mcpbeat Sign in

Terradev MCP Server

answering

Terradev is answering right now. Last checked moments ago. 4 391 installs a week from pypi. It exposes 245 tools.

Cross-cloud GPU orchestration CLI.

The linked repository no longer exists on GitHub — it was deleted or made private.

Installs per day peak 3 056 · avg 604 · -47% w/w
a month agotoday
Uptime history 10 days of history · worst day 0%
10 days agonow
100.0%
Uptime 24h
92 of 92 checks
245
Tools
read from the server
917 ms
Response time
average over 24h
4 391
Installs / week
npm and PyPI

What the code does

We read the source, 6 d ago · tools taken from the live server · rules 3dff92dd89df

A tool parameter reaches a dangerous call

A value the model can set ends up inside a file or shell call. That is not a flaw by itself — for a terminal server it is the job — but it is where things go wrong when it is not.

A tool parameter reaches a dangerous call vault_set.provider → terradev_cli/mcp/new_feature_tools.py:599, deepeval_run.file → terradev_cli/commands/ml.py:2727, vault_run.command → terradev_cli/commands/vault.py:331 и ещё 9
            proc = subprocess.run(cmd, env=run_env, capture_output=True, text=True)
Evidence

Things with no honest explanation: a promise that contradicts the code, code that runs at install time while hiding what it does, data leaving the machine.

    dd_cmd = f"dd if=/dev/zero of={test_file} bs=1M count=256 oflag=direct 2>&1; rm -f {test_file}"
Runs commands and sends data out [пакет] terradev_cli/core/inference_spot_manager.py:152
            result = subprocess.run(
Capabilities

What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.

In the project's build, not in the package

Found in continuous integration, deployment or infrastructure files, or in a neighbouring package of the same monorepo. None of this is installed when you add the server: it describes how the project is built and released. We list it because a leaked key in a build pipeline is still a real problem, but it is not something this server does on your machine.

Builds a database query by concatenation helm/terradev/values.yaml:368
  type: RollingUpdate
  rollingUpdate:
    maxSurge: 25%
    maxUnavailable: 25%

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

A tool parameter here reaches a dangerous call

That is not a flaw by itself — but it is where things go wrong when it is not the job. We re-read this code on every release. Watch it and you hear from us the day another one appears.

Three servers free · no card

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 0 min ago.

run in your terminal
claude mcp add terradev --transport http https://terradev-mcp.terradev.cloud/sse
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "terradev": {
      "url": "https://terradev-mcp.terradev.cloud/sse"
    }
  }
}
~/.codex/config.toml
[mcp_servers.terradev]
url = "https://terradev-mcp.terradev.cloud/sse"
.cursor/mcp.json
{
  "mcpServers": {
    "terradev": {
      "url": "https://terradev-mcp.terradev.cloud/sse"
    }
  }
}
.vscode/mcp.json
{
  "mcpServers": {
    "terradev": {
      "url": "https://terradev-mcp.terradev.cloud/sse"
    }
  }
}

This one needs environment variables set before it will start: RUNPOD_API_KEY (RunPod API key — get at runpod.io/console/settings/api-keys), VAST_API_KEY (Vast.ai API key — get at console.vast.ai/api-keys), LAMBDA_API_KEY (Lambda Labs API key — get at cloud.lambdalabs.com/api-keys), HF_TOKEN (HuggingFace API token — get at huggingface.co/settings/tokens), AWS_ACCESS_KEY_ID (AWS access key ID (pair with AWS_SECRET_ACCESS_KEY)), AWS_SECRET_ACCESS_KEY (AWS secret access key), GOOGLE_APPLICATION_CREDENTIALS (Path to GCP service account JSON key file), TERRADEV_MCP_BEARER_TOKEN (Bearer token for SSE/remote transport mode (stdio mode does not require this)). The author declared them in the registry entry; get the values from the project itself.

Available tools 245

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

agent
agent_agentic_serving_configure
Configure agentic inference serving settings.
agent_agentic_serving_helm_values
Print Helm values for agentic inference deployment.
agent_agentic_serving_k8s
Print K8s deployment manifests for agentic inference.
agent_agentic_serving_launch_args
Print engine launch arguments for copy-paste.
agent_agentic_serving_lmcache_env
Print LMCache environment variables.
agent_agentic_serving_show_config
Show current agentic serving configuration.
agent_cost
Show real-time cost breakdown for a fleet by tier.
agent_deploy
Provision a heterogeneous agent fleet across all tiers simultaneously.
agent_langchain_create_langgraph
Create a LangGraph workflow.
agent_langchain_create_pipeline
Create an SGLang pipeline.
agent_langchain_create_workflow
Create a LangChain workflow.
agent_langchain_test
Test connection to LangChain service.
agent_langgraph_create_workflow
Create a LangGraph workflow.
agent_langgraph_deploy
Deploy a workflow.
agent_langgraph_status
Get workflow status.
agent_langgraph_test
Test connection to LangGraph service.
agent_letta_chat
Send a message to a Letta agent.
agent_letta_create
Create a new stateful Letta agent.
agent_letta_delete
Delete a Letta agent.
agent_letta_list
List Letta agents.
agent_letta_remember
Teach a Letta agent a durable fact.
agent_letta_status
Show the state of a Letta agent.
agent_list
List all known agent fleets.
agent_mem0_add
Store a memory in Mem0 for an agent or user.
agent_mem0_configure
Configure Mem0 credentials and defaults.
agent_mem0_delete
Delete a memory by ID.
agent_mem0_forget
Delete all memories matching an entity scope.
agent_mem0_get
Get a single memory by ID.
agent_mem0_list
List memories for an entity scope.
agent_mem0_search
Search agent/user memories.
agent_mem0_test
Test connection to Mem0.
agent_mem0_update
Update a memory by ID.
agent_plan
Plan a heterogeneous agent fleet without provisioning.
agent_scale
Scale a single fleet tier up or down without affecting other tiers.
agent_skill_attach
Attach a skill.md to a Letta agent as a durable memory block.
agent_skill_init
Create a skill.md template for an agent.
agent_status
Show live status of a fleet — tier health, KV hit rate, queue depth, cost.
agent_teardown
Terminate all fleet instances and remove fleet state.
agent_vector_db_down
Teardown a vector database provisioned for an agent fleet.
agent_vector_db_up
Provision a vector database for an agent fleet.
vllm
ml_vllm_lora_link
Load the active registry version of an adapter onto a vLLM server.
ml_vllm_lora_list
List LoRA adapters currently loaded on a vLLM server.
ml_vllm_lora_load
Hot-load a LoRA adapter onto a running vLLM server.
ml_vllm_lora_sync
Synchronize an adapter from the registry across multiple vLLM replicas.
ml_vllm_lora_unload
Hot-unload a LoRA adapter from a running vLLM server.
vllm_analyze
Analyze a running vLLM server's workload and return specific optimization recommendations with before/after comparisons.
vllm_auto_optimize
Automatically optimize vLLM configuration by analyzing workload patterns. Selects optimal settings for the 6 critical knobs based on live endpoint metrics or sample request files.
vllm_benchmark
Benchmark a vLLM endpoint with concurrent requests. Returns throughput (req/s), success rate, and total latency.
vllm_inference
Test inference against a running vLLM endpoint (completions or chat).
vllm_info
Get vLLM server info: loaded models, config, and health status.
vllm_sleep
Put a vLLM server to sleep. Level 1: offload to CPU (fast wake). Level 2: discard weights (minimal RAM).
vllm_start
Start a vLLM inference server on a remote instance via SSH/systemd. Supports Multi-LoRA, Sleep Mode, KV Offloading, Speculative Decoding.
vllm_stop
Stop a vLLM server on a remote instance.
vllm_wake
Wake a sleeping vLLM server. For Level 2 sleep, also reloads weights and resets prefix cache.
langfuse
langfuse_configure
Configure Langfuse credentials (public key, secret key, host URL).
langfuse_datasets
List Langfuse datasets for evaluation and fine-tuning.
langfuse_export_training_data
Export Langfuse traces as instruction/response pairs for LoRA fine-tuning. Filters by quality score.
langfuse_k8s
Generate Kubernetes deployment manifest for self-hosted Langfuse.
langfuse_otel_env
Print OTEL environment variables for instrumenting LLM apps to send traces to Langfuse.
langfuse_quality
Get aggregated quality metrics from Langfuse scores for drift detection.
langfuse_score
Create an evaluation score for a Langfuse trace (e.g. quality, accuracy, relevance).
langfuse_scores
List evaluation scores from Langfuse, optionally filtered by trace or score name.
langfuse_test
Test Langfuse connectivity and list accessible projects.
langfuse_trace
Get a single Langfuse trace with all observations/spans.
langfuse_traces
List recent LLM traces from Langfuse.
train
train
Launch 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.
train_detect_stragglers
Detect straggler nodes in distributed training. Identifies GPUs with significantly lower utilization that slow the whole job.
train_monitor
Real-time GPU monitoring for training jobs. Shows utilization, memory, temperature, power, and cost.
train_resume
Resume a training job from its latest checkpoint. Rebuilds config with topology revalidation.
train_snapshot
Get complete training monitoring snapshot: GPU metrics (utilization, memory, temp, power), training metrics (loss, grad_norm, lr, throughput), straggler detection, and cost estimate.
train_status
List all training jobs and their state (created, running, completed, failed).
train_stop
Stop a running training job. Kills training processes on all nodes in parallel.
train_unsloth_run
Run an Unsloth local model server.
train_unsloth_start
Start a coding agent backed by Unsloth's local model server.
train_unsloth_stop
Stop a running Unsloth server started with `unsloth run`.
wandb
wandb_create_dashboard
Create a custom W&B dashboard with GPU metrics, training loss, and cost panels.
wandb_create_report
Create a W&B report with custom sections, charts, and narrative text.
wandb_create_terradev_alerts
Auto-create standard Terradev alerts: GPU cost > budget, utilization < 50%, training loss spike, straggler detection.
wandb_create_terradev_dashboard
Auto-create a Terradev-specific W&B dashboard with GPU utilization, cost tracking, training metrics, and infrastructure panels.
wandb_create_terradev_report
Auto-generate a Terradev infrastructure report: GPU costs, provider comparison, training efficiency, and recommendations.
wandb_dashboard_status
Get comprehensive W&B monitoring overview: dashboards, reports, alerts, active runs.
wandb_list_projects
List all Weights & Biases projects for the configured entity.
wandb_list_runs
List runs in a W&B project with status, metrics summary, and config.
wandb_run_details
Get detailed info, metrics, and artifacts for a specific W&B run.
wandb_setup_alerts
Set up custom W&B alerts for GPU metrics: cost thresholds, utilization drops, training anomalies.
database
database_weaviate_create_collection
Create a Weaviate collection.
database_weaviate_delete_collection
Delete a Weaviate collection.
database_weaviate_hybrid_search
Hybrid vector + BM25 search in a Weaviate collection.
database_weaviate_insert
Insert objects into a Weaviate collection.
database_weaviate_list_collections
List Weaviate collections.
database_weaviate_query
Vector similarity search in a Weaviate collection.
database_weaviate_up
Initialize a Weaviate connection.
get_database_connection
Get information about a database connection including type, status, and configuration.
query_database
Execute a SELECT query on a database connection. Returns query results as a list of dictionaries.
inferx
inferx_configure
Configure InferX serverless platform credentials.
inferx_delete
Delete an InferX model deployment.
inferx_deploy
Deploy model to InferX serverless platform
inferx_list
List deployed InferX models
inferx_optimize
Get cost analysis for inference endpoints
inferx_quote
Get InferX pricing quotes for a GPU type.
inferx_status
Check InferX endpoint status
inferx_usage
Get InferX account usage statistics: requests, cost, GPU hours, latency.
k8s
k8s_create
Create Kubernetes cluster with GPU nodes for optimal multi-cloud deployment
k8s_destroy
Destroy a Kubernetes cluster
k8s_device_plugin
Configure Kubernetes GPU device plugin settings: time-slicing, MIG strategy, and resource naming.
k8s_gpu_operator_install
Install NVIDIA GPU Operator on a Kubernetes cluster. Configures driver containers, device plugin, DCGM exporter, and GPU Feature Discovery.
k8s_info
Get information about a specific cluster
k8s_list
List Kubernetes clusters
k8s_mig_configure
Configure Multi-Instance GPU (MIG) partitioning on A100/H100 GPUs. Splits a single GPU into isolated instances for multi-tenant workloads.
k8s_time_slicing
Configure GPU time-slicing for Kubernetes. Allows multiple pods to share a single GPU with configurable oversubscription.
ray
ray_disagg_pd_deploy
Generate a Ray Serve LLM disaggregated Prefill/Decode deployment. Splits inference into compute-bound prefill and memory-bound decode phases with KV cache transfer via NIXL.
ray_list_jobs
List all running Ray jobs and tasks.
ray_parallelism_strategy
Compute optimal TP/DP/EP parallelism strategy for a given MoE model and GPU count. Returns recommended configuration with rationale.
ray_start
Start a Ray cluster (head node or worker). For distributed ML training and inference.
ray_status
Get Ray cluster status including node count, resources, memory, and running jobs.
ray_stop
Stop the Ray cluster on the current node.
ray_submit_job
Submit a job script to the Ray cluster for distributed execution.
ray_wide_ep_deploy
Generate a Ray Serve LLM Wide-EP (Expert Parallel) deployment for MoE models. Returns Python script and config for distributed MoE serving with EPLB and DeepEP.
secrets
secrets_env
Print environment-style export lines for a provider. By default values are masked.
secrets_get
Retrieve a stored secret. By default the value is masked.
secrets_list
List stored provider and key names. Values are never shown.
secrets_remove
Remove a provider or a single key from the secret store.
secrets_run
Run a shell command with secrets injected into the environment.
secrets_set
Store a secret in the Terradev secrets store. Values are encrypted at rest.
secrets_sync
Import TERRADEV_* environment variables into the secret store for supported cloud providers.
secrets_verify
Check which providers are fully configured and which keys are missing.
phoenix
phoenix_k8s
Generate Kubernetes deployment manifest for self-hosted Arize Phoenix server.
phoenix_otel_env
Generate OpenTelemetry environment variables for instrumenting serving pods with Phoenix tracing.
phoenix_projects
List Phoenix projects (trace namespaces).
phoenix_snippet
Generate Python instrumentation snippet for adding Phoenix tracing to LLM applications.
phoenix_spans
List recent spans for a Phoenix project. Supports SpanQuery DSL filters like "span_kind == 'RETRIEVER'" or "status_code == 'ERROR'".
phoenix_test
Test connection to Arize Phoenix server. Returns collector endpoint and project count.
phoenix_trace
View full execution tree for a specific trace ID. Shows span hierarchy, latencies, and token counts.
governance
governance_compliance_report
Generate comprehensive compliance report: consent stats, policy evaluations, data movements, violations. For GDPR/SOC2/HIPAA audits.
governance_evaluate_opa
Evaluate OPA (Open Policy Agent) policies for data access. Checks region restrictions, classification rules, and compliance requirements.
governance_move_data
Move data with full governance audit trail. Requires prior consent and OPA policy approval. Tracks integrity, encryption, and compliance.
governance_movement_history
Get data movement audit log. Filter by user, dataset, or time range.
governance_record_consent
Record a consent response (granted or denied) for a pending consent request.
governance_request_consent
Request user consent for data movement across cloud regions. GDPR/SOC2 compliant consent tracking with audit trail.
ollama
ollama_chat
Chat with an Ollama model using the chat/completions API.
ollama_generate
Generate text using an Ollama model (non-chat completions).
ollama_list
List models available on an Ollama server.
ollama_model_info
Get detailed information about an Ollama model (parameters, template, license).
ollama_ps
List currently running Ollama models.
ollama_pull
Pull a model to an Ollama server on a remote instance.
orchestrator
orchestrator_evict
Evict a model from GPU memory.
orchestrator_infer
Test inference with a model via the orchestrator.
orchestrator_load
Load a model into GPU memory.
orchestrator_register
Register a model with the orchestrator.
orchestrator_start
Start the model orchestrator for multi-model GPU sharing with eviction policies.
orchestrator_status
Get orchestrator and model status including GPU memory utilization.
qdrant
qdrant_collections
List all Qdrant vector collections with their point counts and configurations.
qdrant_count
Count points (vectors) in a Qdrant collection.
qdrant_create_collection
Create a Qdrant vector collection. Auto-configures vector dimensions from embedding model name.
qdrant_info
Get detailed info and stats for a Qdrant collection.
qdrant_k8s
Generate Kubernetes StatefulSet manifest for self-hosted Qdrant vector database.
qdrant_test
Test connection to Qdrant vector database. Returns cluster info and collection count.
checkpoint
checkpoint_delete
Delete a checkpoint.
checkpoint_list
List all checkpoints for a training job.
checkpoint_promote
Promote a checkpoint to a final model path for serving.
checkpoint_restore
Restore a specific checkpoint for a training job.
checkpoint_save
Manually trigger a checkpoint save for a running training job.
deepeval
deepeval_evaluate
Evaluate a single LLM output with a DeepEval metric (AnswerRelevancy, Faithfulness, Hallucination, etc.).
deepeval_init
Generate a starter DeepEval test file.
deepeval_metrics
List available DeepEval metrics for LLM evaluation.
deepeval_run
Run a DeepEval test suite from a Python test file.
dvc
dvc_diff
Show DVC diff between two revisions (e.g. training checkpoints). Shows added, modified, deleted files.
dvc_push
Push DVC-tracked data to the configured remote storage.
dvc_stage_checkpoint
Atomic checkpoint staging: DVC add + push + git commit in one operation. Promotes a training checkpoint to versioned storage.
dvc_status
Get DVC repository status: tracked files, remotes, and changes since last commit.
endpoint
hf_create_endpoint
Create a HuggingFace Inference Endpoint (paid GPU endpoint). Supports custom GPU types, regions, and scaling.
hf_delete_endpoint
Delete a HuggingFace Inference Endpoint.
hf_endpoint_infer
Run inference on a HuggingFace Inference Endpoint. Supports text generation, embeddings, and custom inputs.
hf_endpoint_info
Get detailed info about a specific HuggingFace Inference Endpoint: status, URL, scaling config, cost.
guardrails
guardrails_chat
Send a message through NeMo Guardrails and return the safety-filtered response. Applies topical, jailbreak, PII, and factcheck rails.
guardrails_generate_config
Generate default Colang 2.x guardrails configuration files (topical, jailbreak, PII, factcheck rails).
guardrails_k8s
Generate Kubernetes deployment manifest for NeMo Guardrails server (standalone or sidecar mode).
guardrails_test
Test connection to NeMo Guardrails server.
langgraph
langgraph_create_workflow
Create a LangGraph stateful workflow with monitoring. Supports agent graphs, tool calling, and state persistence.
langgraph_evaluation_workflow
Create an evaluator-optimizer workflow in LangGraph. Generates outputs, evaluates quality, and iteratively improves.
langgraph_orchestrator_worker
Create an orchestrator-worker pattern workflow in LangGraph. The orchestrator delegates tasks to specialized worker agents.
langgraph_workflow_status
Get the status and metrics of a LangGraph workflow execution.
preflight
preflight
Pre-training validation: GPU availability, NCCL, RDMA, drivers across all nodes.
preflight_gpu_check
GPU-specific preflight validation: NVIDIA drivers, CUDA version, GPU count, NCCL, NVLink topology, NCU stall-signature profiling, and adversarial config verification (V1-V3).
preflight_network_check
Network-specific preflight validation: RDMA availability, InfiniBand status, inter-node bandwidth, latency matrix, firewall rules.
preflight_report
Generate full preflight validation report with pass/warn/fail per check. Covers GPU drivers, CUDA, NCCL, RDMA, network, disk, and Docker.
sglang
sglang
Complete SGLang optimization stack with workload-specific auto-tuning for 7 workload types: agentic chat, batch inference, low latency, MoE models, PD disaggregated, structured output, and RAG.
sglang_inference
[DEPRECATED] Use sglang action='inference' instead. Test inference against a running SGLang endpoint.
sglang_start
[DEPRECATED] Use sglang action='start' instead. Start an SGLang inference server on a remote instance.
sglang_stop
[DEPRECATED] Use sglang action='stop' instead. Stop an SGLang server on a remote instance.
cost
cost_analyze
Deep cost analysis of current GPU infrastructure: per-provider breakdown, utilization efficiency, waste identification, and optimization potential.
cost_optimize_recommend
Generate actionable cost optimization recommendations: spot migration, GPU right-sizing, provider arbitrage, idle shutdown, and density packing.
cost_simulate
Simulate cost optimization scenarios with ROI projections. Compare current vs optimized infrastructure costs.
infer
infer_failover
Run health checks and auto-failover for inference endpoints. If a primary endpoint is unhealthy and has a backup configured, traffic automatically shifts to the backup provider.
infer_route
Semantic-aware inference routing. Analyzes query content across 6 signal dimensions (modality, complexity, domain, language, safety, keywords), applies NUMA-aware endpoint scoring, and selects the optimal inference endpoint. Uses DAG parallel execution for signal extraction.
infer_route_disagg
Disaggregated Prefill/Decode routing (DistServe architecture). Splits LLM inference into compute-bound prefill phase (routed to FLOPS-optimized GPUs like H100 SXM) and memory-bound decode phase (routed to bandwidth-optimized GPUs like MI300X). Tracks KV cache handoffs between endpoint pairs.
kserve
kserve_generate_yaml
Generate a GPU-aware KServe InferenceService YAML manifest with NUMA pinning, resource limits derived from model size and VRAM, and topology hints.
kserve_list
List KServe InferenceServices in a Kubernetes namespace.
kserve_status
Get detailed status of a KServe InferenceService including readiness, traffic split, and URL.
lora
lora_add
Hot-load a LoRA adapter onto a running vLLM endpoint. The adapter becomes immediately available as a model name for inference requests. Uses vLLM's fused_moe_lora kernel for 454% higher output tokens/sec on MoE models.
lora_list
List LoRA adapters loaded on a running vLLM endpoint. Shows base models and hot-loaded fine-tuned adapters.
lora_remove
Hot-unload a LoRA adapter from a running vLLM endpoint. Frees GPU memory for other adapters.
mlflow
mlflow_list_experiments
List MLflow experiments on the configured tracking server.
mlflow_log_run
Log a Terradev training run to MLflow with auto-injected GPU type, provider, cost/hr, and duration as params.
mlflow_register_model
Register a trained model in the MLflow model registry with Terradev provenance tags.
price
price_intel
GPU price intelligence with quantitative analytics. Computes delta (rate of change), gamma (acceleration), and annualized realized volatility on GPU spot/on-demand prices across 21+ providers. Identifies cheapest time windows and provider arbitrage opportunities.
price_spot_risk
Spot instance risk assessment per provider. Returns interruption probability, mean time to interruption, and recommended mitigation.
price_trends
Get GPU price trend analysis with delta (rate of change), gamma (acceleration), and annualized volatility. Identifies cheapest time windows.
egress
egress_cheapest_route
Find the cheapest egress route between cloud providers/regions for model weights or dataset transfer. Supports multi-hop routing.
egress_optimize_staging
Optimize dataset or model staging across regions by finding the cheapest transfer plan. Integrates with the dataset stager for parallel uploads.
hardware
hf_hardware_compare
Compare all hardware options for a HuggingFace model. Returns side-by-side cost, performance, and compatibility analysis.
hf_hardware_recommend
Get hardware recommendation with cost breakdown for any HuggingFace model. Returns optimal GPU type, estimated cost, and performance score.
langchain
langchain_create_sglang_pipeline
Create an SGLang model-serving pipeline via LangChain. Connects LangChain agents to SGLang inference endpoints.
langchain_create_workflow
Create a LangChain workflow.
space
hf_space_deploy
Deploy model to HuggingFace Spaces
hf_space_status
Get HuggingFace Space deployment status.
training
training_config_generate
Generate a complete training configuration from a declarative spec. Auto-detects framework, sets optimal parallelism, and configures distributed training.
training_launch_distributed
Full distributed training launch with framework auto-detection, topology validation, and monitoring. Combines preflight + train + monitor in one operation.
warm
warm_pool_start
Start the warm pool manager for intelligent model pre-warming. 5 strategies: traffic_based, time_based, priority_based, cost_optimized, latency_optimized.
warm_pool_status
Get warm pool status: hit rate, cold starts, memory saved, cost saved.
active
active_context
Get current Terradev state: running training jobs, active instances, spend-to-date, alerts. Call this on session start to resume context from previous sessions.
analytics
analytics
Get cost analytics
configure
configure_provider
Configure provider credentials
datasets
hf_list_datasets
Search and browse HuggingFace Hub datasets. Filter by author and search query.
endpoints
hf_list_endpoints
List all active HuggingFace Inference Endpoints with status, URL, and cost.
gpu
gpu_topology
GPU NUMA topology report with intra-GPU XCD (Accelerated Compute Die) awareness. Models MI300X (8 XCDs, 192GB HBM3), MI300A (6 XCDs, 128GB), H200 (unified 141GB HBM3e), H100 (80GB). Reports PCIe locality (PIX/PXB/PHB/SYS), GPU-NIC pairing, SR-IOV VF status, and generates XCD-aware NCCL/AITER environment variables.
helm
helm_generate
Generate Helm charts from workload specifications.
local
local_scan
Scan local machine and network for available GPU devices. Returns total VRAM pool for local-first provisioning.
manage
manage_instance
Manage GPU instances (stop/start/terminate)
manifests
manifests
List cached manifests and versions for jobs.
model
hf_model_info
Get detailed model info: architecture, size, downloads, license, tags, pipeline_tag, and model card.
models
hf_list_models
Search and browse HuggingFace Hub models. Filter by author, task, library. Returns model ID, downloads, likes, and tags.
moe
moe_deploy
Deploy Mixture-of-Experts models with production-ready cluster templates. Auto-applies vLLM cost optimizations (KV cache offloading for up to 9x throughput, MTP speculative decoding for up to 2.8x speed, sleep mode for 18-200x faster restarts). Supports GLM-5, Qwen 3.5, Mistral Large 3, DeepSeek V4, Llama 5. Configures NVLink topology, tensor parallelism, FP8 quantization, vLLM/SGLang backends, and GPU-aware HPA autoscaling.
optimize
optimize
Find cheaper alternatives for running instances
postgresql
create_postgresql_connection
Create a PostgreSQL database connection with auto-table creation. Returns a connection ID for subsequent operations.
provision
provision_gpu
Provision GPU instances for optimal parallel efficiency
rollback
rollback
Explicit versioned rollback. Format: job@version (e.g., llama3@v3).
setup
setup_provider
Get setup instructions for a provider
smart
hf_smart_template
Auto-generate an optimized deployment template for any HuggingFace model. Analyzes model size, architecture, and quantization to select optimal hardware and generate ready-to-deploy configs.
sqlite
create_sqlite_connection
Create a SQLite database connection with auto-table creation. Returns a connection ID for subsequent operations.
stage
stage
Compress, chunk, checksum, and position datasets near compute. Supports local paths, S3/GCS URIs, HTTP URLs, and HuggingFace dataset names. Returns staging plan with agent recommendations.
status
status
View all instances and costs with state optimization
up
up
CLI-native provisioning with manifest cache and drift detection. Use --fix-drift to detect and auto-fix drifted infrastructure.
upsert
upsert_database
Insert or update data in a database table. Performs upsert operation (insert or update on conflict).
workflow
run_workflow
Run a declarative YAML workflow that chains multiple Terradev commands (provision → preflight → train → monitor → checkpoint). Returns step-by-step execution status with cost estimates and confirmation gates for expensive operations.

Endpoints

URLTransportStateLatencyChecked
https://terradev-mcp.terradev.cloud/sse sse answering 901 ms 0 min ago

Alternatives to Terradev

same job, measured the same way
Kilawatt MCP Server
by kilawattcloud

Kilawatt Cloud MCP Server for AI Agent GPU Orchestration

56 installs/wk local only
LLM Orchestration Agent D0a1a1
by getvda

LLM Orchestration Agent

2 tools answering
LLM Orchestration Traced Agent
by getvda

LLM Orchestration Traced Agent

2 tools answering
LLM Orchestration Agent 2 Df5979
by getvda

LLM Orchestration Agent 2

2 tools answering
LLM Orchestration Agent Cryptography
by getvda

LLM Orchestration Agent (Cryptography)

2 tools answering
LLM Orchestration Agent MCP
by getvda

LLM Orchestration Agent (Mcp)

2 tools answering
LLM Orchestration JWT Agent
by getvda

LLM Orchestration JWT Agent

2 tools answering
LLM Orchestration MCP Agent
by getvda

LLM Orchestration MCP Agent

2 tools answering

Terradev — questions

Answers built from our own checks of this server.

What can Terradev do?
It exposes 245 tools, read directly from the server on our last check. Among them: active_context, agent_agentic_serving_configure, agent_agentic_serving_helm_values, agent_agentic_serving_k8s, agent_agentic_serving_launch_args, agent_agentic_serving_lmcache_env and 239 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →
What is Terradev mostly used for?
Its tools cluster around agent, vllm and langfuse. That is what this server is built to work with — the grouping comes from the actual tool names, not from a category we assigned.
Is Terradev working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 92 of 92 checks got a reply (100.0%), average response time 917 ms. The bar chart above shows every period we have measured.
Is Terradev still maintained?
The linked repository no longer exists on GitHub — it was deleted or made private. We show this because it changes what you can expect: an unmaintained server may keep answering for months and then stop without warning.
How do I connect Terradev?
Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does Terradev need an API key?
No. Terradev completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 245 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is Terradev?
It answers our handshake in 917 ms on average, which is faster than 10% of all working MCP servers we measure. That is on the slow side — worth knowing if the tool sits inside an interactive loop. The comparison comes from our own checks across the whole registry, every 15 minutes.
How many people use Terradev?
The pypi package terradev-cli was installed 4 391 times in the last week. Week over week that is -47%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.