MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
pictmcpgithub.com/takeyaqa/pictmcpupdated this year
MCP (Model Context Protocol) server that provides pairwise combinatorial testing capabilities to AI assistants.
npm MIT -
Pairwise / t-wise combinatorial coverage for AI-written tests — check what a suite misses, generate the minimum matrix, extend it without rewriting. A Claude Code plugin and a standalone MCP server, backed by the coverwise WASM engine.
Apache-2.0 -
Deterministic Zero-Trust test design engine: Pairwise & N-way combinatorics with business constraints, bidirectional requirement traceability, and BDD exporters. MCP-ready.
MIT ★ 1 -
rigorgithub.com/mrnh/rigoractive
Verified statistical inference for AI agents -- classical and non-parametric hypothesis testing, correlation/regression, effect sizes, power/sample-size, multiple-comparisons correction, a test-recommendation helper, and a batch pairwise-comparison tool, as a CLI and an MCP server
MIT ★ 1 -
MCP server for the Woodstitch API: paid human listeners judge your text-to-speech audio in blinded pairwise preference or human-vs-AI detection studies.
pypi MIT -
MCP server for the Woodstitch API: paid human listeners judge your text-to-speech audio blind (pairwise preference or human-vs-AI detection). Not MOS.
MIT