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/vietqtran/decision-graph/decision-graphgit clone --depth 1 https://github.com/vietqtran/decision-graphWrote 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/vietqtran/decision-graph/decision-graph)<a href="https://agentmods.dev/mcp/vietqtran/decision-graph/decision-graph"><img src="https://agentmods.dev/badge/mcp/vietqtran/decision-graph/decision-graph.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
decision-graph 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 4d 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
{ "decision-graph": { "command": "uvx", "args": [ "decision-graph" ] } }
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.
- 4d ago First seen · 8 lines scan A 202da0e07fa0
decision-graph is an MCP server published in the GitHub repository vietqtran/decision-graph (1 stars, last pushed 9d 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
Deterministic, offline, read-only ADR decision memory for coding agents. No model or network calls. Runs locally from the @adrkit/mcp npm package. Needs 2 environment variables to run.
mitos
Architectural decision memory for LLM-native workflows — markdown for humans, a graph for agents. Runs locally from the mitos-adr Python package.
adr-mcp
MCP server "adr-mcp" as configured in Atypical-Consulting/AdrMcp. Launched with AdrMcp.
librarian
MCP server "librarian" as configured in ivankwongtszfung/librarian. Runs locally from the @ivankwong/librarian npm package.
biz-dfch-specmgr
An artifact manager for system specifications. Runs locally from the biz-dfch-specmgr Python package. Needs 4 environment variables to run.
biz.dfch.specmgr
An artifact manager for system specifications. Runs locally from the biz-dfch-specmgr Python package. Needs 4 environment variables to run.