https://terradev-mcp.terradev.cloud/sse ↗
Cross-cloud GPU orchestration CLI.
Terradev is a remote MCP server published at terradev-mcp.terradev.cloud. It has been probed 6 times since 9/12/2026. It answered in 6 of them (100.0%), a near-uninterrupted record. Median response time is 896 ms, a delay an agent will notice. It exposes a broad tool surface of 245 tools. On the protocol side it still runs 2025-11-25 and has not moved to the newer spec.
Can an LLM agent pick the right tool here — names, descriptions and parameter clarity are assessed.
| Run | Era | Modern | ms | Legacy | ms | Versions |
|---|---|---|---|---|---|---|
| 2026-09-13 01:33:33 | Legacy | 400 | 800 | 200 | 803 | 2025-11-25 |
| 2026-09-12 23:31:36 | Legacy | 400 | 866 | 200 | 870 | 2025-11-25 |
| 2026-09-12 21:29:15 | Legacy | 400 | 956 | 200 | 896 | 2025-11-25 |
| 2026-09-12 19:27:29 | Legacy | 400 | 870 | 200 | 916 | 2025-11-25 |
| 2026-09-12 17:24:09 | Legacy | 400 | 1205 | 200 | 1205 | 2025-11-25 |
| 2026-09-12 15:21:42 | Legacy | 400 | 943 | 200 | 873 | 2025-11-25 |
tools/list structure, inputSchema validity, and a functional smoke test — the components of the 0-100 score.
Tools the server advertised in the latest measurement — measured, not catalog-claimed.
provision_gpuProvision GPU instances for optimal parallel efficiency
gpu_typestringrequiredcredentialsobjectpreflight_reportGenerate full preflight validation report with pass/warn/fail per check. Covers GPU drivers, CUDA, NCCL, RDMA, network, disk, and Docker.
credentialsobjectpreflight_gpu_checkGPU-specific preflight validation: NVIDIA drivers, CUDA version, GPU count, NCCL, NVLink topology, NCU stall-signature profiling, and adversarial config verification (V1-V3).
credentialsobjectpreflight_network_checkNetwork-specific preflight validation: RDMA availability, InfiniBand status, inter-node bandwidth, latency matrix, firewall rules.
credentialsobjectlocal_scanScan local machine and network for available GPU devices. Returns total VRAM pool for local-first provisioning.
credentialsobjectstatusView all instances and costs with state optimization
credentialsobjectmanage_instanceManage GPU instances (stop/start/terminate)
instance_idstringrequiredactionstringrequiredcredentialsobjectanalyticsGet cost analytics
credentialsobjectoptimizeFind cheaper alternatives for running instances
credentialsobjectsetup_providerGet setup instructions for a provider
providerstringrequiredcredentialsobjectconfigure_providerConfigure provider credentials
providerstringrequiredcredentialsobjecttrainLaunch distributed training on provisioned GPU nodes. Supports torchrun, deepspeed, accelerate, and megatron. Use from_provision='latest' to auto-resolve node IPs from your last provision command.
scriptstringrequiredcredentialsobjectEach block is one measurement round. Green: working response. Amber: responded but the server was returning errors (5xx). Red: no response at all.
Each cell is one probe run. Faded cells are incomplete probes — one leg did not answer, so the era is inconclusive.
The two probe legs separately: modern server/discover and legacy initialize.
Derived by comparing consecutive probes — changes in era, protocol version, build and reachability.
Add this badge to your README — it updates automatically as measurements change.
[](https://mcpmetrics.io/servers/io-github-theoddden-terradev)<a href="https://mcpmetrics.io/servers/io-github-theoddden-terradev"><img src="https://mcpmetrics.io/badge/io.github.theoddden/terradev/era.svg" alt="mcpmetrics"></a>You are seeing the last 7 days. Sign up for the full history. Which check failed and why is in the dashboard.
Sign up free to seeThe catalog entries whose name and description are closest to this one, found with the same index the search box uses.
UNVERIFIED: cross-cloud beta; sandbox by default; production opt-in via customer Guardian.
Graph memory for AI agents: entities, cause-effect links, cross-session recall, time travel.
Simulate the cloud without the cloud. Try 6 cloud simulation and chaos-engineering tools instantly. Authenticate with an API key to unlock all 53 tools. Simulate AWS, Azure, GCP, and OCI infrastructure without provisioning real cloud resources. Create cloud simulations, inject traffic and failures, step through infrastructure behavior, and inspect performance, health, cost, and system metrics before deploying anything to a real cloud. The full authenticated tool set includes architecture analysis, optimization, prediction, reinforcement learning, chaos engineering, and multi-cloud capabilities. Features * Simulate AWS, Azure, GCP, and OCI infrastructure * Start with built-in cloud architecture scenarios * Inject traffic and simulate workload spikes * Inject infrastructure failures and observe their impact * Step simulations and inspect changing system behavior * Analyze latency, CPU, throughput, error rate, cost, and resource health * Unlock all 51 tools with a Cloud World Model A
Deploy, pay for and manage apps on Flux Cloud, the decentralized cloud. Prices in USD.
Manage Kubernetes clusters, deployments, databases, secrets and observability on Mengi Cloud.
European cloud hosting. Deploy and manage apps with your favorite AI coding assistant.
Comments
Sign in to write a comment
No comments yet. Be the first.