arga-context

Endpoint

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, …):

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

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

Tool quality observed · not scored

Unhinted state-changing: create_twin_run, create_test_run, run_test, start_url_validation, cancel_validation_run, cancel_run, delete_scenario_twin_environment

From an anonymous initialize + tools/list capture measured 2026-10-27; tokens are chars/3.6 of each tool definition. Recorded for the Kin Score's agent readiness as an observed signal — it contributes no points yet.

Tools

• list_connected_sources — List all tool sources the authenticated user has connected.
• investigate_bug — Investigate a bug or error by searching all connected sources and tracing the root cause.
• search_context — Search for context across connected tools using natural language.
• get_source_detail — Fetch a specific record from a connected source by its identifier.
• search_github — Search GitHub PRs, issues, and code for the authenticated user.
• search_linear — Search Linear issues for the authenticated user.
• search_slack — Search Slack messages and threads for the authenticated user.
• search_sentry — Search Sentry issues for the authenticated user.
• search_grafana — Search Grafana dashboards or alerts for the authenticated user.
• search_posthog — Search PostHog exceptions or run a HogQL query for the authenticated user.
• create_sandbox_run — Create a sandbox run that deploys app code plus selected twins. Provide either branch or pr_url. Use the returned sandbox_id with run_test or create_test_run via the sandbox_id parameter.
• get_sandbox_run — Get sandbox run status, app URL, twin URLs, and environment variables.
• create_twin_run — Create a twin run that deploys and optionally seeds one or more twins. Use scenario_prompt to generate seed data. Fast is the default; choose thorough for complex requirements when a longer wait is acceptable. A scenario_id reuses saved seed data and ignores scenario_prompt and scenario_generation_mode.
• get_twin_run — Get twin run status, URLs, env vars, and seed details.
• create_test_run — Create an ad hoc test run. Use sandbox_id to run against a sandbox run. Use pr_url/repo/branch as metadata when the test run was triggered by a PR.
• run_test — Run a saved test by ID. For PR checks, pass pr_url/repo/branch and a ready sandbox_id or start_url.
• get_test_run — Get test run status, events, artifacts, and summary fields.
• list_tests — List saved tests, optionally filtered by repository.
• start_url_validation — Legacy alias: start a browser test run against a deployed URL. Prefer create_test_run for new MCP clients. Returns a run ID you can pass to get_validation_results to check progress. If the target app requires sign-in, provide the email and password for a test account on *your* app (not your Arga account). Optionally request digital twins (comma-separated, e.g. "slack,stripe,waterfall"). Optionally provide repo (owner/repo format) and branch to enable diff-aware test planning.
• get_validation_results — Legacy alias: get the status and step-by-step results of a validation run. Prefer get_test_run for new MCP clients. Poll this only after calling the deprecated start_url_validation tool. Terminal statuses are: complete, failed, cancelled. Non-terminal: queued, running. For non-terminal statuses, returns a short text status message. For terminal statuses, returns structured JSON with step-level results, pass/fail counts, and a human-readable summary — suitable for machine parsing.
• cancel_validation_run — Legacy alias: cancel a validation/environment run.
• cancel_run — Cancel a legacy validation/environment run. Test-run cancellation is not wired yet; this currently covers sandbox, twin, and legacy validation runs backed by the environment runner.
• get_twin_provision_status — Return quickstart twin provision status, URLs, and proxy token (when ready).
• reset_twins — Reset quickstart twins to their captured baseline seed state (in-place, no VM restart). This replays the baseline captured at provision time. For long-lived scenario environments, use reseed_scenario_twin_environment instead.
• extend_twins — Extend the TTL of a quickstart twin provision.
• teardown_twins — Tear down a quickstart twin provision immediately.
• ensure_scenario_twin_environment — Create or return the long-lived twin URLs for a saved scenario. twins: optional comma-separated twin names. If omitted, uses the scenario's saved twin list. public: whether stable `base_url`s should be callable without proxy auth.
• get_scenario_twin_environment — Get status and URLs for a scenario's long-lived twin environment.
• reseed_scenario_twin_environment — Reseed a ready long-lived scenario twin environment from its scenario config.
• delete_scenario_twin_environment — Tear down a scenario's long-lived twin environment.
• list_scenario_twin_environments — List all long-lived scenario twin environments for the authenticated user.
• get_twin_catalog — List all available digital twin types that can be provisioned. Returns the name, label, and kind of each twin. Use these names when calling provision_twins or start_url_validation.

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.

Work with this as data

Every MCP server here is available over the APIs.io API and to AI agents over MCP.

curl "https://apis.io/api/v1/mcp/arga-context"

curl "https://apis.io/api/v1/mcp?limit=25"