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/ggozad/haiku.ragWrote 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/ggozad/haiku.rag/haiku-rag)<a href="https://agentmods.dev/mcp/ggozad/haiku.rag/haiku-rag"><img src="https://agentmods.dev/badge/mcp/ggozad/haiku.rag/haiku-rag/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/ggozad/haiku.rag/haiku-rag"><img src="https://agentmods.dev/badge/mcp/ggozad/haiku.rag/haiku-rag.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket warn
Grade A, and why
haiku-rag 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 10d 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
{
"haiku-rag": {
"command": "uvx",
"args": [
"haiku-rag",
"mcp",
"--stdio"
],
"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.
- 10d ago First seen · 11 lines scan A 9b6add3aa3a5
haiku-rag is an MCP server published in the GitHub repository ggozad/haiku.rag (598 stars, last pushed yesterday), 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 2026-08-30.
Other mcp servers, from other repositories
discord-archive
MCP server "discord-archive" as configured in wdwdev/discord-archive. Runs locally from the rag Python package.
rag-db-advisor
MCP server "rag-db-advisor" as configured in kenimo49/rag-db-advisor. Runs locally from the rag-db-advisor Python package.
zvec-mcp-server
MCP server for Zvec vector database. Runs locally from the zvec-mcp-server Python package.
memory-lancedb-mcp
MCP server for LanceDB-backed long-term memory with hybrid retrieval (Vector + BM25), cross-encoder rerank, multi-scope isolation, and memory lifecycle management. Runs locally from the @cablate/memory-lancedb-mcp npm package.
mcp-server-milvus
MCP server for Milvus. Runs locally from the mcp-server-milvus Python package.
octocode
AI-powered code indexer with semantic search and knowledge graphs. Runs locally from the @muvon/octocode npm package.