Tokentrust runs on your own machine — the client starts it, so there is no endpoint to ping. 170 installs a week from pypi. Last commit 25 Sep 2026.
Verifies token/cost savings claimed by AI context-reduction proxies via MCP tools.
We read the source, 18 h ago · rules ccca72095570
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
completed = subprocess.run(
env = deps.env if deps.env is not None else dict(os.environ)
Found in continuous integration, deployment or infrastructure files, or in a neighbouring package of the same monorepo. None of this is installed when you add the server: it describes how the project is built and released. We list it because a leaked key in a build pipeline is still a real problem, but it is not something this server does on your machine.
const child = spawn(binary, args, { env: scrubEnv(process.env) });
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add tokentrust -- uvx tokentrust-cli
{
"mcpServers": {
"tokentrust": {
"args": [
"tokentrust-cli"
],
"command": "uvx"
}
}
}
[mcp_servers.tokentrust]
command = "uvx"
args = ["tokentrust-cli"]
{
"mcpServers": {
"tokentrust": {
"args": [
"tokentrust-cli"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"tokentrust": {
"args": [
"tokentrust-cli"
],
"command": "uvx"
}
}
}
AI-optimized GitHub MCP server: 112 tools, 98% token reduction, compact responses.
Verified context layer for AI coding agents — prunes, compresses, indexes, remembers. 32 MCP tools.
Unified MCP & Skill management gateway, shared across AI agents, 99% context token savings
Reduces AI agent token usage by 90% via context compression and task checkpoint persistence.
Verifies Ed25519-signed attestation records and builds audit reports via MCP tools.
Known MCP tool-call failures and workarounds verified by reproduction.
MCP proxy that lazy-loads tool schemas to cut context token overhead by 6-7x
Stateless MCP server that proxies research queries to Gemini CLI, reducing agent context/model usage
Answers built from our own checks of this server.