Terradev
PYPI · TERRADEV-CLI · 2 COMPONENTS · SCANNED SEP 20
Cross-cloud GPU orchestration CLI.
Available components
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security100
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- Runs setuptools.build_meta at install time, a recognised native-build step with no shell scripting around it. View diagnostics → Pass
- 2 of 63 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency19
- Repository check failed: the declared repository URL returned HTTP 404. See how to fix → View diagnostics → Fail
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (Apache-2.0).Pass
- Actively maintained (last published 10 days ago).Pass
- Security-disclosure policy not yet verified: we couldn't inspect the source repository.Unverified
Schema Quality & AI Usability79
- 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 27375 tokens (~109/item across 250 items; 245 tools + 5 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management80
- Stability check failed: the tool surface changed between 6.1.0 and 6.2.20: 35 tool removals, 0 breaking changes, 17 additions. See how to fix → Fail
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety75
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- 0 of 21 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "inferx_deploy" implies "deploy" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
- An AI judge read all 246 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
How do I install the Terradev MCP server?
Terradev runs locally as a PyPI package, launched with uvx terradev-cli. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
pypi · terradev-cli
claude mcp add theoddden-terradev -- uvx terradev-cli
{
"mcpServers": {
"theoddden-terradev": {
"command": "uvx",
"args": [
"terradev-cli"
]
}
}
} {
"servers": {
"theoddden-terradev": {
"command": "uvx",
"args": [
"terradev-cli"
]
}
}
} codex mcp add theoddden-terradev -- uvx terradev-cli
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"theoddden-terradev": {
"type": "local",
"command": [
"uvx",
"terradev-cli"
],
"enabled": true
}
}
} openclaw mcp add theoddden-terradev --command uvx --arg terradev-cli
mcp_servers:
theoddden-terradev:
command: "uvx"
args: ["terradev-cli"] {
"McpServers": {
"theoddden-terradev": {
"Transport": "stdio",
"Command": "uvx",
"Arguments": [
"terradev-cli"
]
}
}
} assistant mcp add theoddden-terradev -t stdio -c uvx -a terradev-cli
{
"mcpServers": {
"theoddden-terradev": {
"command": "uvx",
"args": [
"terradev-cli"
]
}
}
} Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 20 Sept 26 +14
- Malware scan: unverified → pass ▲ security
- 19 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 83 to 87.
- 18 Sept 26 −1
No change was recorded against any check on this day. Stability & Change Management went from 87 to 83.
- 17 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 83 to 87.
- 15 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 77 to 80.
- 13 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 70 to 73.
- 12 Sept 26 −5
- Source repository: pass → fail ▼ security
- Security disclosure: fail → unverified ▼ functional
- 10 Sept 26 −3
- Package version: 6.2.19 → 6.2.20 functional
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 20 Sept 2026 · Analysed pypi/terradev-cli@6.2.20
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | pypi |
Background: How many MCP packages publish verified provenance →
Install scripts 1 script
| Hook | Tier | Command |
|---|---|---|
| build_backend | allowlisted | setuptools.build_meta |
Background: Why install scripts are a supply-chain risk →
Dependencies 63 packages
| Packages resolved | 63 |
|---|---|
| Stale | 2 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
inferx_delete ~99
Delete an InferX model deployment.
| Name | Type | Req | Description |
|---|---|---|---|
| credentials | object | – | BYOAPI — your own provider credentials as env vars for this call only (never stored). E.g. {"RUNPOD_API_KEY": "..."}, {"AWS_ACCESS_KEY_ID": "...", "AWS_SECRET_ACCESS_KEY": "..."}, or the TERRADEV_<PR… |
| model_id | string | yes | Model deployment ID to delete |
No output schema declared.
No examples provided.
inferx_deploy ~127
Deploy model to InferX serverless platform
| Name | Type | Req | Description |
|---|---|---|---|
| credentials | object | – | BYOAPI — your own provider credentials as env vars for this call only (never stored). E.g. {"RUNPOD_API_KEY": "..."}, {"AWS_ACCESS_KEY_ID": "...", "AWS_SECRET_ACCESS_KEY": "..."}, or the TERRADEV_<PR… |
| gpu_type | string | yes | GPU type for inference |
| model | string | yes | Model ID (e.g., meta-llama/Llama-2-7b-hf) |
No output schema declared.
No examples provided.
inferx_list ~85
List deployed InferX models
| Name | Type | Req | Description |
|---|---|---|---|
| credentials | object | – | BYOAPI — your own provider credentials as env vars for this call only (never stored). E.g. {"RUNPOD_API_KEY": "..."}, {"AWS_ACCESS_KEY_ID": "...", "AWS_SECRET_ACCESS_KEY": "..."}, or the TERRADEV_<PR… |
No output schema declared.
No examples provided.
inferx_optimize ~87
Get cost analysis for inference endpoints
| Name | Type | Req | Description |
|---|---|---|---|
| credentials | object | – | BYOAPI — your own provider credentials as env vars for this call only (never stored). E.g. {"RUNPOD_API_KEY": "..."}, {"AWS_ACCESS_KEY_ID": "...", "AWS_SECRET_ACCESS_KEY": "..."}, or the TERRADEV_<PR… |
No output schema declared.
No examples provided.
inferx_quote ~89
Get InferX pricing quotes for a GPU type.
| Name | Type | Req | Description |
|---|---|---|---|
| credentials | object | – | BYOAPI — your own provider credentials as env vars for this call only (never stored). E.g. {"RUNPOD_API_KEY": "..."}, {"AWS_ACCESS_KEY_ID": "...", "AWS_SECRET_ACCESS_KEY": "..."}, or the TERRADEV_<PR… |
No output schema declared.
No examples provided.
inferx_status ~85
Check InferX endpoint status
| Name | Type | Req | Description |
|---|---|---|---|
| credentials | object | – | BYOAPI — your own provider credentials as env vars for this call only (never stored). E.g. {"RUNPOD_API_KEY": "..."}, {"AWS_ACCESS_KEY_ID": "...", "AWS_SECRET_ACCESS_KEY": "..."}, or the TERRADEV_<PR… |
No output schema declared.
No examples provided.
inferx_usage ~95
Get InferX account usage statistics: requests, cost, GPU hours, latency.
| Name | Type | Req | Description |
|---|---|---|---|
| credentials | object | – | BYOAPI — your own provider credentials as env vars for this call only (never stored). E.g. {"RUNPOD_API_KEY": "..."}, {"AWS_ACCESS_KEY_ID": "...", "AWS_SECRET_ACCESS_KEY": "..."}, or the TERRADEV_<PR… |
No output schema declared.
No examples provided.
k8s_create ~116
Create Kubernetes cluster with GPU nodes for optimal multi-cloud deployment
| Name | Type | Req | Description |
|---|---|---|---|
| cluster_name | string | yes | Name of the cluster |
| credentials | object | – | BYOAPI — your own provider credentials as env vars for this call only (never stored). E.g. {"RUNPOD_API_KEY": "..."}, {"AWS_ACCESS_KEY_ID": "...", "AWS_SECRET_ACCESS_KEY": "..."}, or the TERRADEV_<PR… |
| gpu_type | string | yes | GPU type for nodes |
No output schema declared.
No examples provided.
k8s_destroy ~99
Destroy a Kubernetes cluster
| Name | Type | Req | Description |
|---|---|---|---|
| cluster_name | string | yes | Name of the cluster to destroy |
| credentials | object | – | BYOAPI — your own provider credentials as env vars for this call only (never stored). E.g. {"RUNPOD_API_KEY": "..."}, {"AWS_ACCESS_KEY_ID": "...", "AWS_SECRET_ACCESS_KEY": "..."}, or the TERRADEV_<PR… |
No output schema declared.
No examples provided.
k8s_device_plugin ~110
Configure Kubernetes GPU device plugin settings: time-slicing, MIG strategy, and resource naming.
| Name | Type | Req | Description |
|---|---|---|---|
| cluster_name | string | yes | Target cluster name |
| credentials | object | – | BYOAPI — your own provider credentials as env vars for this call only (never stored). E.g. {"RUNPOD_API_KEY": "..."}, {"AWS_ACCESS_KEY_ID": "...", "AWS_SECRET_ACCESS_KEY": "..."}, or the TERRADEV_<PR… |
No output schema declared.
No examples provided.
k8s_gpu_operator_install ~119
Install NVIDIA GPU Operator on a Kubernetes cluster. Configures driver containers, device plugin, DCGM exporter, and GPU Feature Discovery.
| Name | Type | Req | Description |
|---|---|---|---|
| cluster_name | string | yes | Target cluster name |
| credentials | object | – | BYOAPI — your own provider credentials as env vars for this call only (never stored). E.g. {"RUNPOD_API_KEY": "..."}, {"AWS_ACCESS_KEY_ID": "...", "AWS_SECRET_ACCESS_KEY": "..."}, or the TERRADEV_<PR… |
No output schema declared.
No examples provided.
k8s_info ~99
Get information about a specific cluster
| Name | Type | Req | Description |
|---|---|---|---|
| cluster_name | string | yes | Name of the cluster |
| credentials | object | – | BYOAPI — your own provider credentials as env vars for this call only (never stored). E.g. {"RUNPOD_API_KEY": "..."}, {"AWS_ACCESS_KEY_ID": "...", "AWS_SECRET_ACCESS_KEY": "..."}, or the TERRADEV_<PR… |
No output schema declared.
No examples provided.
k8s_list ~84
List Kubernetes clusters
| Name | Type | Req | Description |
|---|---|---|---|
| credentials | object | – | BYOAPI — your own provider credentials as env vars for this call only (never stored). E.g. {"RUNPOD_API_KEY": "..."}, {"AWS_ACCESS_KEY_ID": "...", "AWS_SECRET_ACCESS_KEY": "..."}, or the TERRADEV_<PR… |
No output schema declared.
No examples provided.
k8s_mig_configure ~136
Configure Multi-Instance GPU (MIG) partitioning on A100/H100 GPUs. Splits a single GPU into isolated instances for multi-tenant workloads.
| Name | Type | Req | Description |
|---|---|---|---|
| cluster_name | string | yes | Target cluster name |
| credentials | object | – | BYOAPI — your own provider credentials as env vars for this call only (never stored). E.g. {"RUNPOD_API_KEY": "..."}, {"AWS_ACCESS_KEY_ID": "...", "AWS_SECRET_ACCESS_KEY": "..."}, or the TERRADEV_<PR… |
| mig_profile | string | yes | MIG profile |
No output schema declared.
No examples provided.
k8s_time_slicing ~115
Configure GPU time-slicing for Kubernetes. Allows multiple pods to share a single GPU with configurable oversubscription.
| Name | Type | Req | Description |
|---|---|---|---|
| cluster_name | string | yes | Target cluster name |
| credentials | object | – | BYOAPI — your own provider credentials as env vars for this call only (never stored). E.g. {"RUNPOD_API_KEY": "..."}, {"AWS_ACCESS_KEY_ID": "...", "AWS_SECRET_ACCESS_KEY": "..."}, or the TERRADEV_<PR… |
No output schema declared.
No examples provided.
kserve_generate_yaml ~170
Generate a GPU-aware KServe InferenceService YAML manifest with NUMA pinning, resource limits derived from model size and VRAM, and topology hints.
| Name | Type | Req | Description |
|---|---|---|---|
| credentials | object | – | BYOAPI — your own provider credentials as env vars for this call only (never stored). E.g. {"RUNPOD_API_KEY": "..."}, {"AWS_ACCESS_KEY_ID": "...", "AWS_SECRET_ACCESS_KEY": "..."}, or the TERRADEV_<PR… |
| gpu_type | string | yes | GPU type (e.g. A100, H100) |
| model_name | string | yes | Model name for the InferenceService |
| model_uri | string | yes | Model storage URI (e.g. s3://bucket/model or gs://bucket/model) |
No output schema declared.
No examples provided.
kserve_list ~90
List KServe InferenceServices in a Kubernetes namespace.
| Name | Type | Req | Description |
|---|---|---|---|
| credentials | object | – | BYOAPI — your own provider credentials as env vars for this call only (never stored). E.g. {"RUNPOD_API_KEY": "..."}, {"AWS_ACCESS_KEY_ID": "...", "AWS_SECRET_ACCESS_KEY": "..."}, or the TERRADEV_<PR… |
No output schema declared.
No examples provided.
kserve_status ~109
Get detailed status of a KServe InferenceService including readiness, traffic split, and URL.
| Name | Type | Req | Description |
|---|---|---|---|
| credentials | object | – | BYOAPI — your own provider credentials as env vars for this call only (never stored). E.g. {"RUNPOD_API_KEY": "..."}, {"AWS_ACCESS_KEY_ID": "...", "AWS_SECRET_ACCESS_KEY": "..."}, or the TERRADEV_<PR… |
| name | string | yes | InferenceService name |
No output schema declared.
No examples provided.
langchain_create_sglang_pipeline ~138
Create an SGLang model-serving pipeline via LangChain. Connects LangChain agents to SGLang inference endpoints.
| Name | Type | Req | Description |
|---|---|---|---|
| api_key | string | yes | LangChain API key |
| credentials | object | – | BYOAPI — your own provider credentials as env vars for this call only (never stored). E.g. {"RUNPOD_API_KEY": "..."}, {"AWS_ACCESS_KEY_ID": "...", "AWS_SECRET_ACCESS_KEY": "..."}, or the TERRADEV_<PR… |
| pipeline_config | object | yes | Pipeline config (model, endpoint, temperature, max_tokens) |
No output schema declared.
No examples provided.
langchain_create_workflow ~117
Create a LangChain workflow.
| Name | Type | Req | Description |
|---|---|---|---|
| api_key | string | yes | LangChain API key |
| credentials | object | – | BYOAPI — your own provider credentials as env vars for this call only (never stored). E.g. {"RUNPOD_API_KEY": "..."}, {"AWS_ACCESS_KEY_ID": "...", "AWS_SECRET_ACCESS_KEY": "..."}, or the TERRADEV_<PR… |
| workflow_config | object | yes | Workflow configuration (name, steps, model, tools) |
No output schema declared.
No examples provided.
langfuse_configure ~132
Configure Langfuse credentials (public key, secret key, host URL).
| Name | Type | Req | Description |
|---|---|---|---|
| credentials | object | – | BYOAPI — your own provider credentials as env vars for this call only (never stored). E.g. {"RUNPOD_API_KEY": "..."}, {"AWS_ACCESS_KEY_ID": "...", "AWS_SECRET_ACCESS_KEY": "..."}, or the TERRADEV_<PR… |
| public_key | string | yes | Langfuse public key (pk-lf-...) |
| secret_key | string | yes | Langfuse secret key (sk-lf-...) |
No output schema declared.
No examples provided.
langfuse_datasets ~93
List Langfuse datasets for evaluation and fine-tuning.
| Name | Type | Req | Description |
|---|---|---|---|
| credentials | object | – | BYOAPI — your own provider credentials as env vars for this call only (never stored). E.g. {"RUNPOD_API_KEY": "..."}, {"AWS_ACCESS_KEY_ID": "...", "AWS_SECRET_ACCESS_KEY": "..."}, or the TERRADEV_<PR… |
No output schema declared.
No examples provided.
langfuse_export_training_data ~104
Export Langfuse traces as instruction/response pairs for LoRA fine-tuning. Filters by quality score.
| Name | Type | Req | Description |
|---|---|---|---|
| credentials | object | – | BYOAPI — your own provider credentials as env vars for this call only (never stored). E.g. {"RUNPOD_API_KEY": "..."}, {"AWS_ACCESS_KEY_ID": "...", "AWS_SECRET_ACCESS_KEY": "..."}, or the TERRADEV_<PR… |
No output schema declared.
No examples provided.
langfuse_k8s ~94
Generate Kubernetes deployment manifest for self-hosted Langfuse.
| Name | Type | Req | Description |
|---|---|---|---|
| credentials | object | – | BYOAPI — your own provider credentials as env vars for this call only (never stored). E.g. {"RUNPOD_API_KEY": "..."}, {"AWS_ACCESS_KEY_ID": "...", "AWS_SECRET_ACCESS_KEY": "..."}, or the TERRADEV_<PR… |
No output schema declared.
No examples provided.
langfuse_otel_env ~101
Print OTEL environment variables for instrumenting LLM apps to send traces to Langfuse.
| Name | Type | Req | Description |
|---|---|---|---|
| credentials | object | – | BYOAPI — your own provider credentials as env vars for this call only (never stored). E.g. {"RUNPOD_API_KEY": "..."}, {"AWS_ACCESS_KEY_ID": "...", "AWS_SECRET_ACCESS_KEY": "..."}, or the TERRADEV_<PR… |
No output schema declared.
No examples provided.
langfuse_quality ~93
Get aggregated quality metrics from Langfuse scores for drift detection.
| Name | Type | Req | Description |
|---|---|---|---|
| credentials | object | – | BYOAPI — your own provider credentials as env vars for this call only (never stored). E.g. {"RUNPOD_API_KEY": "..."}, {"AWS_ACCESS_KEY_ID": "...", "AWS_SECRET_ACCESS_KEY": "..."}, or the TERRADEV_<PR… |
No output schema declared.
No examples provided.
langfuse_score ~138
Create an evaluation score for a Langfuse trace (e.g. quality, accuracy, relevance).
| Name | Type | Req | Description |
|---|---|---|---|
| credentials | object | – | BYOAPI — your own provider credentials as env vars for this call only (never stored). E.g. {"RUNPOD_API_KEY": "..."}, {"AWS_ACCESS_KEY_ID": "...", "AWS_SECRET_ACCESS_KEY": "..."}, or the TERRADEV_<PR… |
| name | string | yes | Score name (e.g. quality, accuracy) |
| trace_id | string | yes | Trace ID to score |
| value | number | yes | Numeric score value |
No output schema declared.
No examples provided.
langfuse_scores ~96
List evaluation scores from Langfuse, optionally filtered by trace or score name.
| Name | Type | Req | Description |
|---|---|---|---|
| credentials | object | – | BYOAPI — your own provider credentials as env vars for this call only (never stored). E.g. {"RUNPOD_API_KEY": "..."}, {"AWS_ACCESS_KEY_ID": "...", "AWS_SECRET_ACCESS_KEY": "..."}, or the TERRADEV_<PR… |
No output schema declared.
No examples provided.
langfuse_test ~90
Test Langfuse connectivity and list accessible projects.
| Name | Type | Req | Description |
|---|---|---|---|
| credentials | object | – | BYOAPI — your own provider credentials as env vars for this call only (never stored). E.g. {"RUNPOD_API_KEY": "..."}, {"AWS_ACCESS_KEY_ID": "...", "AWS_SECRET_ACCESS_KEY": "..."}, or the TERRADEV_<PR… |
No output schema declared.
No examples provided.
langfuse_trace ~103
Get a single Langfuse trace with all observations/spans.
| Name | Type | Req | Description |
|---|---|---|---|
| credentials | object | – | BYOAPI — your own provider credentials as env vars for this call only (never stored). E.g. {"RUNPOD_API_KEY": "..."}, {"AWS_ACCESS_KEY_ID": "...", "AWS_SECRET_ACCESS_KEY": "..."}, or the TERRADEV_<PR… |
| trace_id | string | yes | Trace ID |
No output schema declared.
No examples provided.
langfuse_traces ~91
List recent LLM traces from Langfuse.
| Name | Type | Req | Description |
|---|---|---|---|
| credentials | object | – | BYOAPI — your own provider credentials as env vars for this call only (never stored). E.g. {"RUNPOD_API_KEY": "..."}, {"AWS_ACCESS_KEY_ID": "...", "AWS_SECRET_ACCESS_KEY": "..."}, or the TERRADEV_<PR… |
No output schema declared.
No examples provided.
langgraph_create_workflow ~131
Create a LangGraph stateful workflow with monitoring. Supports agent graphs, tool calling, and state persistence.
| Name | Type | Req | Description |
|---|---|---|---|
| api_key | string | yes | LangChain API key |
| credentials | object | – | BYOAPI — your own provider credentials as env vars for this call only (never stored). E.g. {"RUNPOD_API_KEY": "..."}, {"AWS_ACCESS_KEY_ID": "...", "AWS_SECRET_ACCESS_KEY": "..."}, or the TERRADEV_<PR… |
| graph_config | object | yes | Graph configuration (nodes, edges, state_schema) |
No output schema declared.
No examples provided.
langgraph_evaluation_workflow ~135
Create an evaluator-optimizer workflow in LangGraph. Generates outputs, evaluates quality, and iteratively improves.
| Name | Type | Req | Description |
|---|---|---|---|
| api_key | string | yes | LangChain API key |
| credentials | object | – | BYOAPI — your own provider credentials as env vars for this call only (never stored). E.g. {"RUNPOD_API_KEY": "..."}, {"AWS_ACCESS_KEY_ID": "...", "AWS_SECRET_ACCESS_KEY": "..."}, or the TERRADEV_<PR… |
| evaluation_config | object | yes | Evaluation config (generator_prompt, evaluator_criteria, max_iterations) |
No output schema declared.
No examples provided.
langgraph_orchestrator_worker ~138
Create an orchestrator-worker pattern workflow in LangGraph. The orchestrator delegates tasks to specialized worker agents.
| Name | Type | Req | Description |
|---|---|---|---|
| api_key | string | yes | LangChain API key |
| credentials | object | – | BYOAPI — your own provider credentials as env vars for this call only (never stored). E.g. {"RUNPOD_API_KEY": "..."}, {"AWS_ACCESS_KEY_ID": "...", "AWS_SECRET_ACCESS_KEY": "..."}, or the TERRADEV_<PR… |
| workflow_config | object | yes | Orchestrator-worker config (orchestrator_prompt, workers, routing_strategy) |
No output schema declared.
No examples provided.
langgraph_workflow_status ~117
Get the status and metrics of a LangGraph workflow execution.
| Name | Type | Req | Description |
|---|---|---|---|
| api_key | string | yes | LangChain API key |
| credentials | object | – | BYOAPI — your own provider credentials as env vars for this call only (never stored). E.g. {"RUNPOD_API_KEY": "..."}, {"AWS_ACCESS_KEY_ID": "...", "AWS_SECRET_ACCESS_KEY": "..."}, or the TERRADEV_<PR… |
| workflow_id | string | yes | Workflow ID to check |
No output schema declared.
No examples provided.
local_scan ~98
Scan local machine and network for available GPU devices. Returns total VRAM pool for local-first provisioning.
| Name | Type | Req | Description |
|---|---|---|---|
| credentials | object | – | BYOAPI — your own provider credentials as env vars for this call only (never stored). E.g. {"RUNPOD_API_KEY": "..."}, {"AWS_ACCESS_KEY_ID": "...", "AWS_SECRET_ACCESS_KEY": "..."}, or the TERRADEV_<PR… |
No output schema declared.
No examples provided.
lora_add ~195
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.
| Name | Type | Req | Description |
|---|---|---|---|
| credentials | object | – | BYOAPI — your own provider credentials as env vars for this call only (never stored). E.g. {"RUNPOD_API_KEY": "..."}, {"AWS_ACCESS_KEY_ID": "...", "AWS_SECRET_ACCESS_KEY": "..."}, or the TERRADEV_<PR… |
| endpoint | string | yes | vLLM endpoint URL (e.g. http://10.0.0.1:8000) |
| name | string | yes | Adapter name (becomes the model name in API requests) |
| path | string | yes | Path to adapter weights (local path or HuggingFace ID) |
No output schema declared.
No examples provided.
lora_list ~131
List LoRA adapters loaded on a running vLLM endpoint. Shows base models and hot-loaded fine-tuned adapters.
| Name | Type | Req | Description |
|---|---|---|---|
| credentials | object | – | BYOAPI — your own provider credentials as env vars for this call only (never stored). E.g. {"RUNPOD_API_KEY": "..."}, {"AWS_ACCESS_KEY_ID": "...", "AWS_SECRET_ACCESS_KEY": "..."}, or the TERRADEV_<PR… |
| endpoint | string | yes | vLLM endpoint URL (e.g. http://10.0.0.1:8000) |
No output schema declared.
No examples provided.
lora_remove ~141
Hot-unload a LoRA adapter from a running vLLM endpoint. Frees GPU memory for other adapters.
| Name | Type | Req | Description |
|---|---|---|---|
| credentials | object | – | BYOAPI — your own provider credentials as env vars for this call only (never stored). E.g. {"RUNPOD_API_KEY": "..."}, {"AWS_ACCESS_KEY_ID": "...", "AWS_SECRET_ACCESS_KEY": "..."}, or the TERRADEV_<PR… |
| endpoint | string | yes | vLLM endpoint URL (e.g. http://10.0.0.1:8000) |
| name | string | yes | Adapter name to unload |
No output schema declared.
No examples provided.
manage_instance ~107
Manage GPU instances (stop/start/terminate)
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | yes | Action to perform |
| credentials | object | – | BYOAPI — your own provider credentials as env vars for this call only (never stored). E.g. {"RUNPOD_API_KEY": "..."}, {"AWS_ACCESS_KEY_ID": "...", "AWS_SECRET_ACCESS_KEY": "..."}, or the TERRADEV_<PR… |
| instance_id | string | yes | Instance ID |
No output schema declared.
No examples provided.
manifests ~85
List cached manifests and versions for jobs.
| Name | Type | Req | Description |
|---|---|---|---|
| credentials | object | – | BYOAPI — your own provider credentials as env vars for this call only (never stored). E.g. {"RUNPOD_API_KEY": "..."}, {"AWS_ACCESS_KEY_ID": "...", "AWS_SECRET_ACCESS_KEY": "..."}, or the TERRADEV_<PR… |
No output schema declared.
No examples provided.
ml_vllm_lora_link ~119
Load the active registry version of an adapter onto a vLLM server.
| Name | Type | Req | Description |
|---|---|---|---|
| credentials | object | – | BYOAPI — your own provider credentials as env vars for this call only (never stored). E.g. {"RUNPOD_API_KEY": "..."}, {"AWS_ACCESS_KEY_ID": "...", "AWS_SECRET_ACCESS_KEY": "..."}, or the TERRADEV_<PR… |
| endpoint | string | yes | vLLM endpoint |
| name | string | yes | Registered adapter name |
No output schema declared.
No examples provided.
ml_vllm_lora_list ~107
List LoRA adapters currently loaded on a vLLM server.
| Name | Type | Req | Description |
|---|---|---|---|
| credentials | object | – | BYOAPI — your own provider credentials as env vars for this call only (never stored). E.g. {"RUNPOD_API_KEY": "..."}, {"AWS_ACCESS_KEY_ID": "...", "AWS_SECRET_ACCESS_KEY": "..."}, or the TERRADEV_<PR… |
| endpoint | string | yes | vLLM endpoint |
No output schema declared.
No examples provided.
ml_vllm_lora_load ~129
Hot-load a LoRA adapter onto a running vLLM server.
| Name | Type | Req | Description |
|---|---|---|---|
| credentials | object | – | BYOAPI — your own provider credentials as env vars for this call only (never stored). E.g. {"RUNPOD_API_KEY": "..."}, {"AWS_ACCESS_KEY_ID": "...", "AWS_SECRET_ACCESS_KEY": "..."}, or the TERRADEV_<PR… |
| endpoint | string | yes | vLLM endpoint |
| name | string | yes | Adapter name |
| path | string | yes | Local path to adapter weights |
No output schema declared.
No examples provided.
ml_vllm_lora_sync ~121
Synchronize an adapter from the registry across multiple vLLM replicas.
| Name | Type | Req | Description |
|---|---|---|---|
| credentials | object | – | BYOAPI — your own provider credentials as env vars for this call only (never stored). E.g. {"RUNPOD_API_KEY": "..."}, {"AWS_ACCESS_KEY_ID": "...", "AWS_SECRET_ACCESS_KEY": "..."}, or the TERRADEV_<PR… |
| name | string | yes | Registered adapter name |
| replicas | string | yes | Comma-separated host:port list |
No output schema declared.
No examples provided.
ml_vllm_lora_unload ~121
Hot-unload a LoRA adapter from a running vLLM server.
| Name | Type | Req | Description |
|---|---|---|---|
| credentials | object | – | BYOAPI — your own provider credentials as env vars for this call only (never stored). E.g. {"RUNPOD_API_KEY": "..."}, {"AWS_ACCESS_KEY_ID": "...", "AWS_SECRET_ACCESS_KEY": "..."}, or the TERRADEV_<PR… |
| endpoint | string | yes | vLLM endpoint |
| name | string | yes | Adapter name to unload |
No output schema declared.
No examples provided.
mlflow_list_experiments ~105
List MLflow experiments on the configured tracking server.
| Name | Type | Req | Description |
|---|---|---|---|
| credentials | object | – | BYOAPI — your own provider credentials as env vars for this call only (never stored). E.g. {"RUNPOD_API_KEY": "..."}, {"AWS_ACCESS_KEY_ID": "...", "AWS_SECRET_ACCESS_KEY": "..."}, or the TERRADEV_<PR… |
| tracking_uri | string | yes | MLflow tracking server URI |
No output schema declared.
No examples provided.
mlflow_log_run ~142
Log a Terradev training run to MLflow with auto-injected GPU type, provider, cost/hr, and duration as params.
| Name | Type | Req | Description |
|---|---|---|---|
| credentials | object | – | BYOAPI — your own provider credentials as env vars for this call only (never stored). E.g. {"RUNPOD_API_KEY": "..."}, {"AWS_ACCESS_KEY_ID": "...", "AWS_SECRET_ACCESS_KEY": "..."}, or the TERRADEV_<PR… |
| experiment_name | string | yes | MLflow experiment name |
| run_name | string | yes | Run display name |
| tracking_uri | string | yes | MLflow tracking server URI |
No output schema declared.
No examples provided.
mlflow_register_model ~136
Register a trained model in the MLflow model registry with Terradev provenance tags.
| Name | Type | Req | Description |
|---|---|---|---|
| credentials | object | – | BYOAPI — your own provider credentials as env vars for this call only (never stored). E.g. {"RUNPOD_API_KEY": "..."}, {"AWS_ACCESS_KEY_ID": "...", "AWS_SECRET_ACCESS_KEY": "..."}, or the TERRADEV_<PR… |
| model_name | string | yes | Model registry name |
| run_id | string | yes | MLflow run ID that produced the model |
| tracking_uri | string | yes | MLflow tracking server URI |
No output schema declared.
No examples provided.
moe_deploy ~257
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.
| Name | Type | Req | Description |
|---|---|---|---|
| credentials | object | – | BYOAPI — your own provider credentials as env vars for this call only (never stored). E.g. {"RUNPOD_API_KEY": "..."}, {"AWS_ACCESS_KEY_ID": "...", "AWS_SECRET_ACCESS_KEY": "..."}, or the TERRADEV_<PR… |
| gpu_type | string | yes | GPU type for MoE serving |
| model_id | string | yes | HuggingFace model ID (e.g., zai-org/GLM-5-FP8, Qwen/Qwen3.5-397B-A17B) |
No output schema declared.
No examples provided.
What is the Terradev MCP server?
Terradev is an MCP server listed in the public MCP registry as io.github.theoddden/terradev. Cross-cloud GPU orchestration CLI. This page covers its PyPI package (terradev-cli).
Is the Terradev MCP server safe to use?
Terradev scores 76 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the Terradev MCP server expose?
Terradev exposes 245 tools: provision_gpu, preflight_report, preflight_gpu_check, preflight_network_check, local_scan, and 240 more. Their descriptions and schemas cost roughly 27,281 tokens of context every time the server is loaded.
Is the Terradev MCP server still maintained?
Terradev is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the Terradev MCP server under?
Terradev declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.