Terradev is answering right now. Last checked 10 min ago. 724 installs a week from pypi. It exposes 277 tools.
Cross-cloud GPU orchestration CLI.
The linked repository no longer exists on GitHub — it was deleted or made private.
Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 29 September 2026. No other catalogue keeps this.
We read the source, 51 d ago · tools taken from the live server · rules 3dff92dd89df
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.
proc = subprocess.run(cmd, env=run_env, capture_output=True, text=True)
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}"
"http://169.254.169.254/latest/meta-data/spot/termination-time",
result = subprocess.run(
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.
proc = subprocess.Popen(
return os.path.join(self.config.manifest_dir, f"{self.config.cycle_id}.json")
env = {**dict(os.environ), **self.env}
mountPath: /var/run/docker.sock
ssh_key_path = os.path.expanduser("~/.ssh/id_rsa.pub")
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.
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.
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.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 10 min ago.
claude mcp add terradev --transport sse https://terradev-mcp.terradev.cloud/sse
https://terradev-mcp.terradev.cloud/sse
[mcp_servers.terradev]
url = "https://terradev-mcp.terradev.cloud/sse"
{
"mcpServers": {
"terradev": {
"url": "https://terradev-mcp.terradev.cloud/sse"
}
}
}
{
"servers": {
"terradev": {
"type": "sse",
"url": "https://terradev-mcp.terradev.cloud/sse"
}
}
}
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
agent_agentic_serving_configure
agent_agentic_serving_helm_values
agent_agentic_serving_k8s
agent_agentic_serving_launch_args
agent_agentic_serving_lmcache_env
agent_agentic_serving_show_config
agent_cost
agent_deploy
agent_langchain_create_langgraph
agent_langchain_create_pipeline
agent_langchain_create_workflow
agent_langchain_test
agent_langgraph_create_workflow
agent_langgraph_deploy
agent_langgraph_status
agent_langgraph_test
agent_letta_chat
agent_letta_create
agent_letta_delete
agent_letta_list
agent_letta_remember
agent_letta_status
agent_list
agent_mem0_add
agent_mem0_configure
agent_mem0_delete
agent_mem0_forget
agent_mem0_get
agent_mem0_list
agent_mem0_search
agent_mem0_test
agent_mem0_update
agent_plan
agent_scale
agent_skill_attach
agent_skill_init
agent_status
agent_teardown
agent_vector_db_down
agent_vector_db_up
ml_vllm_lora_link
ml_vllm_lora_list
ml_vllm_lora_load
ml_vllm_lora_sync
ml_vllm_lora_unload
vllm_analyze
vllm_auto_optimize
vllm_benchmark
vllm_inference
vllm_info
vllm_sleep
vllm_start
vllm_stop
vllm_wake
langfuse_configure
langfuse_datasets
langfuse_export_training_data
langfuse_k8s
langfuse_otel_env
langfuse_quality
langfuse_score
langfuse_scores
langfuse_test
langfuse_trace
langfuse_traces
train
train_detect_stragglers
train_monitor
train_resume
train_snapshot
train_status
train_stop
train_unsloth_run
train_unsloth_start
train_unsloth_stop
wandb_create_dashboard
wandb_create_report
wandb_create_terradev_alerts
wandb_create_terradev_dashboard
wandb_create_terradev_report
wandb_dashboard_status
wandb_list_projects
wandb_list_runs
wandb_run_details
wandb_setup_alerts
database_weaviate_create_collection
database_weaviate_delete_collection
database_weaviate_hybrid_search
database_weaviate_insert
database_weaviate_list_collections
database_weaviate_query
database_weaviate_up
get_database_connection
query_database
karpenter_create_nodepool
karpenter_delete_nodepool
karpenter_events
karpenter_gpu_nodes
karpenter_install
karpenter_logs
karpenter_nodepools
karpenter_resources
karpenter_status
inferx_configure
inferx_delete
inferx_deploy
inferx_list
inferx_optimize
inferx_quote
inferx_status
inferx_usage
k8s_create
k8s_destroy
k8s_device_plugin
k8s_gpu_operator_install
k8s_info
k8s_list
k8s_mig_configure
k8s_time_slicing
ray_disagg_pd_deploy
ray_list_jobs
ray_parallelism_strategy
ray_start
ray_status
ray_stop
ray_submit_job
ray_wide_ep_deploy
secrets_env
secrets_get
secrets_list
secrets_remove
secrets_run
secrets_set
secrets_sync
secrets_verify
phoenix_k8s
phoenix_otel_env
phoenix_projects
phoenix_snippet
phoenix_spans
phoenix_test
phoenix_trace
governance_compliance_report
governance_evaluate_opa
governance_move_data
governance_movement_history
governance_record_consent
governance_request_consent
ollama_chat
ollama_generate
ollama_list
ollama_model_info
ollama_ps
ollama_pull
orchestrator_evict
orchestrator_infer
orchestrator_load
orchestrator_register
orchestrator_start
orchestrator_status
qdrant_collections
qdrant_count
qdrant_create_collection
qdrant_info
qdrant_k8s
qdrant_test
checkpoint_delete
checkpoint_list
checkpoint_promote
checkpoint_restore
checkpoint_save
environments_approve
environments_create
environments_history
environments_list
environments_promote
lineage_checkpoint
lineage_diff
lineage_export
lineage_graph
lineage_trace
migrate_compare
migrate_execute
migrate_plan
migrate_rollback
migrate_status
preflight
preflight_gpu_check
preflight_network_check
preflight_provision
preflight_report
triggers_create
triggers_enable
triggers_execute
triggers_history
triggers_list
deepeval_evaluate
deepeval_init
deepeval_metrics
deepeval_run
dvc_diff
dvc_push
dvc_stage_checkpoint
dvc_status
hf_create_endpoint
hf_delete_endpoint
hf_endpoint_infer
hf_endpoint_info
guardrails_chat
guardrails_generate_config
guardrails_k8s
guardrails_test
langgraph_create_workflow
langgraph_evaluation_workflow
langgraph_orchestrator_worker
langgraph_workflow_status
sglang
sglang_inference
sglang_start
sglang_stop
cost_analyze
cost_optimize_recommend
cost_simulate
infer_failover
infer_route
infer_route_disagg
kserve_generate_yaml
kserve_list
kserve_status
lora_add
lora_list
lora_remove
mlflow_list_experiments
mlflow_log_run
mlflow_register_model
price_intel
price_spot_risk
price_trends
egress_cheapest_route
egress_optimize_staging
hf_hardware_compare
hf_hardware_recommend
langchain_create_sglang_pipeline
langchain_create_workflow
hf_space_deploy
hf_space_status
training_config_generate
training_launch_distributed
warm_pool_start
warm_pool_status
active_context
analytics
kv_cache_efficiency
configure_provider
hf_list_datasets
hf_list_endpoints
gpu_topology
helm_generate
local_scan
manage_instance
manifests
hf_model_info
hf_list_models
moe_deploy
optimize
create_postgresql_connection
provision_gpu
quote_gpu
rollback
setup_provider
hf_smart_template
create_sqlite_connection
stage
status
up
upsert_database
run_workflow
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://terradev-mcp.terradev.cloud/sse | sse | answering | 877 ms | 10 min ago |
LLM Orchestration Agent
LLM Orchestration Traced Agent
LLM Orchestration Agent 2
LLM Orchestration Agent (Cryptography)
LLM Orchestration Agent (Mcp)
LLM Orchestration MCP Agent
LLM Orchestration JWT Agent
LLM Orchestration Agent (Openai)
Answers built from our own checks of this server.