BMAD-METHOD MCP server for local network — project-aware AI development skills with web dashboard

The MCP server inside the Pipelex plugin: validate, prepare and run AI methods on Pipelex from a coding agent.

The MCP server inside the Pipelex plugin: validate, prepare and run AI methods on Pipelex from a coding agent.

DPD (Decompose-Propagate Decision) — A method for organizing thoughts with AI

MCP server exposing 193 Slack Web API methods as tools for AI agents

Shared, persistent memory for AI assistants, built on the Zettelkasten method

Public registry of real AI money-making experiments — every method with its cost, numbers, and honest verdict. Built by AI agents, for AI agents.

Modular MCP server for OPNsense firewall management - 88 tools providing access to 2000+ methods through AI assistants

Quality engineering for AI coding agents: a method with steps and human gates, measured by deterministic engines. Runs locally and sends no source code.

Enable AI assistants to seamlessly interact with your Metabase analytics platform. Access dashboards, cards, databases, and execute queries directly through conversational AI. Manage and manipulate your analytics data with comprehensive tools and secure authentication methods.

MCP server that gives AI assistants tools to analyze Salesforce Apex debug logs for performance bottlenecks, slow methods, and governor limit usage.

Research methods, workflow tools, and independent review for AI agents, packaged as a Skill, plugin, and local MCP server.

An IDE for AI agents — CLI that answers what a JVM classpath contains: inherited members, method bodies from sources or decompiled bytecode, find-usages, type and call hierarchy.

A dynamic Model Context Protocol (MCP) server that provides AI assistants with secure access to Smartschool APIs. This server automatically discovers all available Smartschool methods and exposes them as MCP tools with comprehensive safety guardrails.

Whole-codebase knowledge for AI coding agents. A field-aware code graph (functions, classes, methods, fields, references) plus persistent memory. Rust, Postgres + pgvector, MCP.

Apex Log MCP Server - AI-powered Salesforce Apex debug log analysis. Find performance bottlenecks, slow methods, SOQL bottlenecks, and governor limit issues.

1000+ arXiv-verified 3DGS methods · 15 AI agent skills · MCP server (34 tools) · open ebook — the AI-native entry to 3D Gaussian Splatting research

Model Context Protocol (MCP) server for the SOLIDWORKS API. Gives AI assistants (Claude, Cursor) instant ranked search and exact lookups across 14,000+ methods, properties, enums, and examples.

Bitrix MCP is the official server that gives AI assistants direct, up-to-date access to Bitrix24 REST API documentation. Instead of relying on assumed method names or parameters, assistants can query this server and get authoritative answers straight from Bitrix24 docs.

The terminal AI agents can drive — and the cockpit to run them from. 151 MCP methods, agent Inbox, git-worktree fleets, diff review & rollback, one-click updates. macOS / Linux / Windows, local-first, free, MIT.

Native macOS port of SPSS-MCP — let AI assistants drive IBM SPSS Statistics 20-31 on macOS through the Model Context Protocol. 23 analysis methods validated, triple output (OXML+SPV+HTML).

A statistical analyst in your AI chat. Bring a dataset and a question, get back a citable, re-runnable analysis with its method named. Works in Claude, Cursor, and any MCP client.

Read-only MCP server that gives AI assistants Roslyn-powered browsing of a C# solution: list types by folder or namespace, read XML docs, and fetch method signatures and bodies without reading whole files.

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.

MCP server that gives AI agents quantitative risk analytics tools: Value at Risk (VaR) and Expected Shortfall by 4 methods, GARCH volatility forecasting, extreme value theory (EVT) tail risk, Basel backtesting, stress testing, and a credit-risk PD scorecard. Python, FastMCP, works with Claude.

Your AI writes the code; Karajan governs how it happens: TDD-first method, cross-AI review on every commit and git gates that make a false green impossible. Works with Claude, Codex, Gemini, OpenCode and Aider, on the subscriptions you already pay for. MCP server included.

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.

Open-source, read-only AWS security scanner. 110 checks across 25 services, 31 attack-chain rules, 64 IAM escalation methods (incl. lateral AssumeRole graph), Proof Mode exploitability verification, data perimeter and Bedrock AgentCore checks, Blast Radius CLI, Threat Feed, What-If simulator, AI-SPM, 6 compliance frameworks, breach-cost estimation, MCP server. CLI + Terraform remediation on every finding.

MCP API Translator turns OpenAPI (3.0/3.1, Swagger 2.0) specs and Postman collections into MCP servers that let AI assistants call your APIs. Preview: see exactly which tools a spec will produce, then filter by tag, HTTP method or path. Generate: get a complete project you can run and own, in TypeScript or Python (low-level SDK or FastMCP), over stdio or HTTP. Extend: add operations from more specs to an existing project without duplicating tools. Serve: skip code generation and mount one or more specs as live tools, each API with its own base URL and credentials.

A complete Model Context Protocol (MCP) server that gives AI assistants full access to Obsidian vault operations. Features 11 tools for note management, automatic template application, format preservation, and an extensible architecture for adding new productivity apps.

MCP server for Kratos Multiphysics

Donate AI inference to advance open mathematical problems.

Composable mathematics tools for agents

MCP server connecting AI agents to YADE — run DEM simulations through natural conversation

MCP server connecting AI agents to ITASCA FLAC — run continuum simulations through natural conversation

Official MCP interface for AgentFEM: create, validate, run, inspect, and verify finite-element simulations.

MCP server connecting AI agents to ITASCA engines (PFC, FLAC, 3DEC, MPoint, MassFlow) — run geotechnical & geomechanics simulations through natural conversation

MCP server for interactive Agda type-checking and proof development. Mutating or Non-Mutating.

Automatically categorizes customer complaint emails and generates legally-binding resolution drafts via the protocol.

Generates professional project reports by combining data from Sheets and Notion, analyzing insights for stakeholders.

AI-powered stock data analysis with fundamental insights and automated trade execution triggers via GenPark protocol.

Deterministic Python Model Context Protocol (MCP) server & autonomous agent skill for Openclaw Recursive Operational Synthesis.

Real-time performance and profit leaderboard for the GenPark Alpha Layer. Showcasing the most efficient nodes in the agent economy.

Topology optimization for 3D printing, as an MCP server for Claude, Codex, Cursor and other AI agents. Loads and regions in, a lighter printable STL out.

Adaptive Cognitive Mentorship & First-Principles Teaching MCP Server. Distilled from Matt Pocock's /teach, supercharged with Source Credibility Scoring, Production Edge-Case Traps, and Ebbinghaus Spaced Repetition.

openPASO (formerly OASiS): an MCP server that lets an AI model run nine finite-element and multiphysics codes, with curated knowledge, verified execution and cross-code coupling. Under active development; contributions welcome.

A native desktop IDE for Lean 4 on macOS, Windows and Linux. Every proof re-checked by Tenet, an independent Lean 4 kernel. An MCP server for AI assistants, with Git and GitHub built in.

A networked PARA knowledge brain for coding agents — documents managed by PARA and woven into one connected graph, held in a searchable Postgres store with a revision history per document. One static binary: MCP server + CLI.

MCP server for YADE open-source discrete element method simulation

DocGen - 100% COMPLETE Google Docs API - All 3 primary methods + 33 batch operations + helpers

MCP server for scaffolding and validating high-quality Metalsmith plugins with native methods enforcement

MCP server for static navigation of .NET assemblies — types, methods, attributes, decompilation. Companion to dotnet-diagnostics-mcp.

Block-method film pipeline as MCP tools: plan → lock → render (Higgsfield Soul) → style-drift QC → cut. Provider-agnostic LLM layer.

MCP server for NEC2 wire-antenna method-of-moments simulation — dipole, Yagi, vertical, loop, inverted-V. Gain patterns, impedance, VSWR.

MCP-сервер для API Диадока (Контур): 114 методов, документы, документооборот, контрагенты, МЧД | MCP server for the Kontur Diadoc EDI API: 114 methods, documents, workflow, counterparties.

Collects research material from web pages, papers, APIs, PDFs, scans, audio and video into a local corpus where every item records its source, method and hash.

Framework-agnostic Java observability sidecar agent: chat with a live JVM via MCP/web UI (metrics, slow calls, errors, logs, thread dumps, method traces). Self-hosted, attachable (Arthas-style). 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

Inspectable, source-traceable public-equity research for Codex, Claude Code, OpenCode, Grok Build and ChatGPT Work developer mode. 26 provisional method lenses, 34 MCP tools. Research software, not investment advice.

Critical Path Method planner as an MCP server: schedules task graphs (slack, critical path, resource levelling, Monte Carlo), leases lock-aware parallel cohorts to agents, versions plan-as-code variants, and tracks earned value.