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/aabxtract/kodaWrote 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/mcp/aabxtract/koda/koda)<a href="https://agentmods.dev/mcp/aabxtract/koda/koda"><img src="https://agentmods.dev/badge/mcp/aabxtract/koda/koda/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/mcp/aabxtract/koda/koda"><img src="https://agentmods.dev/badge/mcp/aabxtract/koda/koda.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
koda 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 1mo 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
{
"koda": {
"command": "npx",
"args": [
"-y",
"koda-verify"
],
"env": {}
}
}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.
- 1mo ago First seen · 10 lines scan A 37389a087c34
koda is an MCP server published in the GitHub repository aabxtract/koda (0 stars, last pushed 1mo ago), licensed MIT. 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 2026-08-31.
Other mcp servers, from other repositories
memtrust
Independent, reproducible benchmark harness for agent-memory backends (MemPalace, Mem0, Zep/Graphiti, OpenViking): runs LongMemEval, LoCoMo, contradiction-detection, and a dozen other evals against all four and publishes the raw logs, not vendor-curated numbers. Runs locally from the memtrust-cli Python package.
june-mcp
MCP server for Junê — give any MCP agent (Claude Desktop, Claude Code, …) a shared, cited knowledge-graph memory backed by a June endpoint. Runs locally from the june-mcp Python package. Needs 13 environment variables to run.
agent-context-graph
MCP server "agent-context-graph" as configured in Raviraj2024/Agent-Context-Graph. Runs locally from the agent-context-graph npm package.
pg-git-mcp
A PostgreSQL-backed Git implementation and semantic memory MCP server for AI IDEs. Runs locally from the pg-git-mcp npm package.
chaosmesh-mcp
MCP server "chaosmesh-mcp" as configured in Ausium/chaosmesh-mcp. Runs locally from the chaosmesh-mcp Python package.
token-lens
Context window token analysis and budget management. Runs locally from the token-lens-mcp npm package.