Token Enhancer runs on your own machine — the client starts it, so there is no endpoint to ping. 29 installs a week from pypi. Last commit 3 Apr 2026.
Cuts AI web-fetching costs up to 99.9% by stripping page junk before it reaches your LLM.
Nothing serious here today
Today is the operative word: we check Token Enhancer every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Connect this server
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 token-enhancer -- uvx xelektron-token-enhancer{
"mcpServers": {
"token-enhancer": {
"args": [
"xelektron-token-enhancer"
],
"command": "uvx"
}
}
}[mcp_servers.token-enhancer]
command = "uvx"
args = ["xelektron-token-enhancer"]{
"mcpServers": {
"token-enhancer": {
"args": [
"xelektron-token-enhancer"
],
"command": "uvx"
}
}
}{
"mcpServers": {
"token-enhancer": {
"args": [
"xelektron-token-enhancer"
],
"command": "uvx"
}
}
}Alternatives to Token Enhancer
same job, measured the same wayBlock prompt injection, evasive spacing, and obscene content before it reaches your LLM.
Reports real token usage and cost from Claude Code and OpenCode data. Nothing leaves your machine.
Redact PII from text before it reaches a model. Nothing stored, no third-party AI.
Publish a site your AI built to paid hosting, then read it back, change a page or restore a version.
Redacts PII/PHI from text before it reaches an LLM. Fail-closed, self-hosted, no egress.
Pin visual feedback on any live web page and send it to Claude Code, Cursor or your AI agent.
Index your codebase. AI searches instead of re-reading files. 94% token savings.
Web grounding for local & cloud LLMs: search, fetch, token-capped evidence packs, and research.
Token Enhancer — questions
Answers built from our own checks of this server.