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/johnnywuj81/tokenknowsWrote 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/johnnywuj81/tokenknows/tokenknows-mcp-tokenknows)<a href="https://agentmods.dev/mcp/johnnywuj81/tokenknows/tokenknows-mcp-tokenknows"><img src="https://agentmods.dev/badge/mcp/johnnywuj81/tokenknows/tokenknows-mcp-tokenknows/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/johnnywuj81/tokenknows/tokenknows-mcp-tokenknows"><img src="https://agentmods.dev/badge/mcp/johnnywuj81/tokenknows/tokenknows-mcp-tokenknows.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
tokenknows 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 8d 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.
This is a copy
91% identical to tokenknows — 11 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
{
"tokenknows": {
"command": "uvx",
"args": [
"tokenknows-mcp"
],
"env": {
"TOKENKNOWS_API_BASE": "http://127.0.0.1:8001",
"TOKENKNOWS_API_TOKEN": "",
"TOKENKNOWS_DEFAULT_PROJECT": "proj-demo-001",
"TOKENKNOWS_WEB_BASE": "http://127.0.0.1:5173"
}
}
}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.
- 8d ago First seen · 14 lines scan A 17441c06e43d
tokenknows is an MCP server published in the GitHub repository johnnywuj81/tokenknows (4 stars, last pushed yesterday), 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. It is 91% identical to tokenknows, differing in 11 lines, and is treated as a copy.
Other mcp servers, from other repositories
levh
Local-first memory layer for AI agents and humans. Runs locally from the levh Python package.
devcodex-memory
MCP server "devcodex-memory" as configured in devcodex-labs/devcodex. Runs mcp/memory-server.js with node.
aidex
Persistent code indexing for AI assistants. 50x less context than grep. 11 languages. Runs locally from the aidex-mcp npm package.
engram
Ranked local code-graph context for AI coding agents. Intercepts reads + greps. Apache-2.0. Runs locally from the engramx npm package. Needs 5 environment variables to run.
codebase-memory
MCP server "codebase-memory" as configured in BernhardJackiewicz/architect-to-product. Launched with codebase-memory-mcp.
faf-mcp
Dedicated IDE Edition. Persistent project context for Cursor, Windsurf, Cline, VS Code. Runs locally from the faf-mcp npm package.