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/andrewaltimit/template-repo/opencodegit clone --depth 1 https://github.com/AndrewAltimit/template-repoGrade A, and why
opencode 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 2d ago.
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
{
"opencode": {
"command": "docker",
"args": [
"compose",
"-f",
"./docker-compose.yml",
"--profile",
"services",
"run",
"--rm",
"-T",
"mcp-opencode",
"mcp-opencode",
"--mode",
"stdio"
]
}
}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.
- 2d ago First seen · 19 lines scan A 1f3a363b9683
opencode is an MCP server published in the GitHub repository AndrewAltimit/template-repo (131 stars, last pushed 1mo ago), licensed Unlicense. 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
aegis
Auto-instrument AI agent frameworks with runtime security. One line to govern LangChain, CrewAI, OpenAI, Anthropic — injection blocking, PII masking, action policy, audit trail. Zero code changes. Runs locally from the agent-aegis Python package. Needs 1 environment variable to run.
invinoveritas
Verification layer for AI agents: neutral /review verdict, signed /prove, public /ledger record. Remote server at api.babyblueviper.com.
veriswarm-mcp
VeriSwarm MCP Server — Trust infrastructure for AI agents via Model Context Protocol. Runs locally from the veriswarm-mcp Python package.
lanchu
Control and trust layer for coordinating multiple AI agents. MCP, 100% local, open source. Runs locally from the lanchu npm package.
kernel
Open proof-required execution kernel for consequential actions. Runs locally from the actenon-kernel Python package.
vitna-compliance-preflight
Pre-action allow/deny for AI agents. 24 statutes, 13 jurisdictions: EU AI Act, GDPR, DPDP. Runs locally from the @costrinity/vitna-compliance-mcp npm package. Needs 4 environment variables to run.