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/henrardo/llm-graph-builder-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/henrardo/llm-graph-builder-mcp/llm-graph-builder)<a href="https://agentmods.dev/mcp/henrardo/llm-graph-builder-mcp/llm-graph-builder"><img src="https://agentmods.dev/badge/mcp/henrardo/llm-graph-builder-mcp/llm-graph-builder.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
llm-graph-builder 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
{
"llm-graph-builder": {
"command": "uvx",
"args": [
"--from",
"/absolute/path/to/llm-graph-builder-mcp",
"llm-graph-builder-mcp"
],
"env": {
"NEO4J_URI": "neo4j+s://your-instance.databases.neo4j.io",
"NEO4J_USERNAME": "neo4j",
"NEO4J_PASSWORD": "your-password",
"NEO4J_DATABASE": "neo4j",
"GRAPH_BUILDER_URL": "http://localhost:8000"
}
}
}What else claude_desktop_config.json configures
This page is one entry in a file that holds 2. Installing the file brings all of them; each is measured and scanned on its own page.
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 · 17 lines scan A 076aeb510375
llm-graph-builder is an MCP server published in the GitHub repository henrardo/llm-graph-builder-mcp (0 stars, last pushed 9mo ago), licensed Apache-2.0. 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 2026-09-01.
Other mcp servers, from other repositories
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.
chromadb-remote-mcp
MCP server "chromadb-remote-mcp" as configured in meloncafe/chromadb-remote-mcp. Runs in Docker (devsaurus/chromadb-remote-mcp:latest). Needs 2 environment variables to run.
mcp-neo4j-knowledge-graph
Neo4j-based knowledge graph MCP server with temporal versioning and semantic search. Runs locally from the @henrychong-ai/mcp-neo4j-knowledge-graph npm package.
toolbelt
A collaborative substrate over your data: vector, knowledge graph, SQL, geospatial, streaming. Remote server at mcp.toolbelt.ai.
mad-mcp-qdrant
MCP server for retrieving context from a Qdrant vector database. Runs locally from the mad-mcp-qdrant Python package.
local-knowledge-rag
MCP server "local-knowledge-rag" as configured in patakuti/local-knowledge-rag-mcp. Runs /path/to/local-knowledge-rag-mcp/dist/mcp-server.js with node. Needs 3 environment variables to run.