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/shinpr/mcp-local-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/shinpr/mcp-local-rag/mcp-local-rag)<a href="https://agentmods.dev/mcp/shinpr/mcp-local-rag/mcp-local-rag"><img src="https://agentmods.dev/badge/mcp/shinpr/mcp-local-rag/mcp-local-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/shinpr/mcp-local-rag/mcp-local-rag"><img src="https://agentmods.dev/badge/mcp/shinpr/mcp-local-rag/mcp-local-rag.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket warn
Grade A, and why
mcp-local-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.
Copies of this mod
2 near-identical copies found in the catalogue:
- mcp-local-rag — 91% identical, 7 lines differ
- local.local-rag — 83% identical, 11 lines differ
What it actually says
{
"mcp-local-rag": {
"command": "npx",
"args": [
"-y",
"mcp-local-rag"
],
"env": {
"BASE_DIR": "",
"DB_PATH": "",
"CACHE_DIR": "",
"MODEL_NAME": "",
"MAX_FILE_SIZE": "",
"RAG_MAX_DISTANCE": "",
"RAG_GROUPING": "",
"RAG_MAX_FILES": ""
}
}
}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 · 19 lines scan A 869a33c92433
mcp-local-rag is an MCP server published in the GitHub repository shinpr/mcp-local-rag (387 stars, last pushed 3d 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 2026-08-30.
Other mcp servers, from other repositories
ragwatcher
MCP server "ragwatcher" as configured in neumann-mlucas/ragwatcher. Runs locally from the ragwatcher Python package.
local-faiss-mcp
MCP server with FAISS local vector database for RAG. Runs locally from the local-faiss-mcp Python package.
haiku-rag
Local-first agentic RAG with citations - hybrid search, reranking and multimodal retrieval over your own documents, no database server required. Runs locally from the haiku-rag Python package.
haiku-rag
MCP server "haiku-rag" as configured in ggozad/haiku.rag. Launched with haiku-rag mcp --stdio.
octocode
AI-powered code indexer with semantic search and knowledge graphs. Runs locally from the @muvon/octocode npm package.
mcp-server
Apple Developer Documentation with Semantic Search, RAG, and AI reranking for MCP clients. Remote server at mcp.apple-rag.com.