Faceabot

Catalog › io.github.base76-research-lab/token-compressor

Is token-compressor reliable?

Not measured yet token-compressor runs locally (installed package), so Faceabot cannot measure it over the network.

En français : Pas encore mesuré. Faceabot teste cet outil lui-même, en continu, sans dépendre de ce que son auteur affirme.

What it does

Compress prompts 40-60% using local LLM + embedding validation. Preserves all conditionals.

Source: official MCP registry (registry.modelcontextprotocol.io) · version 0.1.1 · publisher website
Connect your agent
{
  "mcpServers": {
    "token-compressor": {
      "command": "uvx",
      "args": [
        "token-compressor-mcp"
      ]
    }
  }
}
Or ask Faceabot first: MCP tool check_reliability {"id":"io.github.base76-research-lab/token-compressor"} on https://faceabot.com/api/mcp.
Does it actually do the job?

— Faceabot asked to do a small read-only task undefined time(s): undefined returned a real result. Last result: .

Sample input: {}. A success means a non-empty result without error; it does not certify the accuracy or safety of the content.
Faceabot measurements

No measurement yet.

Method: MCP initialize then tools/list from Faceabot (FaceabotProbe/1.0), plus one read-only tool call with a neutral input when the server declares one, repeated over time. This checks that the server is up and speaks MCP correctly; it does not certify the quality or safety of each tool. How measurement works.

Similar tools

Execute brotli-prompt-compressor-mcp Not measured yet

Premium agentic endpoint for brotli-prompt-compressor-mcp.

MCP endpoint : https://api.m2mcent.com/brotli-prompt-compressor-mcp/sse · measurements and details
TokenSqueezer LLM Token Compressor Not measured yet

x402-gated LLM token compressor: strip filler, collapse JSON, densify prose. Paid in USDC.

Package npm : @nodeproxy/tokensqueezer · website · measurements and details
CompactPrompt Not measured yet

Review and compact prompts, docs, and AI-agent skills to save tokens, preserving structure.

Package pypi : compactprompt · website · measurements and details
.prompts Not measured yet

.prompts, the home to all your AI prompts, everywhere you need them.

MCP endpoint : https://dotprompts.com/mcp · website · measurements and details
llmtrim Not measured yet

MCP server and proxy that compresses LLM prompts, tool output, and replies to cut token cost.

Package npm : @llmtrim/cli · website · measurements and details
Publisher of token-compressor?

Show your measured reliability on your README or website:

Faceabot reliability badge for token-compressor

[![Measured by Faceabot](https://faceabot.com/badge/io.github.base76-research-lab/token-compressor.svg)](https://faceabot.com/tools/io.github.base76-research-lab/token-compressor)
Data in JSON: /api/catalog?id=io.github.base76-research-lab/token-compressor · Stop probes: POST /api/reliability/opt-out

AI agents: all of this is available without keys over MCP https://faceabot.com/api/mcp · HTTP https://faceabot.com/api/catalog?q=… · Guide : llms.txt

Pulse: what is changing in agent commerce · Is your store ready for AI shopping agents? · State of MCP (weekly) · MCP server doctor · Open reliability data