MCP server · Driver

driver-mcp

One-click install for Cursor, VS Code, Claude, and 20+ other MCP clients, powered by API Commons MCP Install — visit install.apicommons.org for more information.

Provider: Driver Type: Hosted endpoint Transport: http Host: api.us1.driverai.com

Endpoint

https://api.us1.driverai.com/mcp/v1

Hosted endpoint · transport http

Connect

This is a remote MCP server — point an MCP client at the endpoint URL. Clients with native remote support (Claude, Cursor, VS Code, …):

# mcp client config (e.g. .mcp.json / mcp settings) { "mcpServers": { "driver": { "url": "https://api.us1.driverai.com/mcp/v1" } } }

For stdio-only clients (older Claude Desktop, etc.), bridge with mcp-remote:

# Add to claude_desktop_config.json { "mcpServers": { "driver": { "command": "npx", "args": ["-y", "mcp-remote", "https://api.us1.driverai.com/mcp/v1"] } } }

If the server requires authentication, add the provider's token/header (e.g. an X-API-Key) per its docs. A quick reachability check:

curl -i -X POST https://api.us1.driverai.com/mcp/v1 \ -H "Content-Type: application/json" -H "Accept: application/json, text/event-stream" \ -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'

Tools

gather_task_context — Runs a specialized context agent that reads architecture docs and synthesizes high-signal context tailored to a specific task.
get_codebase_names — Returns all codebases available in your Driver organization for use with other tools.
get_branches — Returns all branches for a codebase that have completed documentation.
get_architecture_overview — Provides a comprehensive architecture document covering system structure, key components, and design patterns.
get_llm_onboarding_guide — Delivers a guide optimized for AI agents covering navigation tips and coding conventions.
get_changelog — Returns a high-level development timeline organized by year and month.
get_detailed_changelog — Provides detailed commit-level information for a specific month.
get_code_map — Explores directory structure with pre-computed descriptions of file and directory purposes.
get_file_documentation — Returns symbol-level documentation for a specific file including functions and classes.
get_source_file — Returns actual source code with line numbers for implementation details.
get_related — Surfaces code dependencies via a type-aware symbol table across Python, JavaScript, TypeScript, Java, and Rust.
get_registered_content_list — Lists all registered content documents accessible to the user.
fetch_registered_content — Retrieves the full content of a registered document by name.
register_content — Registers new content documents, supporting both static and auto-updating types.
remove_registered_content — Permanently deletes a registered content document.

About MCP

The Model Context Protocol (MCP) is an open protocol Anthropic introduced for connecting LLM-based agents to external tools and data sources. Providers publish MCP servers that expose their API surface as structured, discoverable tools — an MCP-compatible client (Claude Desktop, Cursor, Cline, Continue, etc.) can connect to the server and call its tools without any per-provider integration code.

Browse every MCP server on the APIs.io network or compare with the broader Agent Skill surfaces of the same providers.