage, a baseline score of 3 is appropriate, as the schema adequately handles parameter semantics without extra help from the 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?
The description clearly states the action ('Delete') and resource ('a short link on dub.co'), making the purpose immediately understandable. It doesn't explicitly differentiate from sibling tools like 'create_link' or 'update_link', but the verb 'Delete' inherently distinguishes it from creation and modification operations. The description is specific enough to understand what the tool does without being tautological.
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?
The description provides no guidance on when to use this tool versus alternatives like 'update_link' or 'upsert_link'. It doesn't mention prerequisites (e.g., needing an existing link ID), error conditions, or typical use cases. While the action is clear, there's no context to help an agent decide between this and other link management tools in the sibling set.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Update an existing short link on dub.co
| Name | Required | Description | Default |
|---|---|---|---|
| linkId | Yes | The ID of the link to update | |
| url | No | The new destination URL | |
| domain | No | The new domain for the short link | |
| key | No | The new slug for the short link |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. It states this is an update operation but doesn't mention what permissions are required, whether changes are reversible, what happens to existing data not mentioned in parameters, or any rate limits. For a mutation tool with zero annotation coverage, this leaves significant behavioral questions unanswered.
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?
The description is a single, efficient sentence that states exactly what the tool does without any wasted words. It's appropriately sized and front-loaded with the essential information.
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?
For a mutation tool with no annotations and no output schema, the description is insufficient. It doesn't explain what happens when the update succeeds or fails, what permissions are needed, or how this differs from sibling tools. Given the complexity of updating database records and the lack of structured safety information, more context is needed.
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?
Schema description coverage is 100%, so all parameters are documented in the schema. The description adds no additional parameter information beyond what the schema provides. According to scoring rules, when schema coverage is high (>80%), the baseline score is 3 even with no parameter information in the 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?
The description clearly states the action ('Update') and resource ('an existing short link on dub.co'), making the purpose immediately understandable. However, it doesn't differentiate this tool from its sibling 'upsert_link' which might also update links, leaving some ambiguity about when to choose one over the other.
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?
The description provides no guidance on when to use this tool versus alternatives like 'upsert_link' or 'create_link'. It mentions 'existing short link' which implies a prerequisite that the link must already exist, but offers no explicit when/when-not instructions or comparison with sibling tools.
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.
v1.0.0create_linkdelete_linkupdate_linkScored across 3 tools
Each tool has a clearly distinct purpose targeting a specific CRUD operation on short links: create, delete, and update. There is no overlap or ambiguity between these actions, making it easy for an agent to select the correct tool based on the intended operation.
All tool names follow a consistent verb_noun pattern (create_link, delete_link, update_link) with uniform snake_case styling. This predictability enhances readability and reduces cognitive load for agents when scanning the toolset.
With only 3 tools, the set feels thin for a link management domain, as it lacks a 'get' or 'list' tool to retrieve existing links, which is a common and necessary operation. While the tools present are well-defined, the count is borderline low for practical use.
The toolset has significant gaps for a dub.co link management server. It covers create, update, and delete operations but omits retrieval tools (e.g., get_link, list_links), leaving agents unable to query existing links. This incompleteness will likely cause agent failures in workflows requiring read operations.
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
A Model Context Protocol server for Wix AI tools
Model Context Protocol server for the Apideck Unified API. Connect any MCP-compatible agent framework to 100+ accounting systems, HRIS platforms, file storage providers, and more through one integration. More information https://www.apideck.com/mcp-server
Short-link service embedded in your AI workflow — shorten links, track campaigns, read stats.
