Provides tools for interacting with Roboflow's computer vision platform, including searching models and datasets, creating models from prompts, running inference (detection, segmentation, classification), managing workflows, and uploading images to projects.
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., "@Roboflow MCP Server create a model for detecting potholes"
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 that gives AI coding agents programmatic access to Roboflow's computer vision platform. Provides 10 tools across 5 groups: Discovery, Rapid Creation, Inference, Workflows, and Utilities.
curl -fsSL https://raw.githubusercontent.com/eusef/Eusef_Roboflow_MCP/main/install.sh | bashThis clones the repo to ~/.roboflow/mcp-server, installs dependencies, builds, and prints the config snippet to add to Claude Code.
Related MCP server: MCP Server for n8n Integration
Node.js >= 20.0.0
A Roboflow API key (get one at https://app.roboflow.com/settings/api)
git clone https://github.com/eusef/Eusef_Roboflow_MCP.git
cd Eusef_Roboflow_MCP
npm install
npm run buildSet your Roboflow API key as an environment variable:
export ROBOFLOW_API_KEY="your_api_key_here"Optional environment variables:
Variable | Description | Default |
| Your Roboflow API key (required) | -- |
| Override the base API URL |
|
| Default workspace ID | API key owner's workspace |
Add this to your Claude Code MCP settings (~/.claude/settings.json or project-level .claude/settings.json):
{
"mcpServers": {
"roboflow": {
"command": "node",
"args": ["/absolute/path/to/Eusef_Roboflow_MCP/dist/index.js"],
"env": {
"ROBOFLOW_API_KEY": "your_api_key_here"
}
}
}
}Tool | Description |
| Check API connectivity and key validity |
| Search Universe for existing models and datasets |
| List projects in your workspace |
| List curated pre-trained APIs (OCR, people, PPE, etc.) |
Tool | Description |
| Create a model from a natural language prompt (no training data needed) |
Tool | Description |
| Run object detection or segmentation on an image |
| Run classification on an image |
Tool | Description |
| List available Workflows in a workspace |
| Execute a Workflow pipeline |
Tool | Description |
| Upload an image to a project dataset |
npm testWatch mode for TypeScript compilation:
npm run devStart the server directly:
npm startMIT
Check Roboflow API connectivity and key validity. Use as a first call to verify setup.
Inputs: no named parameters.
Run classification inference on a Roboflow model. Returns top-K class predictions with confidence scores.
Inputs: image (required), model_id (required), top_k.
Run object detection or segmentation inference on a Roboflow model. Accepts image as URL, base64, or local file path.
Inputs: image (required), model_id (required), format, overlap, +1 more.
List Roboflow's curated pre-trained APIs for common vision tasks (OCR, people detection, PPE, license plates, etc.). These are production-ready, zero-setup endpoints.
Inputs: task.
List projects in the authenticated Roboflow workspace.
Inputs: workspace.
Create a model using Roboflow Rapid (prompt-based, no training data required). Describe what to detect in natural language.
Inputs: prompt (required), project_name (required), workspace.
Search Roboflow Universe for existing models and datasets. Use before building a custom model to check if a solution already exists.
Inputs: query (required), type, limit.
Upload an image to a Roboflow project dataset for training. Specify the dataset split (train/valid/test).
Inputs: image (required), project_id (required), tag, split, +1 more.
List available Roboflow Workflows in a workspace.
Inputs: workspace.
Execute a Roboflow Workflow. Workflows chain multiple models and logic steps into a single pipeline.
Inputs: image (required), workflow_id (required), workspace, parameters.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 10 tools
Each tool targets a distinct operation: status checking, searching, listing different resource types, creating via Rapid, running different inference types, executing workflows, and uploading images. The only potential overlap between inference_run and inference_classify is clearly differentiated by model task type.
All tools share the 'roboflow_' prefix, but the suffix pattern is inconsistent: some use noun_verb (universe_search, inference_run), some use noun_noun (project_list, api_status), and one uses verb_noun (upload_image). This mix of patterns makes it less predictable than a uniform convention.
With 10 tools, the server is well-scoped, covering the core Roboflow workflows without being bloated. Each tool serves a clear purpose and the count fits the intended functionality.
The set covers discovery, inference, workflow execution, and data upload, but lacks project management operations like create/update/delete project or dataset. This creates notable gaps for users who need to set up new projects outside of Rapid creation.
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 Mercado Pago MCP Server implements the Model Context Protocol to provide AI agents and LLMs with access to Mercado Pago's APIs and tools within compatible development environments. It acts as an intermediary that translates Mercado Pago resources into executable functions (tools) that AI applications can invoke to perform actions and automate flows. The server simplifies integration, enables using documentation to implement or improve code, and optimizes operations through natural language interactions without manual implementations.
MCP server for building and testing AI agents with multi-model experimentation and insights.
