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/monahand1023/corpusWrote 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/monahand1023/corpus/corpus-rag)<a href="https://agentmods.dev/mcp/monahand1023/corpus/corpus-rag"><img src="https://agentmods.dev/badge/mcp/monahand1023/corpus/corpus-rag.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
corpus-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 7d 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
{ "corpus-rag": { "command": "uvx", "args": [ "corpus-rag" ] } }
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.
- 7d ago First seen · 8 lines scan A 36b6f6ad0e52
corpus-rag is an MCP server published in the GitHub repository monahand1023/corpus (0 stars, last pushed 6d 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
shelfmark-rag
Local hybrid retrieval (BM25 + embeddings + RRF) for agent memory and codebases — one SQLite file, MCP server included. Runs locally from the shelfmark-rag Python package.
docs-rag-mcp
Minimal local RAG MCP server: semantic search over your markdown docs, embeddings via Ollama, nothing leaves your machine. Runs locally from the docs-rag-mcp npm package.
re-call
Trustworthy retrieval for an AI agent's own memory — verdict, confidence and provenance per hit, or an explicit abstention. Runs locally from the recall-rag Python package. Needs 3 environment variables to run.
ariadne
MCP server "ariadne" as configured in mclaut/ariadne. Launched with https://github.com/mclaut/ariadne/releases/download/v0.8.9/ariadne-v0.8.9.mcpb. Needs 5 environment variables to run.
cortex
Local multi-client RAG server over the Model Context Protocol. Runs locally from the cortex-local-rag Python package. Needs 1 environment variable to run.
semantic-search-mcp
RAG-lite: local semantic search over your files, as a CLI and an MCP server. No LLM, no API keys, no servers. Runs locally from the @adborroto/semantic-search-mcp npm package.