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.
-
MCP server for web search that extracts relevant excerpts instead of summarizing. BM25 + structural heuristics surface the actual Stack Overflow answer, GitHub discussion, or docs paragraph you need. No LLM summarization layer, just IR-based extraction.
npm MIT ★ 2 -
Rank a GitHub repo's dependents by stars or trust heuristic, and search their code — CLI and MCP server.
pypi MIT ★ 1 -
tubemind-secure-mcpgithub.com/dewtech-technologies/tubemind-secure-mcpupdated this year
Secure MCP server for YouTube intelligence — 18 tools (search, analytics, benchmark, heuristics, competitor research) for Claude Desktop. OAuth2 + AES-256-GCM + OWASP Top 10.
npm MIT -
Algorithms you can watch — and that an agent can drive, live, on the exact page you're looking at. Real search + sort algorithms run as Python in your browser (Pyodide), exposed as WebMCP tools. Human and agent share one live state, and either can empirically verify a heuristic or comparator.
MIT -
heuristic-mcpgithub.com/softerist/heuristic-mcpupdated this year
Enhanced MCP server for semantic code search with call-graph proximity, recency ranking, and find-similar-code. Built for AI coding assistants.
npm MIT ★ 20 -
An open-source heuristic engine & CLI for detecting phantom job postings, resume harvesting traps, and corporate hiring theater.
MIT -
inquisitorgithub.com/iamalisson/inquisitorupdated this year
Hypothesis-driven problem solving for AI agents: probe, falsify, escalate — never blind-retry. MCP server + agent skill built on Newton, Popper, and NASA's P10
MIT ★ 5