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/neo4j-contrib/gds-agentWrote 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/neo4j-contrib/gds-agent/neo4j-gds)<a href="https://agentmods.dev/mcp/neo4j-contrib/gds-agent/neo4j-gds"><img src="https://agentmods.dev/badge/mcp/neo4j-contrib/gds-agent/neo4j-gds/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/neo4j-contrib/gds-agent/neo4j-gds"><img src="https://agentmods.dev/badge/mcp/neo4j-contrib/gds-agent/neo4j-gds.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
neo4j-gds 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 11d 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
{
"neo4j-gds": {
"type": "stdio",
"command": "uv",
"args": [
"run",
"--directory",
"src/mcp_server_neo4j_gds",
"gds-agent"
]
}
}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.
- 11d ago First seen · 12 lines scan A 4b074063ce90
neo4j-gds is an MCP server published in the GitHub repository neo4j-contrib/gds-agent (96 stars, last pushed 13d 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
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.
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.
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.
sap-datasphere
MCP server for SAP Datasphere — 39 tools (49 with diagnostics), Smart Query, Streamable HTTP, and built-in config-driven PII/sensitive-field masking (fail-closed, audit-logged, GDPR-ready). Runs locally from the @mariodefe/sap-datasphere-mcp npm package. Needs 6 environment variables to run.
text2sql-mcp
MCP server for text2sql-framework. Lets any MCP-compatible assistant (Claude Desktop, Cursor, Goose, etc.) ask a SQL database questions in natural language. Runs locally from the text2sql-mcp Python package. Needs 4 environment variables to run.
better-qdrant-mcp-server
MCP server for enhanced Qdrant vector database functionality. Runs locally from the better-qdrant-mcp-server npm package.