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.
-
cortexgithub.com/tsubasa-rsrch/cortexupdated this year
Cognitive-science-based perception framework for AI agents. Habituation, circadian rhythm, scheduling, notifications — stdlib-only, zero dependencies.
MIT ★ 3 -
mcp-memory-servergithub.com/yaowubarbara/mcp-memory-serverupdated this year
MCP server with cognitive-science-based memory decay and consolidation for AI agents
★ 1 -
.NET SDK and MCP server implementing a cognitive science-based 3-axis memory system (type x scope x tier) for LLM context management beyond finite context windows.
nuget MIT ★ 1 -
An open-source MCP server that turns any LLM into an Intelligent Tutoring System. 50 years of cognitive science, MIT licensed.
go MIT ★ 103 -
MCP server for meta-cognitive reasoning strategies and problem resolution.
npm (MIT AND Apache-2.0) -
C4REQBERgithub.com/C4MIND/C4REQBERupdated this year
Read-only mirror of c4reqber (primary repo on GitLab). Cognitive exoskeleton for AI agents and humans: discovery pipeline, formal verification, 21 MCP tools, terminal-first UX. pip install c4reqber. Issues/PRs: GitLab only.
NOASSERTION ★ 1 -
aseke-compass-mcpgithub.com/angrysky56/aseke-compass-mcpupdated this year
Building systemic discernment directly into a population, to recognize how their biological levers are being pulled by external leadership or algorithms—shifts the Cognitive Effort required for an Information System to capture the SEEKING system.
-
lensgithub.com/frescodicredito/lensupdated this year
Cognitive infrastructure for LLM reasoning — an MCP server that wraps problems in structural cognitive constraints and runs multi-agent analysis. Navigate the tails of the distribution.
MIT -
bullet-mcpupdated this year
MCP server for evidence-based bullet point summarization guidance
npm MIT -
psychopy-mcpgithub.com/hackerunner/psychopy-mcpupdated this year
Drive PsychoPy from Claude Code / Codex via MCP — 14 literature-grounded experiment paradigms, run/compile/introspect, live window, desktop launcher.
MIT ★ 1 -
bullet-mcpgithub.com/nikkoxgonzales/bullet-mcpupdated this year
MCP server for evidence-based bullet point validation. Scores lists against cognitive research (Miller's Law, serial position effects) with actionable feedback.
MIT ★ 1 -
steelmind-mcpgithub.com/stabgan/steelmind-mcpupdated this year
Research-grounded structured thinking + steel-manning verification for AI agents via MCP. Sequential step tracking with cognitive mode separation. Backed by 43+ papers.
npm MIT ★ 1 -
Cross-platform persistent memory MCP for Codex, Gemini CLI, Claude Code, and other local MCP hosts. 36 cited neuroscience mechanisms, local-first SQLite/PostgreSQL, hybrid retrieval, decay-based consolidation, and reproducible benchmarks. Claude adds optional automatic lifecycle hooks.
pypi MIT ★ 77 -
AttentionOSgithub.com/zhonghaozhan/AttentionOSupdated this year
60s attention span test + desktop pet + attention://state MCP for agents. Local-first human attention observability. 60秒注意力测试 · 桌宠 · 注意力观测
★ 4 -
Temporal memory system for AI assistants with human-like forgetting curves. All data stored locally in human-readable formats: JSONL for short-term memory, Markdown (Obsidian-compatible) for long-term. Memories naturally decay unless reinforced. Features knowledge graphs, smart prompting, and MCP server integration for Claude.
pypi AGPL-3.0 ★ 39 -
🎓 ICIL — Intelligence Campus Interactive Library. 243 courses · 32 faculties · 10 MCP tools. Curated context injection for AI agents. P@3=86.5%, R@3=98.9%.
MIT