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.
-
Thin MCP server for OrionBelt Semantic Layer — delegates to REST API
pypi Apache-2.0 -
MCP server for using the DBT Semantic Layer API
npm MIT -
MCP server for the OrionBelt Semantic Layer. Enables LLMs to explore semantic models, compile queries, and execute analytics via natural language. Works with Claude, Cursor, Windsurf, Copilot.
Apache-2.0 ★ 3 -
Source-available semantic and context layer, rule engine, and semantic sidecar for agentic AI and governed analytics. Compiles declarative YAML models into optimized SQL, KPIs, and semantic context across 8 SQL dialects.
pypi NOASSERTION ★ 104 -
A read-only MCP server for SQL databases with a semantic layer in an open format (Apache Ossie), metrics, your own context and skills — for any database and any MCP client.
Apache-2.0 -
Open source AI data analyst that answers questions about your data in plain English. Governed by a dbt semantic layer, runs locally on DuckDB, refuses to guess when it is unsure, and publishes execution accuracy on every commit. Text to SQL you can put in a board deck.
MIT ★ 1 -
Ask questions about your metrics in plain English, answered only through a MetricForge semantic layer. MCP server + Claude API CLI.
MIT -
MCP server for Tableau Knowledge: semantic search, lineage, impact, Business Preferences checks, and semantic-layer porting via Apache Ossie (OSI), from any MCP client.
MIT -
NVIDIA Auto Ontology's semantic layer and a personal knowledge base as an MCP server for Claude, ChatGPT and other MCP clients. No LLM API key needed.
Apache-2.0 ★ 419 -
High-speed shared semantic & hybrid memory layer for AI agents — MCP server, CLI, and Python library
pypi MIT -
GA-Bagua Semantic KG: LLM semantic memory layer using Geometric Algebra and I-Ching Bagua taxonomy
-
Local memory MCP server for coding agents like Claude Code and Codex - Three-layer architecture with semantic search, knowledge graphs, and intelligent retrieval
npm MIT -
@iflow-mcp/renefichtmueller-papercortexupdated this year
Self-hosted AI intelligence layer for Paperless-ngx with semantic search, receipt extraction, and MCP Server integration
npm MIT -
ai-longterm-wiki-memory-ClaudeCodegithub.com/giovannifrontera/ai-longterm-wiki-memory-ClaudeCodeupdated this year
Persistent semantic memory for Claude Code. Three-layer wiki + LanceDB vectors, hooks, self-healing lint, knowledge graph. Native MCP integration.
AGPL-3.0 ★ 1 -
Zero-knowledge persistent memory layer for LLMs — AES-256-GCM encrypted, semantic search via Qdrant, MCP server for Claude Desktop / Sovereign European MCP memory layer — self-hostable, AGPL v3
NOASSERTION ★ 1 -
agentic-memorygithub.com/Verace-Pvt-Ltd/agentic-memoryupdated this year
6-layer persistent memory (sensory, working, episodic, semantic, long-term, procedural) with non-destructive belief revision and injection-safe context synthesis — an MCP server for Claude Code, Cursor, Antigravity, Codex CLI, and any MCP-compatible agent.
MIT ★ 1 -
querywise-mcpgithub.com/kosminus/querywise-mcpupdated this year
An MCP server (and a CLI) that lets an LLM query your databases in natural language through a business semantic layer — glossary, metric definitions, data dictionary, knowledge base, and example queries — grounded against your real schema.
MIT ★ 3 -
An MCP (Model Context Protocol) layer that exposes sktime’s native registry and semantics to an LLM
BSD-3-Clause ★ 31 -
jamjet-engramgithub.com/jamjet-labs/engramupdated this year
Engram — durable memory layer for AI agents. Temporal knowledge graph, semantic search, and MCP-native tools.
pypi Apache-2.0 -
dokorogithub.com/bypawel/dokoroupdated this year
Multi-layer agent-memory MCP server (working, episodic, semantic, procedural, affective) for Claude Code and any MCP client.
npm MIT -
Local-first semantic file organism layer — transforms your filesystem into a living knowledge graph for humans and AI agents
MIT ★ 2 -
protocontextgithub.com/protocontext/protocontextupdated this year
Deterministic knowledge layer for RAG systems. Open standard + search engine + semantic retrieval for AI-readable web content.
Apache-2.0 ★ 2 -
amemgithub.com/amanasmuei/amemupdated this year
The memory layer for AI coding tools. Local-first, semantic, works with Claude Code, Cursor, Windsurf & any MCP client.
MIT ★ 2 -
The semantic layer for software engineering: Connect code to meaning, build on understanding
Apache-2.0 ★ 39 -
Multi-layer agent memory MCP server — working, episodic, semantic, procedural & affective — for Claude Code and any MCP client.
MIT ★ 3 -
Zero-knowledge persistent memory layer for Claude — AES-256-GCM encrypted, semantic search, EU hosted. MCP server for Claude Desktop.
MIT ★ 1 -
mailbox-mcpgithub.com/JMauricioVLJunior/mailbox-mcpupdated this year
Self-hosted MCP server: any IMAP mailbox + CalDAV calendar for AI agents, with multi-user OAuth (mailbox password = login) and a semantics layer
MIT ★ 1 -
The trust and intelligence layer between AI agents and your database. Read-only by architecture, semantic knowledge graph + audit log, MCP-native.
Apache-2.0 ★ 12 -
cell-memgithub.com/Aether-liusiqi/cell-memupdated this year
Brain-inspired memory system for AI agents. Four memory layers (working, episodic, semantic, procedural) with consolidation, self-reflection, generative replay, and creative hypothesis discovery. Ships as an MCP server for Claude Code & Codex CLI.
MIT ★ 1 -
🛡️ Rust CLI extension for Claude Code — LLM-powered command validation, SQLite context persistence & MCP tools. Two-layer safety (rules + Ollama), vector semantic search, and user-adaptive learning.
MPL-2.0 ★ 1 -
Scoped, least-privilege MCP access to Home Assistant. Per-token permissions, capabilities, approvals, auditing, and a per-entity semantic safety layer. Uses a built-in client, Voice Assist, or external clients.
MIT ★ 1 -
Design-token discipline layer for AI-generated codebases. Lints DESIGN.md, enforces explicit > atlas > palette precedence, and ships an MCP server agents can call. +149.98% lift in semantic-token conformance.
MIT -
Chat-native analysis of official statistics: an MCP server and Python library to find indicators, build a semantic layer, and chart them from your AI agent.
Apache-2.0 -
Starlight Intelligence System — substrate (SIP protocol, alliance forging method, attestation) + reference operational layer (6 semantic vaults, SQLite hybrid retrieval, temporal reasoning, MCP server, platform adapters, sanitization gateway, empirical sa
npm MIT -
ai-memory-vaultgithub.com/munikumar-pulikanti/ai-memory-vaultupdated this year
Persistent memory layer for AI coding agents — SQLite + FTS, ChromaDB semantic search, and optional DynamoDB team sync. Query-first, so agents check accumulated knowledge before touching Jira, AWS, or code.
MIT ★ 1 -
SessionRelay: a local-first, session-level memory layer for AI coding agents — 5-source capture · Chinese+semantic search · 16 MCP tools · right to be forgotten · HOP handoff | 会话接力:本地优先的 AI 编程会话记忆层
MIT ★ 2 -
The open retrieval layer for AI coding agents. Indexes code, docs, legal, research, data — 24 parsers (incl. EPUB, DOCX, ODT, MIDI, audio), FTS5 + semantic search, knowledge graph. Serves surgical context via MCP. Open source, local, free.
pypi MIT ★ 27 -
cctx-optimizergithub.com/anil7948/cctxupdated this year
Reduce Claude Code token usage by 70-90% with cross-session memory and four-layer optimization: semantic codebase indexing, PostToolUse tool compression, turn summarization, and session consolidation. MCP server powered by Ollama — zero API calls, runs en
npm MIT -
Local, persistent memory for AI agents (MCP server). Plain JSON on your disk; fact-level search with an optional local semantic layer; corrections replace old facts; stale-value warnings; secrets kept out; a browser page to read, edit and merge it. One command installs it in Claude Code, Claude Desktop, Codex and Cursor.
npm MIT ★ 8 -
ai-memory-layergithub.com/NishantJLU/ai-memory-layerupdated this year
—
MIT ★ 6 -
The Open Context Layer for Data Agents
NOASSERTION ★ 3 -
@runcontext/mcpgithub.com/runcontext/runcontextupdated this year
MCP server that serves semantic metadata to AI agents. Connect your data catalog to Claude Code, Cursor, Copilot, Windsurf, and any MCP-compatible tool.
npm MIT -
Wake Intelligence: 5-Layer Temporal Intelligence for AI Agents A production-ready Model Context Protocol (MCP) server implementing a temporal intelligence "brain" with five layers: Past (causality tracking), Present (memory management), Future (predictive pre-fetching), Adaptive (meta-learning — per-project weight tuning), and Personality (tempora
MIT ★ 4 -
Open-source MCP server for self-hosted Lightdash
MIT ★ 2 -
An open source MCP and REST server for Malloy semantic models, so AI agents, applications, and BI tools query one governed model instead of raw SQL.
npm -
先进且稳定的企业级智能分析平台;面向企业问数、洞察分析的Data Agent,基于数据分析方法论打造可审计、可治理、可复现workflow
Apache-2.0 ★ 69 -
Semantic Data Gateway for AI Agents: databases and HTTP APIs, shared business ontologies, verified query templates, controlled MCP access and audit logs. Built in Go.
Apache-2.0 ★ 3 -
Metric catalog and data service over HTTP and MCP: versioned definitions, precomputed metric serving, and governed exploration. Self-host with OIDC.
Apache-2.0 ★ 4 -
Census ACS to DuckDB to tested dbt marts to governed metrics, served by a read-only MCP server AI agents can query safely.
NOASSERTION -
Messy retail data turned into trusted metrics with dbt, plus an AI analyst that answers from them (40/40)
MIT -
Read-only, file-watching semantic-search MCP server and CLI over local files
pypi MIT -
@semanticintent/semantic-wake-intelligence-mcpgithub.com/semanticintent/semantic-wake-intelligence-mcpupdated this year
Wake Intelligence - 5-layer temporal intelligence brain for AI agents. MCP server with causality tracking, memory management, predictive pre-fetching, meta-learning, personality modes, causal graph visualization, and Rune Protocol integration.
npm MIT -
Verified context for AI coding agents. A local context layer that intelligently compresses, filters, indexes, and verifies AI coding-agent tool output. 32 MCP tools across 10 layers: code intelligence (tree-sitter, 30+ languages), context selection, tool
npm SEE LICENSE IN LICENSE -
schemabraingithub.com/arun-kc/schemabrainupdated this year
The trust and intelligence layer between AI agents and your database.
pypi Apache-2.0 -
Perfect recall for imperfect machines. A shared memory layer for LLMs via MCP
Apache-2.0 ★ 3 -
Local RAG MCP server for markdown docs. Retrieval only (no answer LLM): ask_docs returns grounded passages plus citations that resolve to real files on disk. Index any local path or git repo, filter by layer, embed offline.
MIT -
omnexgithub.com/sup3rus3r/omnexupdated this year
Omnex is not a search tool. It is the memory substrate for the agentic era — the data layer that sits beneath AI agents, AI operating systems, and human-AI interaction. What exists today (file systems, folder hierarchies, manual search) is legacy. Omnex is the foundation of what comes next.
AGPL-3.0 ★ 4