MCP RTK: cut 90% of MCP server tokens

Developer Thomas Tartrau built MCP RTK, an open-source Rust proxy that sits between Claude Code and MCP servers to filter tool responses before they reach the model's context. Across more than 38,000 commands, the tool reports saving 267 million tokens at an average reduction rate of 87%, roughly $4,000 in input-token costs on Opus 4.6. MCP RTK ships as a single binary with TOML-based presets for servers like GitLab, Grafana, and Sentry, and is distributed under the MIT license.

I use Claude Code https://dev.to/blog/en/claude-code-setup-2026 every day for development. Like many developers, I've connected several MCP servers GitLab, Grafana, Sentry... to give Claude direct access to my tools. The problem: every MCP call injects tens of thousands of tokens into the context, and the bill spirals fast. I built MCP RTK https://gitlab.com/ThomasTartrau/mcp-rtk to fix this. It's an MCP proxy written in Rust that sits between Claude Code and MCP servers, filtering responses before they reach the model. Result: over 267 million tokens saved across my 38,000+ commands. The MCP protocol Model Context Protocol https://modelcontextprotocol.io/ lets Claude interact with external tools. When Claude calls an MCP tool, the server returns a JSON response. The issue is that these responses often contain: A single list issues call on GitLab can consume over 180,000 tokens. Claude only needs a fraction to answer the question. The rest is pure waste. Over a typical work session with 50 to 100 MCP calls, that easily adds up to 500,000 wasted tokens injected into the context. MCP RTK sits transparently between Claude Code and MCP servers. No workflow change needed: Claude keeps calling the same tools, but responses pass through a filtering pipeline before reaching the context. The pipeline has 8 steps: Each step is independently configurable. You can enable or disable each filter, adjust thresholds, and define server-specific rules. Configuration uses a TOML file. MCP RTK ships with community presets for popular servers: servers.gitlab preset = "gitlab" servers.grafana preset = "grafana" servers.sentry preset = "sentry" Each preset defines which fields to keep, which to exclude, and appropriate truncation thresholds for the server. For custom servers, you define rules directly: servers.my-api whitelist = "id", "name", "status", "created at" max string length = 500 max array length = 10 MCP RTK auto-detects installed MCP servers and offers to configure them. Across my 38,000+ commands, MCP RTK has saved 267 million tokens with an average reduction rate of 87%. On Opus 4.6 $15/M input tokens , that's roughly $4,000 in savings : Useful information is preserved. Claude responds with the same accuracy, but consumes far fewer tokens per session. The mcp-rtk gain command lets you track savings in real time: Tokens saved: 267.1M 86.7% Efficiency meter: █████████████████████░░░ 86.7% MCP RTK is distributed as a single binary: cargo install mcp-rtk One line change in your Claude Code config - wrap the existing MCP command with mcp-rtk -- : { "mcpServers": { "gitlab": { "command": "mcp-rtk", "args": "--", "npx", "-y", "@nicepkg/gitlab-mcp" , "env": { "GITLAB PERSONAL ACCESS TOKEN": "glpat-..." } } } } MCP RTK detects the upstream server from the command and loads the matching preset automatically. Rust was a deliberate choice. The proxy must process every MCP response with minimal latency to avoid slowing down the workflow. Rust provides: MCP RTK is published under the MIT license on GitLab https://gitlab.com/ThomasTartrau/mcp-rtk mirror on GitHub https://github.com/ThomasTartrau/mcp-rtk . Community presets are maintained by users: anyone can contribute their own configurations for new MCP servers. The project is part of a tooling ecosystem I'm building around Claude Code, alongside Skill Radar https://gitlab.com/ThomasTartrau/skill-radar detecting repetitive patterns in sessions and Claude Deck https://github.com/ThomasTartrau/claude-deck multi-workspace for parallel sessions . To learn how to write your own skills, see the guide on effective skills https://dev.to/blog/en/writing-effective-claude-code-skills . The project page https://dev.to/projects/mcp-rtk has installation links and documentation.