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.
npx agentmods add mcp/rctruta/sql-benchmarks-dagster/sqlbenchdaggit clone --depth 1 https://github.com/rctruta/sql-benchmarks-dagsterGrade A, and why
sqlbenchdag 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 yesterday.
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
{ "sqlbenchdag": { "command": "uvx", "args": [ "sqlbenchdag" ], "env": { "SB_RESULTS_DIR": "", "SB_API_BASE": "" } } }
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.
- yesterday First seen · 12 lines scan A 086420d77562
sqlbenchdag is an MCP server published in the GitHub repository rctruta/sql-benchmarks-dagster (2 stars, last pushed 1mo 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 2026-08-31.
Other mcp servers, from other repositories
graphjin
MCP server "graphjin" as configured in dosco/graphjin. Launched with graphjin mcp --path ${GRAPHJIN_CONFIG_PATH:-./config}.
mcp-read-only-sql
MCP server "mcp-read-only-sql" as configured in lukleh/mcp-read-only-sql. Runs locally from the . Python package.
playwright
Lets the agent drive a real browser: open pages, click, type, take screenshots and read the accessibility tree, using Playwright. Runs locally from the @playwright/mcp npm package.
dryrun
PostgreSQL schema intelligence from a committed snapshot. No connection, no credentials. Runs locally from the @boringsql/dryrun npm package.
streams
MCP server "streams" as configured in slotix/dbconvert-streams-public. Launched with https://github.com/slotix/dbconvert-streams-public/releases/download/v2.7.1/dbco.
placeroot
Ground AI agents in open map data. MCP server for Overture Maps — compact answers, no API key. Runs locally from the placeroot Python package. Needs 1 environment variable to run.