Ramp Developer MCP Server
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., "@Ramp Developer MCP Server How do I authenticate with the Ramp API?"
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.
Ramp Developer MCP Server
A local Model Context Protocol (MCP) server that provides AI assistants with access to Ramp's developer documentation, API schemas, and development guidance. This server enables natural language queries about Ramp's API endpoints, authentication methods, data relationships, and implementation patterns. Built specifically for developers building on Ramp's platform, it serves as an intelligent companion for API integration and development workflows. The server runs locally and processes Ramp's comprehensive developer documentation to provide contextual, accurate responses about API usage and best practices.
Example Queries and Use Cases
API Development
"How do I authenticate with the Ramp API?"
"Show me the schema for the cards endpoint"
"What are the required fields for creating a new user?"
"How do I handle rate limiting in the Ramp API?"
Data Relationships
"How are cards related to users in the API?"
"What's the relationship between transactions and bills?"
"Show me how to link a purchase order to a bill"
Implementation Guidance
"What are the best practices for handling webhooks?"
"How do I implement single-use card creation?"
"What scopes do I need for bill management?"
"How should I structure pagination for large datasets?"
Troubleshooting
"Why am I getting a 403 error on the users endpoint?"
"What's the proper format for monetary values?"
"How do I debug failed API requests?"
Related MCP server: OwlPay MCP Server
Available Tools
Core Tools
ping- Test server connectivity and healthsearch_documentation- Search through Ramp's developer documentation for specific topics, endpoints, or conceptsget_endpoint_schema- Retrieve detailed OpenAPI schema information for specific Ramp API endpointssubmit_feedback- Submit feedback about the MCP server or Ramp API development experience
Documentation Coverage
The server includes comprehensive documentation for:
Authentication & Authorization - OAuth flows, API keys, scopes
API Endpoints - Cards, users, bills, transactions, transfers, and more
Data Relationships - How different Ramp entities connect
Rate Limiting - Request limits and best practices
Webhooks - Event handling and security
Error Handling - Common errors and debugging approaches
Monetary Values - Proper formatting and precision
Pagination - Handling large result sets
Category Codes - Spending categories and classifications
How to Use
Prerequisites
Python 3.8+ with
uvpackage managerMCP-compatible client (Claude Desktop, Claude Code, or other MCP client)
Git for cloning the repository
Setup Instructions
Clone the repository:
git clone https://github.com/riker-t/ramp-dev-mcp.git cd ramp-dev-mcpInstall dependencies:
uv syncTest the server:
uv run python src/server.pyThe server should start and display initialization messages.
Claude Desktop Configuration
Locate your configuration file:
macOS:
~/Library/Application Support/Claude/claude_desktop_config.jsonWindows:
%APPDATA%\Claude\claude_desktop_config.json
Add the server configuration:
Option 1: Full path configuration (recommended):
{ "mcpServers": { "ramp-developer": { "command": "/Users/yourusername/.local/bin/uv", "args": [ "--directory", "/path/to/ramp-dev-mcp", "run", "src/server.py" ] } } }Option 2: Simple configuration (if
uvis in your PATH):{ "mcpServers": { "ramp-developer": { "command": "uv", "args": ["run", "python", "src/server.py"], "cwd": "/path/to/ramp-dev-mcp" } } }Configuration notes:
Replace
/path/to/ramp-dev-mcpwith the actual path where you cloned the repositoryReplace
/Users/yourusername/.local/bin/uvwith your actualuvinstallation pathTo find your
uvpath, run:which uvin your terminalIf
uvis not in your PATH, use the full path configuration
Restart Claude Desktop
Claude Code Configuration
# Navigate to your project directory
cd /path/to/ramp-dev-mcp
# Add the MCP server
claude mcp add ramp-developer uv run python src/server.py
# Start using it in your conversations
# The server will be automatically available in your Claude Code sessionsOther MCP Clients
For other MCP-compatible clients, configure them to run:
uv run python src/server.pyFrom the project directory.
Getting Started
Once configured, you can start asking questions like:
"How do I create a new card using the Ramp API?"
"What's the schema for the bills endpoint?"
"Show me documentation about webhook security"
"How do I handle rate limiting?"
The AI assistant will use the MCP server to search documentation, retrieve schemas, and provide accurate, contextual answers about Ramp API development.
Troubleshooting
Server fails to start:
Ensure Python 3.8+ is installed
Run
uv syncto install dependenciesCheck that you're in the correct directory
Configuration not working:
Verify the file path in your MCP client configuration
Ensure JSON syntax is correct
Restart your MCP client after configuration changes
Getting help:
Use the
submit_feedbacktool to report issuesCheck the console output for error messages
Ensure all dependencies are properly installed
Available Tools
4 toolsget_endpoint_schemaA
🎯 GET PRECISE ENDPOINT SCHEMA - Returns exact OpenAPI schema for specific endpoints.
Perfect for when you need:
• Exact request parameter names and types
• Response field names and structures
• Required vs optional parameters
• Related endpoints for the same use case
Example queries this replaces:
• "bills endpoint response schema fields amount vendor status" → Use this tool with /developer/v1/bills
• "API pagination limit page_size next cursor" → Get schema for any paginated endpoint
• "cards creation request parameters" → Use this tool with /developer/v1/cards
Usage: Provide an endpoint path (and optionally method) to get the complete technical specification.
Inputs: endpoint (required), method, include_related.
pingA
Test connectivity to the MCP server
Inputs: no named parameters.
search_documentationA
🔍 SMART DOCUMENTATION SEARCH - Finds the most relevant Ramp API documentation for your query.
What this does: • 🎯 Detects your intent from natural language queries • 📚 Searches through all Ramp documentation and guides • 🧠 Reasons about which content is most relevant • 📋 Returns clean, actionable markdown chunks
Perfect for: • Getting started with authentication • Understanding specific API workflows • Finding implementation examples • Troubleshooting integration issues
Usage: Just describe what you're trying to do naturally. Examples: "building an integration", "setting up OAuth", "bill payment workflow", "webhook events"
Inputs: query (required).
submit_feedbackB
Submit feedback to Ramp about the MCP server interface, tools, or problems you encounter. Helps improve the developer experience.
Inputs: feedback (required), tool_name.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
Each tool has a clearly distinct purpose with no overlap: get_endpoint_schema retrieves technical API specifications, ping tests connectivity, search_documentation finds documentation content, and submit_feedback collects user feedback. The descriptions explicitly differentiate their functions, eliminating any ambiguity in tool selection.
The naming conventions are mixed: get_endpoint_schema and search_documentation follow a verb_noun pattern, but ping is a single verb and submit_feedback uses a verb_noun structure. While all names are readable and descriptive, the inconsistency in style (e.g., ping vs. get_endpoint_schema) prevents a higher score.
With 4 tools, the count is reasonable for a developer-focused server, covering API schema retrieval, documentation search, connectivity testing, and feedback submission. It feels slightly thin for a full API integration suite but well-scoped for core developer assistance tasks, with each tool earning its place.
The tool set covers key developer needs like schema lookup and documentation search, but there are notable gaps for actual API interaction (e.g., no tools to create, update, or delete resources like bills or cards). This limits agents to informational tasks without execution capabilities, which may cause workarounds or failures in broader integration workflows.
Maintenance
Related MCP Connectors
Access and search Branch's official API documentation directly within any AI agent or client.
Publish your API docs so AI assistants can look up endpoints and call your API correctly.
Provides AI assistants with direct access to Mapbox developer APIs and documentation.
Versioned documentation registry and semantic search for AI tools and coding assistants.
Related MCP Servers
- AlicenseBqualityDmaintenanceProvides AI assistants with access to Payman's documentation, helping developers build integrations more efficiently through enhanced contextual support.5ISC
- AlicenseBqualityCmaintenanceEnables LLMs to search and retrieve OwlPay documentation directly through natural language queries. Accelerates system integration by providing instant access to OwlPay API documentation and guides.11MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI coding assistants to automatically scan, store, and query API endpoints from codebases, providing instant lookup and semantic search to reduce context switching and token consumption.1MIT
- AlicenseNot gradedqualityDmaintenanceProvides STORES API documentation to AI clients, enabling natural language queries about endpoints, authentication, and more.MIT