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. Each candidate is checked by a language model from its name, description and topics, and only actual MCP servers are listed (not clients, SDKs, lists or skills). Package descriptions, licences and links are read from each package's own registry (npm, PyPI, crates.io, NuGet, RubyGems; Go and Maven packages are only checked to exist), and packages the registry no longer has are removed. 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.
-
A Python-based MCP server implementing causal inference analysis on synthetic customer spending data. Uses DoWhy for causal effect estimation and FastMCP for exposing causal tools. Enables interactive causal analysis with treatment and outcome variables from program signup data.
-
Six causal-inference tools (DoWhy, PyMC, EconML, causal-learn) exposed over both FastAPI and MCP/SSE. Every result returns a uniform envelope whose evidence level is gated on sample size and convergence, so an agent gets a structured 'insufficient' instead of a confident wrong number.
MIT -
aigroup-econ-mcpgithub.com/jackdark425/aigroup-econ-mcpupdated this year
Econometrics MCP server for regression, causal inference, time series, panel data, and statistical analysis workflows.
pypi MIT ★ 10 -
StatsPAI is an Agent-native Python library for causal inference and applied econometrics — unified API, broad cross-method coverage, structured result objects, machine-readable schemas, Skills, an MCP server, and R/Stata parity validation.
pypi MIT ★ 375 -
Best Free Stata MCP Causal Inference Tool 2026 - Download Now
★ 1 -
Autonomous Biophysical Causal Inference and Farquhar-Governed Invariant Framework for Multi-Stress Crop Decoupling over Model Context Protocol (MCP v2025-11-25)
MIT -
🌍 MCP server giving Claude live environmental data: air quality, wildfires, and weather, plus statistical anomaly detection and causal inference (DoWhy) to explain why pollution spikes happen.
MIT -
causal-panopticon-mcpgithub.com/apifyforge/causal-panopticon-mcpupdated this year
Causal Panopticon is a cross-domain causal discovery and inference engine for AI agents, exposed via the Model Context Protocol.
MIT ★ 1 -
Autonomous AI-driven Root Cause Analysis (RCA) & causal inference engine for EV fast-charging networks. Triages multi-party telemetry across OCPP 1.6-J and OCPI roaming protocols with FastMCP agentic diagnostics.
MIT ★ 1 -
causalos-mcpupdated this year
Dual Memory Agent Runtime: Causal Graph Engine + General Memory + Forward Simulation + Backward Inference for AI Agents
npm ISC -
On-chain risk enforcement and behavioral analytics for autonomous AI trading agents on Solana. 19-tool MCP server with semantic routing, DR-CAM causal inference, and 3-layer evaluation suite.
MIT ★ 3 -
A股因果链推演 MCP:事件↔标的匹配 / CAR 计算 / 知识图谱传播 / LLM 传导分析 / 反驳评级,13 工具,与 news-mcp 联动
-
Causal memory layer for AI agents — MCP server that records decision→outcome relationships. Survives compaction.
pypi Apache-2.0 ★ 107 -
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 -
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.
NOASSERTION ★ 128 -
ATLASgithub.com/web3guru888/ATLASupdated this year
Active-inference Training with Learned Adaptive Stigmergy — Pure Rust AGI framework, 21 crates, 565 tests, 28 MCP tools, BF16 GPU inference (15.4 tok/s OLMo-3-7B on A100), OpenAI-compatible API, ZK proofs. Zero external dependencies.
Apache-2.0 ★ 3 -
simulacrum-mcpgithub.com/codesmirnov/simulacrum-mcpupdated this year
The Physics Engine for LLM Thought. A comprehensive MCP toolkit for reality simulation: system dynamics, chaos theory, Bayesian reasoning, and game theory for AI agents
MIT -
tabintgithub.com/shubham303/tableintelligenceupdated this year
A deterministic, reproducible intelligence layer for single-table data.
pypi Apache Software License -
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 -
Agentic AI platform with MCP tool servers for vaccine coverage equity analysis using UNICEF (8.8M rows), WHO immunization, and OECD ODA financing data
-
Home Assistant app: authenticated ingestion API, event store, feature engineering, coverage metrics and a read-only MCP server for Android timeline data. Experimental.
MIT -
heor-studiogithub.com/andey0Saikiran/heor-studioupdated this year
Turn a study protocol into machine-verified SAS + SQL for claims-data (MarketScan) studies: 2,563 executed checks across 24 groups, mutation-tested, honest refusals
NOASSERTION -
Read-only MCP server giving AI agents governed access to CRM data, a commercial calendar and an SEO auditor, with a benchmark scored against a known answer key. TypeScript.
MIT -
google-meridian-mcpgithub.com/muhammad1azmi/google-meridian-mcpupdated this year
Cloud-agnostic Model Context Protocol (MCP) server for Google Meridian & Marketing Mix Modeling (MMM). Grounded in first principles, data science control points, Bayesian prior calibration, and workflow diagnostics.
MIT ★ 1 -
Reproducible scientific modeling engine and agent skill pack: versioned Model IR with mandatory units, dimensional and numerical validation, calibration, uncertainty analysis, and portable export (SBML, CellML, Modelica) via CLI, REST and MCP. Install: pip install axiomize.
pypi MIT ★ 9 -
Local-first Rust service that watches how your machine and your AI coding agent work together, tests what it notices with randomized trials, and serves the verified lessons back to any AI over MCP. Windows desktop app.
Apache-2.0 ★ 1 -
Ask your AI assistant real questions about your data and get answers you can rely on — an MCP server with 45 analysis tools that pick the right statistical method themselves and tell you how much to trust the result.
MIT ★ 10 -
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.
MIT ★ 77 -
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 -
Aurora MCP server — glass-box statistical analysis for AI agents: 19 research-grade methods, cited findings, integrity-hashed bundles, zero invented numbers. Now with a calibration engine: measured false-fire rates attached to changepoint findings, verdicts downgraded when the data can't support the claim. Local-first.
pypi Apache-2.0