SoftProbe MCP Server
An MCP server for managing API test data and resources.
SoftProbe MCP Server
A Model Context Protocol (MCP) server implementation for managing API test data and resources.
Overview
This server implements the MCP protocol to provide a structured way to access and manage API test data. It uses a hierarchical organization model where resources are scoped under organizations and applications.
Current Implementation
This server currently implements MCP using Tools (as Resources and Roots are not yet supported by Cursor). The server provides the following tools:
- list-APIs: Lists all recorded APIs available in Softprobe
- list-api-record-ids: Lists all recorded API records for a specific operation
- getApiSamples: Retrieves recorded API interaction samples in JSON format
Configuration
The server can be configured using environment variables or through the mcp.json configuration file:
{
"mcpServers": {
"mcp-server-softprobe": {
"command": "npx",
"args": [
"-y",
"@softprobe/mcp-server"
],
"env": {
"SOFTPROBE_API_URL": "https://api-onpremise-gcp.softprobe.ai",
"SOFTPROBE_ACCESS_TOKEN": "<your-access-token>"
}
}
}
}
Required environment variables:
SOFTPROBE_API_URL: Base URL for the Softprobe APISOFTPROBE_ACCESS_TOKEN: Authentication token for API access
Future Architecture
Root Hierarchy
softprobe://orgs/{orgId}
└── softprobe://orgs/{orgId}/apps/{appId}
└── API Samples (resources)
- Organization Root: Represents a top-level organization
- Application Root: Represents an application within an organization
- API Samples: Test data resources scoped to specific applications
Resource Types
-
System Resources
resources/list: Lists available resourcesresources/read: Reads a specific resourceresources/subscribe: Subscribes to resource changesroots/list: Lists available root templatesroots/resolve: Resolves a specific root
-
API Sample Resources
softprobe://apiSamples/{orgId}/{appId}/{apiPath}: Access API test samples
Workflow
1. Root Discovery
// Client calls roots/list
// Server returns:
{
roots: [
{ uri: 'softprobe://orgs/{orgId}', name: 'Organization Root' },
{ uri: 'softprobe://orgs/{orgId}/apps/{appId}', name: 'Application Root' }
]
}
2. Root Resolution
// Client calls roots/resolve with:
// uri: softprobe://orgs/123
// Server returns:
{
root: {
uri: 'softprobe://orgs/123',
name: 'Organization Root'
}
}
3. Resource Access
// Client calls resources/list
// Server returns resources under org/123
// Client calls softprobe/apiSamples/123/456/users
// Server returns API samples for the users endpoint
4. Application Access
// Client calls roots/resolve with:
// uri: softprobe://orgs/123/apps/456
// Server returns:
{
root: {
uri: 'softprobe://orgs/123/apps/456',
name: 'Application Root'
}
}
// Now all resource access is scoped to app/456
API Sample Structure
{
samples: [
{
name: "test_case_name",
request: {
method: "POST",
body: { /* request body */ }
},
response: {
status: 200,
body: { /* response body */ }
}
}
]
}
Integration with Cursor IDE
The MCP server enables Cursor IDE to:
-
Organize Test Data
- Keep test data separate from production
- Organize tests by application/feature
- Maintain test data versioning
-
Test Case Management
- Access test cases through the resource system
- Subscribe to test case changes
- Monitor test data updates
-
Test Execution
- Retrieve test cases for validation
- Compare actual responses with expected
- Generate test reports
-
Environment Management
- Use different roots for different environments
- Maintain environment-specific test data
- Safe testing without affecting production
Development
Prerequisites
- Node.js v16 or higher
- TypeScript
Setup
npm install
npm run dev
Building
npm run build
Running
npm start
License
MIT
संबंधित सर्वर
Alpha Vantage MCP Server
प्रायोजकAccess financial market data: realtime & historical stock, ETF, options, forex, crypto, commodities, fundamentals, technical indicators, & more
Honeybadger
Interact with the Honeybadger API for error monitoring and reporting using LLMs.
Autodocument
Automatically generates documentation for code repositories by analyzing directory structures and code files using the OpenRouter API.
MCP Code Crosscheck
A server for bias-resistant AI code review using cross-model evaluation.
Dev/Infra
MCP server that gives LLMs full control over local Kubernetes dev environments via k3d, kubectl, Tilt, Helm, and kustomize
Lean LSP
Interact with the Lean theorem prover via the Language Server Protocol (LSP), enabling LLM agents to understand, analyze, and modify Lean projects.
MCP SSH Server
Securely execute remote commands and perform file operations over SSH, with support for both password and key-based authentication.
SAME (Stateless Agent Memory Engine
Your AI's memory shouldn't live on someone else's server — 12 MCP tools that give it persistent context from your local markdown, no cloud, no API keys, single binary.
symbolica-mcp
A scientific computing server for symbolic math, data analysis, and visualization using popular Python libraries like NumPy, SciPy, and Pandas.
Algorand
A comprehensive MCP server for tooling interactions(40+) and resource accessibility(60+) plus many useful prompts to interact with Algorand Blockchain.
MCP Agentic AI Crash Course with Python
A comprehensive crash course on the Model Context Protocol (MCP), covering everything from basic concepts to building production-ready MCP servers and clients in Python.