tokensaver

Fewer tokens, every page. A local MCP server that turns web pages, PDFs, Office files and JSON into compact text for your coding agent.

A 183,000-token Wikipedia article becomes 19,000 — or a 250-token outline, so the agent reads only the section it needs.

Watch the 10-second intro on YouTube

• Local. One Go binary. No API keys, never calls an LLM, no telemetry unless you opt in.

• Nothing else to install. PDF support is built in. Chrome is optional (for pages that need JavaScript).

Install

brew tap use-tokensaver/tokensaver
brew install tokensaver

No Homebrew, or on Windows? Download a binary from Releases and put it on your PATH.

Or run it with Docker: docker run -i --rm ghcr.io/use-tokensaver/tokensaver (how to connect it).

Related MCP server: daimonos

Connect

claude mcp add --scope user tokensaver -- tokensaver

Cursor, Claude Desktop, other MCP clients — add this server and restart:

{ "mcpServers": { "tokensaver": { "command": "tokensaver" } } }

Use

You don't call it yourself — just ask your agent:

read https://go.dev/doc/effective_go with tokensaver
outline https://arxiv.org/pdf/1706.03762 with tokensaver, then read just the Attention section
read https://github.com/use-tokensaver/tokensaver/pull/16 with tokensaver
fetch https://api.github.com/search/repositories?q=language:go with tokensaver — just full_name and stargazers_count, as a table

Reads: web pages, PDF, DOCX, XLSX, PPTX, JSON, diffs and PRs, ZIP, log files, folders, and any text file.

How much it saves

Measured on real sources (tokens ≈ characters ÷ 4; reproduce with TOKENSAVER_LIVE=1 go test ./e2e/ -run Live -v):

Learn more

Docs — every option, configuration, telemetry and security notes. Developing it? go test ./..., and see CLAUDE.md for the layout and release flow.

MIT licensed — see LICENSE.