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/patakuti/local-knowledge-rag-mcpWrote 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/patakuti/local-knowledge-rag-mcp/local-knowledge-rag)<a href="https://agentmods.dev/mcp/patakuti/local-knowledge-rag-mcp/local-knowledge-rag"><img src="https://agentmods.dev/badge/mcp/patakuti/local-knowledge-rag-mcp/local-knowledge-rag.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
local-knowledge-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 8d 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
{
"local-knowledge-rag": {
"command": "node",
"args": [
"/path/to/local-knowledge-rag-mcp/dist/mcp-server.js"
],
"env": {
"WORKSPACE_PATH": "/path/to/your/knowledge/base",
"DATABASE_URL": "postgresql://user:password@localhost:5432/local_knowledge_rag",
"OPENAI_API_KEY": "your-openai-api-key"
}
}
}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.
- 8d ago First seen · 13 lines scan A de23679a4214
local-knowledge-rag is an MCP server published in the GitHub repository patakuti/local-knowledge-rag-mcp (9 stars, last pushed 2mo 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
mcp-pgvector-search
MCP server "mcp-pgvector-search" as configured in JuanPinilla198/mcp-pgvector-search. Runs locally from the mcp-pgvector-search Python package.
dbconvert-streams
Read-only SQL across PostgreSQL, MySQL, S3 buckets and local data files — one query can join across all of them. MCP server. Runs locally from the @dbconvert/stream-mcp npm package. Needs 1 environment variable to run.
mad-mcp-qdrant
MCP server for retrieving context from a Qdrant vector database. Runs locally from the mad-mcp-qdrant Python package.
seedfast
AI-powered PostgreSQL database seeding tool. Runs locally from the seedfast npm package. Needs 1 environment variable to run.
pgmcp
MCP server "pgmcp" as configured in pascalallen/pgmcp. Runs in Docker (ghcr.io/pascalallen/pgmcp:1.1.0). Needs 1 environment variable to run.
datris
MCP server for AI-driven data pipeline operations — ingest, validate, transform, analyze, and query data. Tools covering ETL, AI data quality, vector search, PostgreSQL, MongoDB, Snowflake, Databricks, Kafka, S3/MinIO, HashiCorp Vault, Qdrant, Weaviate, Milvus, Chroma, pgvector. Runs locally from the datris-mcp-server…