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.
-
neuroversegithub.com/joshua400/neuroverseupdated this year
Multilingual intelligence + memory + safety MCP server for autonomous AI agents
npm Apache-2.0 -
Static, deterministic memory-safety checker for C/C++ that verifies code against declared contracts, with an MCP server for AI coding agents
Apache-2.0 ★ 1 -
SQLite-backed MCP Memory Server with WAL concurrent safety, FTS5 search, session tracking, task management, and cross-machine bridge sync
MIT ★ 18 -
Your ADRs are lying to you. MCP server with live drift detection, content safety, and decision memory — validates architectural decisions against your actual code.
npm MIT ★ 35 -
Self-improving long-term memory for AI agents in Rust. Safety-gated procedural learning, MCP server, Python/Node SDKs, and durable memory.
NOASSERTION ★ 2 -
lore-mcpgithub.com/eliotshift/lore-mcpupdated this year
LORE v0.1.6 — Type-Aware Architectural Memory for AI Coding. Plugin-based code archaeology engine with 13 analyzers, MCP integration, dependency graph, circular dependency detection, type safety scoring, hotspot analysis, and AI recommendations.
npm MIT -
Persistent memory, architectural decision enforcement, pre-execution safety hooks, and session handoff for Claude Code. MCP server plugin for AI coding agents.
go MIT ★ 14 -
clarik-mcp-servergithub.com/Mikerichardmail/clarik-mcp-serverupdated this year
Clarity and memory for Claude. Persistent memory, intelligent context ranking, safety modes, and session checkpoints for Claude Desktop & Claude Code in a single install.
npm MIT ★ 1 -
smritigithub.com/thelonewolf1337-code/smritiupdated this year
Portable memory + simulated affect for AI agents — episodic, semantic & procedural memory, emotion-driven strategy with hard safety guarantees. Ships as an MCP server. Zero dependencies.
MIT -
A transparent, Markdown-backed, L0-L3 tiered hybrid memory system for AI agents with CBT safety and enterprise multi-tenancy support. Powered by MCP. 中文:为 AI Agent 打造的透明 Markdown 白盒与 L0-L3 分层混合记忆系统,兼顾 CBT 心理安全与企业级多租户支持,由 MCP 驱动。
MIT -
gomcpgithub.com/syntrex-lab/gomcpupdated this year
🛡️ The only Open-Source RLM Memory Server with Mathematically Proven Safety. Persistent context, MCP tools & Sentinel Lattice protection for autonomous AI agents.
go Apache-2.0 ★ 13 -
LM Studio MCP server with concurrent multi-agent support and memory safety
npm MIT -
Runtime for a persistent autonomous research agent on Claude: scheduler, MCP tool server, memory index, safety hooks, change control
-
Filesystem-first hybrid vector memory engine & MCP server in Go. Couples human notes (Obsidian/Copyparty) with PostgreSQL + pgvector, hybrid RRF search, graveyard safety guardrails, and parent-child chunking for nomic-embed-text-v2-moe.
-
A Model Context Protocol server that lets an AI agent drive a mock e-signature workflow, with a **human approval gate** on anything that sends mail or cancels a document. In-memory backend, no accounts or API keys, so you can learn MCP and agent safety without risk.
MIT -
@sgraal/mcpgithub.com/sgraal-ai/coreupdated this year
AI agent memory governance MCP server — preflight validation before every action. Works with Claude Desktop, LangGraph, and any MCP-compatible client.
npm Apache-2.0 -
MCP server for CognOS trust scoring and session trace storage
pypi MIT -
Durable, private, time-aware memory engine for long-running AI agents
npm MIT ★ 1 -
Context compaction and safety gating for AI agents via TypeSafe Jev: keeps messages verbatim, no summarization. OpenAI, Anthropic, LangChain, CLI, MCP.
MIT ★ 2 -
verifiable-memorygithub.com/Mars-proj/verifiable-memoryupdated this year
Verifiable memory for AI agents — 0% hallucination, cited answers or honest abstention, provable forgetting, deterministic. MCP server. CPU-only, no GPU.
MIT ★ 1 -
Verified, scoped, retractable memory for coding agents — learns from code review, resists poisoned advice, human-governed. MCP server.
MIT ★ 1 -
praxosgithub.com/JustVugg/praxosupdated this year
MCP-powered memory, policy, and experience layer for safer AI agents.
MIT ★ 12 -
A semantic mistake-memory system for AI agents with MCP and in-process guardrail entrypoints.
pypi MIT -
Project-scoped rule memory for coding agents.
MIT ★ 2 -
Portable MCP server for AI agents: persistent session checkpoints, resume and Total Recall, with package-aware build tools. Linux, macOS, Windows and SSH.
NOASSERTION -
CeeSafe: a memory-safe systems language with modern syntax, compiled to portable C. Its compiler, ceesafec, is written in CeeSafe.
GPL-2.0 -
GitHub MCP Auto Git v3.0 - メモリ効率化・統合MCP・モジュール化完了の完全自動Git操作システム
npm MIT -
Local-first guard layer for AI coding agents: rejection memory, loop and drift detection, assumption ledger, and evidence-based completion checks. MCP server + CLI.
MIT -
COGO — la memoria con semáforo de confianza para construir software con IA. Suite Escriba.
MIT ★ 1 -
Secrets that live only as long as you do — a session-bound, memory-zeroizing dead-man's-switch. Locks secrets in non-swappable RAM and wipes + SIGKILLs the instant your session dies. Hardened Rust, seccomp-confined, with an MCP adapter for agents.
mcpb MIT ★ 3 -
Howdexgithub.com/rossbuckley1990-hash/Howdexupdated this year
The audit and verification layer for AI agents - verified procedural memory with compliance reports (SOC 2, EU AI Act, NIST AI RMF), a public procedure registry, and the verifier gate
NOASSERTION ★ 1 -
Local-first verification layer for AI agents: evidence, provenance, policy gates, human approval, and auditable Trust Receipts before a claim, memory write, or action is trusted.
npm Apache-2.0 ★ 31 -
ada-revivalgithub.com/assafbar2/ada-revivalupdated this year
Make Ada delightful again: an in-browser playground that PROVES your code correct (SPARK), plus an MCP kit that teaches AI assistants to write Ada. A community passion project.
MIT -
A shared fix-pool for coding agents with a write-time poisoning shield — every post_solution is screened for prompt-injection and leaked secrets before it can reach a reading agent.
Apache-2.0 ★ 1 -
The system of record for what an AI agent believed and did. Append-only beliefs with evidence, contradictions kept, risky actions gated behind a named human. MIT, self-hosted.
npm MIT -
An agent-native database. Sessions are branches an agent can fork, merge, and rewind; every write records what it was derived from; and taint-and-recall tells you exactly what a poisoned input contaminated. Built on substrate.
Apache-2.0 ★ 1 -
Computer-Use — a Windows desktop agent with memory, vision, and gated actions: human-issued pass, three-state verdicts, audit trail, one kill switch. MCP / CLI / panel.
Apache-2.0 ★ 2 -
Open-source MCP control plane for AI coding agents: mechanical time-locks, evidence-gated proof receipts, red-team remediation, and persistent engineering memory.
pypi MIT ★ 26 -
The policy layer for AI coding agents. aiZee governs what Cursor, Claude Code, Copilot, Windsurf, Devin & MCP agents may do — 139 enforcement gates, 29 personas, 245 skills, BMAD runtime, hybrid memory, tamper-evident audit. pip install aizee
pypi MIT ★ 6 -
HeartFlow (心虫) — AGI Layer 1: the Discriminator. Rule-based engine that checks what AI says before it reaches humans. 46 discrimination dimensions, 9-layer pipeline, 137 modules (logic/decision/cognition/emotion/memory/ethics/collaboration), 179 MCP tools
npm MIT -
AgenticStore: The secure toolkit for AI agents. Instantly equip Claude Desktop, Cursor, and Windsurf with 75+ MCP tools, persistent memory, and SearXNG search, all protected by a built-in PII prompt firewall to protect your data from being exposed to AI agents.
pypi MIT ★ 5 -
Live structural code graph for AI agents — one-curl install wires MCP + an agent skill into Claude Code, OpenCode, Codex and Cursor. Indexes a 96k-file Linux kernel tree in 2m51s on a laptop Intel i7; sub-ms structural queries from a memory-mapped graph.
MIT ★ 13