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.
git clone --depth 1 https://github.com/harness/mcp-serverWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/plugins/harness/mcp-server/gemini-extension)<a href="https://agentmods.dev/plugins/harness/mcp-server/gemini-extension"><img src="https://agentmods.dev/badge/plugins/harness/mcp-server/gemini-extension.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
harness-mcp 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
{
"name": "harness-mcp",
"description": "AI-native interface to the Harness Platform — ask questions, diagnose failures, and manage deployments without leaving your terminal",
"version": "0.5.2",
"mcpServers": {
"harness": {
"command": "node",
"args": [
"--env-file=.env",
"build/index.js",
"stdio"
],
"env": {
"HARNESS_BASE_URL": "https://app.harness.io"
}
}
},
"contextFileName": "docs/gemini.md"
}
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 First seen · 20 lines scan A dbf4ec251b51
harness-mcp is a plugin published in the GitHub repository harness/mcp-server (95 stars, last pushed yesterday), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-09-06.
Other plugins, from other repositories
unifi-network
UniFi Network MCP server — manage network devices, clients, firewall, VPN, and more.
ksail
KSail MCP server + expertise skill — spin up and manage local Kubernetes clusters (Kind/K3d/Talos/vCluster) and GitOps workloads declaratively.
obto
Build, deploy, and operate apps on the OBTO platform — one MCP connection (Google sign-in, auto-provisioned workspace), a /obto:start session command, plus skills for the build loop, large-file deploys (patch-in-place, chunked, and deploy-by-reference), media/binary upload (signed-URL and chunked), agent memory…
runwhen-platform
Infrastructure automation for RunWhen — monitor, troubleshoot, and automate with AI agents. Build health checks, investigate issues, and manage SRE tasks across Kubernetes and cloud environments.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
themes-example
themes-example. An open-source AI agent that brings the power of Gemini directly into your terminal.