Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add mcp/gemini-cli-extensions/data-agent-kit-starter-pack/serverless-sparkgit clone --depth 1 https://github.com/gemini-cli-extensions/data-agent-kit-starter-packGrade A, and why
serverless-spark scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"serverless-spark": {
"command": "npx",
"args": [
"-y",
"@toolbox-sdk/server@latest",
"--prebuilt",
"serverless-spark",
"--stdio",
"--user-agent-metadata",
"datacloud.codex"
],
"env": {
"SERVERLESS_SPARK_PROJECT": "$PROJECT_ID",
"SERVERLESS_SPARK_LOCATION": "$GCP_REGION"
}
}
}What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday Changed fe35dab32ae4
- 3d ago First seen · 18 lines scan A 07e55fc4eb3f
serverless-spark is an MCP server published in the GitHub repository gemini-cli-extensions/data-agent-kit-starter-pack (177 stars, last pushed yesterday), licensed Apache-2.0. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other mcp servers, from other repositories
terradev
Imperative Command Line Interface for AI Workload Orchestration across 17 GPU cloud providers. Runs locally from the terradev-cli Python package. Needs 3 environment variables to run.
vmware-privateai
VMware Private AI Foundation with NVIDIA ops — GPU inventory, vGPU/DirectPath profiles, utilization, model-serving (MCP + CLI). Runs locally from the vmware-privateai Python package.
dataproc-mcp-server
A production-ready Model Context Protocol (MCP) server for Google Cloud Dataproc operations. Provides intelligent defaults, comprehensive tooling, and seamless integration with Roo (VS Code) for big data workflows. Runs locally from the @dipseth/dataproc-mcp-server npm package.
auxen
Provision private AI model endpoints on dedicated GPUs (Llama, Qwen, Mistral). Pay per minute. Remote server at api.auxen.ai.
google-cloud-mcp
A comprehensive Model Context Protocol (MCP) server for Google Cloud Platform services including BigQuery, Cloud Logging, Cloud Storage, and Compute Engine. Runs locally from the google-cloud-mcp Python package.
adls2-mcp-server
Azure Data Lake Storage Gen2 Model Context Protocol (MCP) service. Runs locally from the adls2-mcp-server Python package.