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.
-
knowledge-graph-causal-discovery-mcpgithub.com/apifyforge/knowledge-graph-causal-discovery-mcpupdated this year
Knowledge graph causal discovery over multi-domain research data, delivered through a single Model Context Protocol interface.
MIT -
mcp-servergithub.com/causari/mcp-serverupdated this year
Open-source MCP server — a causal knowledge graph for AI agents. npx @causari/mcp-server
npm ★ 1 -
Open-source causal graph memory for AI agents. 85.55 on LoCoMo under a frozen, reproducible protocol. MCP server with ACT-R scoring, spreading activation, and active forgetting.
AGPL-3.0 ★ 31 -
polyg-mcpgithub.com/captain-jay29/polyg-mcpupdated this year
Multi-Graph Agent Memory via MCP - The memory system that understands causality
npm MIT -
causalist-mcpupdated this year
Model Context Protocol server for Causalist — agents get typed access to the causal graph of any mapped GitHub repository.
npm MIT -
Codegeist 2026: Project World Model (PWM) × Jira Time Machine — Causal AI Digital Twin, Rovo Agent, Teamwork Graph (TWG) & MCP Server on Atlassian Forge
-
Engramgithub.com/bitphonix/Engramupdated this year
🐘 Local-first causal knowledge graph for AI developer memory. Tracks decisions, rejected alternatives & reasoning — not just facts. MCP-native for Claude, Cursor & VS Code.
AGPL-3.0 ★ 2 -
因果Harness:自动编排从数据处理、因果发现到交互式因果图与分析报告的完整流程,融合 LangGraph、MCP 与 RAG。AI Harness for automated causal analysis—from data preparation and causal discovery to interactive causal graphs and reports. Powered by LangGraph, MCP & RAG.
AGPL-3.0 ★ 39 -
MCP connector for RCA-MCP — causal root-cause analysis via causal graphs, Bayesian networks, PyRCA algorithms. 56 tools.
pypi MIT -
@sweyaai/tenex-graph-mcpupdated this year
Graph MCP server wrapping LadybugDB for causality-based requirement graphs
npm MIT -
causalos-mcpupdated this year
Dual Memory Agent Runtime: Causal Graph Engine + General Memory + Forward Simulation + Backward Inference for AI Agents
npm ISC -
iglegaisgithub.com/cintu07/iglegaisupdated this year
memory that answers why, not just what. causal graph memory with an mcp server.
pypi MIT License Copyright (c) 2026 Pawan Kalyan Pe -
io.github.CanopyHQ/phloemgithub.com/canopyhq/phloemno update data
Local-first AI memory with causal graphs. Fully offline, zero config, your data stays local.
mcpb -
SuperMem 超级记忆系统 — local-first long-term memory for AI agents: knowledge graph + vector search + verbatim layer, episodic memory, forgetting curve, causal edges, MCP/REST API. 图数据库与向量检索的语义记忆平台。
MIT ★ 3 -
On-call agent on a FalkorDB context graph. No path, no claim: it blames a change only when the graph proves a causal path that can carry the impact, contains with a min-cut, routes to who fixes it, takes one approved action and verifies it.
npm Apache-2.0 ★ 2 -
graphonomousgithub.com/c-u-l8er/graphonomousupdated this year
Continual learning MCP server for AI agents — topology-aware knowledge graph with kappa-routing, exposed as 5 loop-phase machines (retrieve/route/act/learn/consolidate), causal metadata, and neural embeddings. One of four MCP servers in the [&] three-prot
npm Apache-2.0 -
A shared debugging environment for humans and AI agents. Turns browser telemetry into one causal graph, exposed to agents through 12 WebMCP tools.
MIT -
history-graph-protocolgithub.com/wgsim/history-graph-protocolupdated this year
An MCP server that gives AI agents a permanent, append-only causal history
pypi MIT -
DreamGraph is a graph-governed conceptual development environment (CDE) that turns plans, architecture decisions, and project knowledge into auditable execution through a persistent cognitive graph.
npm NOASSERTION ★ 128 -
Making What If into How So
MIT -
Zikkarongithub.com/amanhij/Zikkaronupdated this year
Biologically-inspired persistent memory engine for Claude Code. 26 cognitive subsystems, Hopfield networks, predictive coding, causal discovery, successor representations, all running locally over SQLite.
pypi MIT ★ 61 -
Deterministic cognitive state substrate & world model runtime for autonomous agents. Features transactional belief updates, hybrid RK4 rollouts, and 3-tier experience consolidation via MCP & REST.
pypi Apache-2.0 ★ 6 -
A flight recorder for AI agents: records every step, ranks the step most likely at fault, then proves it by replaying the run with only that step repaired, at zero model calls. Top-1 0.60 on unseen failures against 0.25 baselines. MCP server, CI regression firewall, on PyPI.
MIT -
FlowGuard: End-to-End Causality Flow (Source -> Branch -> Sink) Architecture Vision, 10+ Lang Bridge Linker & Incremental Flow Verifier MCP Plugin
MIT -
CMHM - Causal Hierarchical Memory: an MCP server giving AI agents persistent local memory (Rust). Engine runs offline; releases include a portable Windows build.
MIT