MCP server · Arga Labs

arga-context

Open endpoint → Arga Labs provider profile

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: Arga Labs Type: Hosted endpoint Transport: http Host: api.argalabs.com

Endpoint

https://api.argalabs.com/mcp

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": { "arga-labs": { "url": "https://api.argalabs.com/mcp" } } }

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

# Add to claude_desktop_config.json { "mcpServers": { "arga-labs": { "command": "npx", "args": ["-y", "mcp-remote", "https://api.argalabs.com/mcp"] } } }

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.argalabs.com/mcp \ -H "Content-Type: application/json" -H "Accept: application/json, text/event-stream" \ -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'

Tools

create_sandbox_run — Create a sandbox run that deploys app code plus selected twins.
get_sandbox_run — Fetch sandbox status, app URL, twin URLs, and environment variables.
create_twin_run — Create a standalone twin run on the current /twin-runs API.
get_twin_run — Fetch twin-run status, URLs, environment variables, and seed details.
create_test_run — Create an ad hoc browser test run on the current /test-runs API.
run_test — Run a saved browser test by ID.
get_test_run — Fetch test-run status, events, artifacts, and summary fields.
list_tests — List saved browser tests.
get_twin_catalog — List all available digital twin types that can be provisioned.
list_connected_sources — List all tool sources you have connected (GitHub, Slack, Jira, etc.).
investigate_bug — Investigate a bug by searching all connected sources and tracing the root cause.
search_context — Search for context across all connected tools using natural language.
get_source_detail — Fetch a specific record from a connected source by its identifier.
search_github — Search GitHub pull requests, issues, and code.
search_linear — Search Linear issues.
search_slack — Search Slack messages and threads.
search_sentry — Search Sentry issues.
search_grafana — Search Grafana dashboards or alerts.
search_posthog — Search PostHog exceptions or run a HogQL query.

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.