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/humano-ai/token-reconcilerWrote 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/humano-ai/token-reconciler/token-reconciler)<a href="https://agentmods.dev/mcp/humano-ai/token-reconciler/token-reconciler"><img src="https://agentmods.dev/badge/mcp/humano-ai/token-reconciler/token-reconciler/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/humano-ai/token-reconciler/token-reconciler"><img src="https://agentmods.dev/badge/mcp/humano-ai/token-reconciler/token-reconciler.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
token-reconciler 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 10d 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
{ "token-reconciler": { "command": "npx", "args": [ "-y", "token-reconciler" ] } }
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.
- 10d ago First seen · 9 lines scan A 4aa253585e6e
token-reconciler is an MCP server published in the GitHub repository humano-ai/token-reconciler (1 stars, last pushed 19d 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
colors-le
Extract colors from stylesheets and code, with their notation and position. Runs locally from the colors-le-mcp npm package.
figma
MCP server "figma" as configured in jubscodes/get-shit-pretty. Runs locally from the @anthropic/mcp-figma npm package. Needs 1 environment variable to run.
tokens-studio-mcp
MCP server "tokens-studio-mcp" as configured in Blyawon/tokensStudioMCP. Runs locally from the tokens-studio-mcp npm package.
kiyas
AI design fidelity — compare Figma designs or screenshots against rendered UI. No API keys. Runs locally from the kiyas-cli npm package. Needs 1 environment variable to run.
ds-mcp
MCP server for exposing dspack design system corpora to AI coding agents. Runs locally from the @aestheticfunction/ds-mcp npm package.
uxlint
Audit a site's UX the way a design-literate reviewer would, with a concrete fix for every finding. Runs locally from the @uxlint-net/uxlint npm package.