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/uttambharadwaj/kb-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/uttambharadwaj/kb-graph/kb-graph)<a href="https://agentmods.dev/mcp/uttambharadwaj/kb-graph/kb-graph"><img src="https://agentmods.dev/badge/mcp/uttambharadwaj/kb-graph/kb-graph/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/uttambharadwaj/kb-graph/kb-graph"><img src="https://agentmods.dev/badge/mcp/uttambharadwaj/kb-graph/kb-graph.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
kb-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 1mo 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
{ "kb-graph": { "command": "npx", "args": [ "-y", "kb-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.
- 1mo ago First seen · 9 lines scan A d55302fe3467
kb-graph is an MCP server published in the GitHub repository uttambharadwaj/kb-graph (4 stars, last pushed 11d 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
knowit
Shared team memory for AI coding agents — MCP server and CLI for persistent, queryable knowledge across sessions and teammates. Runs locally from the knowit npm package.
centered-agent-memory
MCP server "centered-agent-memory" as configured in arlinamid/centered-agent-memory. Runs locally from the centered-agent-memory npm package.
repowise
MCP server "repowise" as configured in 2233admin/obsidian-llm-wiki. Launched with repowise mcp D:/projects/obsidian-llm-wiki --transport stdio.
exomem
MCP server "exomem", hosted remotely at exomem.substratesystems.io, as configured in Artexis10/exomem.
kage
Verified memory for coding agents: claims cited against code, stale withheld, savings receipts. Runs locally from the @kage-core/kage-graph-mcp npm package.
burn-mcp-server
Burn MCP — give your AI agent a reading workflow. 26 tools to search, triage, burn, vault, and analyze your saved articles. Works with Claude, Cursor, Windsurf. Runs locally from the burn-mcp-server npm package. Needs 1 environment variable to run.