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. Each candidate is checked by a language model from its name, description and topics, and only actual MCP servers are listed (not clients, SDKs, lists or skills). Package metadata comes from ecosyste.ms (CC BY-SA 4.0). 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.
-
viveka-mcp-serverupdated this year
MCP server for structured iterative reasoning with 13 critical thinking lenses — a disciplined thinking scaffold for AI agents. Features structured reasoning state, cognitive moves (branch/revise/supersede/falsify/verify/retract/stop), Escalation Ladder,
npm MIT -
A lightweight Cognitive Scaffolding Platform that provides advanced task decomposition, metacognitive guidance, and intelligent memory for AI agents.
-
ejentum-mcpno update data
Exposes the four Ejentum cognitive harnesses (reasoning, code, anti-deception, memory) as MCP tools any agentic client can call. Drop-in scaffolding that catches LLM failure modes like sycophancy, hallucination, and reasoning shortcuts.
smithery -
fpf-thinker-assistantgithub.com/nergal-perm/fpf-thinker-assistantupdated this year
A specialized subsystem designed to guide humans and AI agents through rigorous First Principles reasoning. It acts as the "Laboratory" of the system, providing the *soft constraints* (heuristics, cognitive scaffolding, prompt engineering) required to convert vague "Problems" into structured "Hypotheses" and "Decisions".
MIT -
The methodology layer for Claude Code — 99 first-party working methods across 10 behavioral plugins. Better methods, not just more data.
oci MIT -
llama-index-tools-ejentumgithub.com/ejentum/llama-index-tools-ejentumupdated this year
LlamaIndex tool spec for the Ejentum Reasoning Harness. Wraps the hosted Ejentum MCP server and exposes 8 tools (4 harnesses × dynamic + adaptive).
pypi MIT ★ 1