A local-first workbench for developing, inspecting, and benchmarking MCP servers against local (LM Studio, Ollama) or remote (OpenRouter) models —
A local-first workbench for developing, inspecting, and benchmarking MCP servers against local (LM Studio, Ollama) or remote (OpenRouter) models — Web UI, CLI, and
Building a good MCP server is empirical work, and you rarely do it alone anymore: a coding agent can run every benchmark and read every trace, but the numbers only get good when the developer stays in the loop — looking at the one run that failed, tightening a tool description or a rubric, deciding what to try next, and re-running. mcpscope is built for that partnership. It is not a benchmark harness an agent runs unattended, and not a GUI a developer drives by hand: every capability is exposed through a web UI shaped for a person and through a CLI and an MCP interface shaped for an agent, all over one shared
The server publishes 2 tools. What each one is for:
LLM — evaluate answer quality**: a separate judge model scores each run against a per-case rubric (see BENCHMARK.md)Interfaces — The Interfaces tool exposed by this serverCompare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
claude mcp add mcpscope --env BACKEND_HOST=your-value -- npx -y mcpscope| Variable | Description | Required |
|---|---|---|
| BACKEND_HOST | Endpoint or connection string the server talks to. | Optional |
The original Chromium automation reference server — simple, screenshot-driven browser control.
Build a programmable telecommunications stack for connecting telephony services with the Internet via a cloud-based utility.
Automates browsers and APIs, enabling Large Language Models (LLMs) to interact with web pages for tasks like screenshot capture and JavaScript
Workers, KV, R2 and D1 by conversation — Cloudflare's official remote servers for building and observability.
Search built for AI, not humans — semantic web search that returns model-ready content, plus code context.
Answers, not links — delegate questions to Perplexity's search-grounded models and get cited responses back.