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/plugins/neo4j-contrib/gds-agent/gemini-extension)<a href="https://agentmods.dev/plugins/neo4j-contrib/gds-agent/gemini-extension"><img src="https://agentmods.dev/badge/plugins/neo4j-contrib/gds-agent/gemini-extension/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/plugins/neo4j-contrib/gds-agent/gemini-extension"><img src="https://agentmods.dev/badge/plugins/neo4j-contrib/gds-agent/gemini-extension.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
gds-agent 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 3d 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
{
"name": "gds-agent",
"version": "1.1.0",
"description": "Neo4j Graph Data Science MCP server + graph-analysis skill",
"contextFileName": "GEMINI.md",
"settings": [
{
"name": "Neo4j URI",
"description": "Connection URI, e.g. neo4j://localhost:7687",
"envVar": "NEO4J_URI"
},
{
"name": "Neo4j username",
"description": "Database user",
"envVar": "NEO4J_USERNAME"
},
{
"name": "Neo4j password",
"description": "Database password",
"envVar": "NEO4J_PASSWORD",
"sensitive": true
},
{
"name": "Neo4j database",
"description": "Optional database name",
"envVar": "NEO4J_DATABASE"
},
{
"name": "Aura API client ID",
"description": "Optional: enables Aura Graph Analytics session mode",
"envVar": "AURA_API_CLIENT_ID"
},
{
"name": "Aura API client secret",
"description": "Optional: Aura Graph Analytics session mode",
"envVar": "AURA_API_CLIENT_SECRET",
"sensitive": true
},
{
"name": "Aura project ID",
"description": "Optional: only needed if the Aura API client can access multiple projects",
"envVar": "AURA_API_PROJECT_ID"
}
],
"mcpServers": {
"neo4j-gds": {
"command": "uvx",
"args": [
"gds-agent"
]
},
"neo4j-cypher": {
"command": "uvx",
"args": [
"[email protected]",
"--transport",
"stdio"
],
"env": {
"NEO4J_READ_ONLY": "true",
"NEO4J_RESPONSE_TOKEN_LIMIT": "20000"
}
}
}
}
What ships with it
1 file beside gemini-extension.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 3d ago Changed 841024afa9f5
- 24d ago First seen · 66 lines scan A cdb230ec160c
gds-agent is a plugin published in the GitHub repository neo4j-contrib/gds-agent (98 stars, last pushed 4d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-09-22.
Other plugins, from other repositories
butterbase-skills
Build full-stack apps with Butterbase — AI-Native Backend-as-a-Service. Skills for app creation, schema design, frontend deployment, RLS debugging, serverless functions, and contributing.
migrate-tool
Generate database migrations and code migration scripts for framework upgrades.
data-scientist
Data analysis expert for SQL queries, BigQuery operations, and data insights. Use proactively for data analysis tasks and queries.
cloud-sql-sqlserver
Connect to Cloud SQL for SQL Server.
sql-database-pipeline
Build SQL database pipelines with dlt: connect to any SQL source, load tables to a destination, tune performance with backends.
materialize
Materialize agent skills: docs, dbt, Terraform, mz-deploy, health checks, freshness debugging, memory tuning, and live demo data.