{"slug": "localcloud-mcp-local-cloud-workflows-for-coding-agents", "title": "LocalCloud MCP: local cloud workflows for coding agents", "summary": "LocalGCloud released LocalCloud CLI 0.1.9 with an MCP bridge that gives coding agents a free local Google Cloud environment for building, testing, and debugging applications, requiring Docker and runtime 0.1.5 or newer for validated strict-client tool schemas. The packaged example, run with mcp==2.0.0 and the Google Cloud Python SDKs, passed all nine checks covering Cloud Storage upload and read-back, Pub/Sub publish-pull-verify-acknowledge, and a BigQuery SELECT 1 query, then cleaned up only its uniquely named resources. The tool exposes localcloud_list_services, localcloud_check_readiness, and localcloud_get_env so agents use returned local endpoints and SDK settings instead of real cloud credentials.", "body_md": "# A local cloud environment for coding agents\n\nGive your coding agent a free local cloud environment to build, test, and debug Google Cloud applications. MCP supplies the services, SDK settings, and diagnostics; your application runs its integration tests against the local runtime.\n\n## Install and connect\n\nInstall **LocalCloud CLI 0.1.9 or newer** and have Docker running. Use runtime **0.1.5 or newer** for validated strict-client tool schemas. On macOS, or Linux with Homebrew:\n\n```\nbrew install LocalGCloud/tap/localcloud\nlc --version\nlc doctor\nlc mcp install --client cursor\n```\n\nReload Cursor and enable `localcloud`. The bridge starts or reuses your local runtime automatically. The [client guide](https://local.cloud/docs/mcp/) also covers Claude Code/Desktop, Codex, VS Code, Cline, Gemini CLI, Antigravity, and Windsurf, plus installation without Homebrew.\n\n## Give the agent a task\n\nAsk for a small test with observable results:\n\n```\nUse LocalCloud MCP to list local services, check readiness, and obtain SDK settings.\nCheck compatibility before writing a small Cloud Storage, Pub/Sub, and BigQuery integration test.\nUse only the returned local endpoints and uniquely named test resources.\nAssert the actual results and clean up only resources created by the test.\nStop if a required operation is unavailable; do not fall back to real Google Cloud.\n```\n\nThe agent starts with `localcloud_list_services`, `localcloud_check_readiness`, and `localcloud_get_env`. Returned SDK settings account for the runtime's actual port mappings, so the test does not guess endpoints or request real cloud credentials.\n\n## Three cloud workflows\n\n1. **Cloud Storage:** create a uniquely named bucket, upload a known string, read it back, and check the exact content.\n2. **Pub/Sub:** create a topic and subscription, publish a known message, pull and verify its bytes, then acknowledge it.\n3. **BigQuery:** run`SELECT 1 AS mcp_smoke` and check that the result contains exactly one row with value 1.\n\nThese assertions exercise application behavior through standard Google Cloud SDKs. The example removes its own bucket, topic, and subscription in cleanup. [Read the workflow guide](https://github.com/LocalGCloud/localcloud-cli/blob/main/docs/mcp-workflows.md) for individual agent prompts.\n\n## Run the example\n\nStart an independent runtime for the three services. Dynamic ports allow it to run beside your everyday environment:\n\n```\nlc start --image agentcloud/localcloud:0.1.5 \\\n  --data-volume localcloud-mcp-demo \\\n  --services gcs,pubsub,bigquery --local-only --accept-dynamic-ports\n```\n\nFrom the public CLI repository, run the example with its optional Python SDK dependencies using [uv](https://docs.astral.sh/uv/):\n\n```\ngit clone https://github.com/LocalGCloud/localcloud-cli.git\ncd localcloud-cli\nuv run --with mcp==2.0.0 --with google-cloud-storage \\\n  --with google-cloud-pubsub --with google-cloud-bigquery \\\n  examples/mcp_workflows.py --data-volume localcloud-mcp-demo\n```\n\nThe demonstrated result through CLI 0.1.9 and the full packaged runtime 0.1.5 candidate was:\n\n```\nPASS MCP: localcloud_list_services\nPASS MCP: localcloud_check_readiness\nPASS MCP: localcloud_check_compatibility\nPASS MCP: localcloud_get_diagnostics\nPASS MCP: SDK configuration validates against its output schema\nPASS MCP: BigQuery query returns the expected row\nPASS Cloud Storage: upload and read back the exact content\nPASS Pub/Sub: publish, pull, verify, and acknowledge\nPASS BigQuery: SELECT 1 returns the expected row\nCleanup complete: only uniquely named example resources were removed\n```\n\nWhen finished, use `lc stop --data-volume localcloud-mcp-demo` to stop the example runtime. Its named volume remains available for reuse.\n\n## Diagnose a failure\n\nGive the agent the failing assertion and ask it to inspect readiness, diagnostics, and recent requests before changing the test. A service can be present in the catalog while disabled in the running environment; use its current readiness and compatibility records.\n\nIf an existing runtime predates 0.1.5, follow the [runtime upgrade and troubleshooting instructions](https://local.cloud/docs/mcp/). Updating the CLI or installing another client configuration does not replace an existing container.\n\n## Local data and verification\n\nThe SDK workflows above passed through a published macOS ARM64 CLI and a full Linux ARM64 runtime image, without mounted source or JAR overlays. This local evidence is separate from Google Cloud production parity and verification on every platform.\n\nUse test-owned resources and explicit cleanup. The default data volume is shared; a logical project is not a security boundary between agents. Choose a separate named volume when you need an independent runtime. MCP management writes and destructive actions require explicit runtime permission settings.\n\n[MCP setup guide](https://local.cloud/docs/mcp/) · [More SDK examples](https://local.cloud/docs/sdk-examples/) · [CLI source and releases](https://github.com/LocalGCloud/localcloud-cli)", "url": "https://wpnews.pro/news/localcloud-mcp-local-cloud-workflows-for-coding-agents", "canonical_source": "https://local.cloud/blog/localcloud-mcp-agent-cloud/", "published_at": "2026-10-09 14:26:43+00:00", "updated_at": "2026-10-09 14:54:42.014623+00:00", "lang": "en", "topics": ["ai-agents", "agent-protocols", "developer-tools", "ai-tools", "ai-infrastructure"], "entities": ["LocalGCloud", "LocalCloud CLI", "LocalCloud MCP", "Cursor", "Google Cloud", "Cloud Storage", "Pub/Sub", "BigQuery"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/localcloud-mcp-local-cloud-workflows-for-coding-agents", "markdown": "https://wpnews.pro/news/localcloud-mcp-local-cloud-workflows-for-coding-agents.md", "text": "https://wpnews.pro/news/localcloud-mcp-local-cloud-workflows-for-coding-agents.txt", "jsonld": "https://wpnews.pro/news/localcloud-mcp-local-cloud-workflows-for-coding-agents.jsonld"}}