Token Compressor MCP Server

Semantic prompt compression for LLM workflows. Reduce token usage by 40–60% without losing meaning. It runs locally over stdio via the published package.

People connecting this server to Claude, Cursor, VS Code, or another MCP client. The project is written in Python.

VERIFIED ACTIVE

LAST COMMIT 2026-03-08 · ★ 10 · #599 OF 848 MAINTAINED OTHER · VERIFIED 2026-08-25

MIT · Python servers · how we verify → /methodology

01 · Install Token Compressor

Claude Code

claude mcp add base76-research-lab-token-compressor -- uvx token-compressor-mcp

Claude Desktop / Cursor / VS Code - add to config

{
  "mcpServers": {
    "base76-research-lab-token-compressor": {
      "command": "uvx",
      "args": [
        "token-compressor-mcp"
      ]
    }
  }
}

Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.

Using another client? Same JSON, different key

Claude Desktop · mcpServers

Cursor · mcpServers

VS Code · servers

Windsurf · mcpServers

Zed · context_servers

Cline · mcpServers

Roo Code · mcpServers

Continue · mcpServers

LibreChat · mcpServers

Gemini CLI · mcpServers

Codex CLI · mcp_servers

Full setup guides: every client.

02 · Evidence

Security posture

What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.

runs as local process (stdio) - runs on your machine with your user's permissions

license MIT - declared in the repository

pypi package token-compressor-mcp - check the name against the project README before installing (PyPI has no namespace ownership)

registry namespace io.github.base76-research-lab is GitHub-verified and matches the repo owner

03 · Who maintains Token Compressor

token-compressor is maintained by base76-research-lab. We track 3 MCP servers from base76-research-lab - 1 actively maintained, 11 combined GitHub stars, oldest repo from Feb 2026.

04 · Facts

repository: github.com/base76-research-lab/token-compressor
category: other - ranked #599 of 848 actively-maintained other servers as of 2026-08-25.
registry: io.github.base76-research-lab/token-compressor (active, first published 2026-03-03)
packages: pypi:token-compressor-mcp

05 · Token Compressor FAQ

What is Token Compressor?

Semantic prompt compression for LLM workflows. Reduce token usage by 40–60% without losing meaning. It runs locally over stdio via the published package.

Is Token Compressor still maintained?

Yes - as of 2026-08-25, its last commit was 2026-03-08. We re-verify nightly.

How do I install Token Compressor?

Run `uvx token-compressor-mcp`. You can also paste the ready-made client config above.

Does Token Compressor run locally?

Yes - it's a stdio server: it runs on your machine (via uvx) with your user's permissions. Your data stays local unless the server itself calls external APIs.

06 · Alternatives to Token Compressor

Alternatives to Token Compressor

Maintained other servers if Token Compressor isn't the fit.

More MCP servers to compare · Forums · Myco: Agent-First Cognitive Substrate · Janusmcp · Daimonos · AXON Epistemic MCP (bemarking)

More Python MCP servers · Basic Memory · Omni Seek · Bawbel Scanner · Agentfetch · Beever Atlas · see all