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.
-
Multi-domain scientific dataset fetcher (neuroscience, biology, medical)
pypi AGPL-3.0 ★ 1 -
pd-discovery-platformgithub.com/bmh2127/pd-discovery-platformupdated this year
CrewAI multi-agent research platform with custom MCP servers for biomarker discovery and target identification in preclinical neuroscience
MIT -
Neuroscience-inspired memory for AI agents — sleep cycles that rewrite and strengthen knowledge over time. TypeScript, PostgreSQL, MCP.
npm MIT ★ 15 -
io.github.brain-bbqs/neurogithub.com/brain-bbqs/neuromcpno update data
Neuroscience MCP server (Python)
npm -
alayagithub.com/securityronin/alayaupdated this year
A memory engine for conversational AI agents, inspired by neuroscience and Buddhist psychology
cargo MIT -
Local AI memory: neuroscience-inspired Data→Information→Knowledge in SQLite you own.
npm MIT ★ 3 -
MCP server for accessing and querying BrainKB’s neuroscience knowledge graph.
-
mnemosynthgithub.com/VasudevJaiswal/mnemosynthupdated this year
🧠 MNEMOSYNTH — Universal AI Memory Plugin: Persistent, verified, hallucination-resistant memory for ANY AI system. Neuroscience-inspired cognitive patterns, zero-config setup, MCP server for Claude/Cursor/Windsurf. Python + VS Code extension.
NOASSERTION -
flowzen-mcpgithub.com/deng-diana/flowzen-mcpupdated this year
An MCP server for Claude that answers with one task to do right now, chosen from your task list, the time of day and your current energy, with the neuroscience reason attached. TypeScript, Supabase.
-
Persistent memory for AI agents — 60 MCP tools, spreading activation recall, neuroscience-inspired consolidation. Works with Claude, GPT, Gemini.
pypi MIT -
Provide AI agents with long-term memory using a neuroscience-based knowledge graph and Model Context Protocol for improved coding assistance.
NOASSERTION ★ 1 -
Search and read public neuroscience data from your coding agent: DANDI, OpenNeuro, NeuroMorpho, Allen and BrainGlobe. Reads NWB files remotely, with a license and citation for every dataset. MCP server, CLI and skills.
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 -
ne-mcp-eeggithub.com/giulioruffini/ne-mcp-eegupdated this year
MCP server for EEG analysis with Neuroelectrics data formats
pypi Apache-2.0 -
Next-Gen Connectome Data Analysis
MIT ★ 9 -
Brain-inspired long-term memory for AI agents — zero LLM during ingest or retrieval
pypi AGPL-3.0-or-later -
The somatic vocabulary for AI agents. 29 zones, 20 qualities, 16 territories. MCP integration.
NOASSERTION -
MCP server for read-only analysis of intracortical (spike-level) brain-computer-interface recordings
pypi CC0-1.0 ★ 1 -
Self-hosted, brain-inspired memory + permissions for AI agents. MCP-native. One SQLite file.
pypi Apache-2.0 -
Motor-imagery EEG pipeline with a hand-written signal core, validated against MNE, exposed as an MCP server
MIT ★ 2 -
MCP server for ABBA (Aligning Big Brains and Atlases): an AI assistant registers brain sections to atlases in a pinned Fiji
pypi MIT -
floopgithub.com/nvandessel/floopupdated this year
Spreading activation memory for AI coding agents - corrections in, context-aware behaviors out.
go Apache-2.0 ★ 26 -
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 -
Cortexgithub.com/somarakis/Cortexupdated this year
A cognitive layer for Claude Code — inspired by how brains actually work
MIT -
SSTIM living reference MCP for the senses, stimuli, perception, research, technology and reviewed community proposals.
npm Apache-2.0 -
neuroencoderactive
EEG embeddings API client, CLI and MCP server for EPI-300K, an EEG foundation model
pypi Apache-2.0 -
MCP server for building connectome analysis workflows in Coda (coda.science) — neuPrint, CAVE/FlyWire, CATMAID — from Claude, ChatGPT or any MCP client.
MIT -
Index and search Markdown vaults as knowledge graphs to provide AI agents with persistent, structured long-term memory across sessions.
Apache-2.0 ★ 2 -
Memory OS AI — Adaptive memory system for AI agents (forked from RoaminS/Memory-os-ai)
pypi GPL-3.0 ★ 3 -
Real-time Windows computer use for AI agents over MCP: screen perception, bounded reflexes, closed-loop motor control, and experimental fly-connectome controllers.
MIT -
mne-docs-mcpgithub.com/weiyongxu/mne-docsupdated this year
DEPRECATED - superseded by the 'mne-docs' Python package on PyPI. MCP server for MNE-Python documentation, source code, GitHub issues, and forum.
npm MIT -
Find cells in the MICrONS mouse visual cortex EM dataset in plain language and open them in Neuroglancer, from any AI (MCP server, CLI, Python).
MIT ★ 1 -
metcoregithub.com/hopenmind/metcoreupdated this year
Neural memory diagnostics engine based on the Markov Embedding Theorem (MET). Includes a Python library, a 17-tool Model Context Protocol (MCP) server for LLMs, and a cross-platform desktop GUI.
NOASSERTION -
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.