SWI-Prolog

SWI-Prolog

vpursuit

Provides secure access to SWI-Prolog logic programming environment through an MCP server with sandboxed execution and dynamic knowledge base management.

Provides secure access to SWI-Prolog logic programming through dual query modes with sandboxed execution, dynamic knowledge base management, and mathematical operations for educational use cases, logic puzzle solving, and AI reasoning workflows.

7256 views4Local (stdio)

What it does

  • Load and manage Prolog files
  • Add and remove facts and rules dynamically
  • Execute Prolog queries with deterministic pagination
  • Run queries with true backtracking engine mode
  • List Prolog symbols and predicates
  • Perform mathematical operations in Prolog

Best for

Educational logic programming coursesSolving logic puzzles and constraintsAI reasoning workflow developmentInteractive Prolog development
Sandboxed execution for securityDual query modesZero setup with npx

About SWI-Prolog

SWI-Prolog is a community-built MCP server published by vpursuit that provides AI assistants with tools and capabilities via the Model Context Protocol. Access SWI-Prolog for secure logic programming, ladder logic, and PLC coding. Ideal for education, puzzles, and AI logic It is categorized under ai ml, developer tools.

How to install

You can install SWI-Prolog in your AI client of choice. Use the install panel on this page to get one-click setup for Cursor, Claude Desktop, VS Code, and other MCP-compatible clients. This server runs locally on your machine via the stdio transport.

License

SWI-Prolog is released under the BSD-3-Clause license. This is a permissive open-source license, meaning you can freely use, modify, and distribute the software.

MCP Ecosystem by vpursuit

Build Status

This monorepo contains Model Context Protocol (MCP) packages and products that enable AI assistants to work with SWI-Prolog, filesystems, and extensible plugin systems.

Products

SWI-Prolog MCP Server

Full-featured MCP server with Prolog knowledge base integration

A MCP server that lets tools-enabled LLMs work directly with SWI‑Prolog. It supports loading Prolog files, adding/removing facts and rules, listing symbols, and running queries with two modes: deterministic pagination and true engine backtracking.

Features:

  • Knowledge base management (load, assert, retract, dump)
  • Two query modes: standard (call_nth/2) and engine (true backtracking)
  • Expert Prolog assistance prompts (e.g. solving logic puzzles)
  • Comprehensive security sandboxing
  • Dynamic filesystem roots
  • Plugin-based architecture

Architecture

This repository follows a products/plugins architecture:

  • Products (products/): Published packages that end-users install (e.g., @vpursuit/swipl-mcp-server)
  • Plugins (plugins/): Internal, reusable components bundled within products (not published separately)

Internal Plugin System

The MCP server is built with a modular plugin architecture. These plugins are internal dependencies bundled into the main product:

PluginDescriptionLocation
@vpursuit/mcp-server-corePlugin system foundationplugins/server/core
@vpursuit/mcp-server-prologSWI-Prolog integrationplugins/server/prolog
@vpursuit/mcp-server-rootsFilesystem roots discoveryplugins/server/roots

Note: These plugins are marked as private in their package.json and are bundled into @vpursuit/swipl-mcp-server. They are not published separately to npm.

Plugin System for Developers

If you're developing within this monorepo, you can use the plugin system directly:

import { McpServer } from '@modelcontextprotocol/sdk/server/mcp.js';
import { loadPlugins } from '@vpursuit/mcp-server-core';
import { plugin as prologPlugin } from '@vpursuit/mcp-server-prolog';
import { plugin as rootsPlugin } from '@vpursuit/mcp-server-roots';

const server = new McpServer({
  name: 'my-mcp-server',
  version: '1.0.0',
});

// Load plugins
await loadPlugins(server, [prologPlugin, rootsPlugin]);

📂 Repository Structure

This is a monorepo managed with npm workspaces. Each package can be developed, tested, and published independently.

model-context-lab/
├── products/
│   └── swipl-mcp-server/    # Main MCP server (published to npm)
├── plugins/
│   └── server/
│       ├── core/            # Plugin system foundation (internal)
│       ├── prolog/          # SWI-Prolog integration (internal)
│       └── roots/           # Filesystem roots discovery (internal)
├── docs/                    # Monorepo-level documentation
├── .archive/                # Historical strategy documents
└── package.json             # Workspace configuration

Each package has:

  • Own package.json with independent versioning
  • Own README.md with complete documentation
  • Own LICENSE (BSD-3-Clause)
  • Own test suite

🔧 Development

Prerequisites

  • Node.js ≥ 20.0.0
  • SWI-Prolog (for testing Prolog integration)
  • npm ≥ 9.0.0

Setup

# Clone repository
git clone https://github.com/vpursuit/model-context-lab.git
cd model-context-lab

# Install all dependencies
npm install

# Build all packages
npm run build

# Run all tests
npm test

Working with Packages

# Build specific package
npm run build -w plugins/server/core

# Test specific package
npm test -w plugins/server/prolog

# Clean all build artifacts
npm run clean

Package Development

Each package supports:

  • npm run build - TypeScript compilation
  • npm run clean - Remove build artifacts
  • npm test - Run Vitest tests
  • npm run test:watch - Watch mode for tests

Documentation

Product Documentation (swipl-mcp-server)

Monorepo Documentation

Contributing

We welcome contributions! Please see CONTRIBUTING.md for:

  • Code of conduct
  • Development workflow
  • Testing requirements
  • Pull request process
  • Coding standards

For security issues, see SECURITY.md.

Publishing

Only products are published to npm under the @vpursuit scope:

  • Products (e.g., @vpursuit/swipl-mcp-server) are published to npm for end users
  • Plugins are internal dependencies bundled within products (not published separately)
  • Releases use semantic versioning: v<version> (e.g., v3.0.0)
  • Automated publishing via GitHub Actions
  • Supply chain security: All packages published with npm provenance attestation
  • See PUBLISHING.md for complete details

Security

All packages implement security best practices:

  • File path restrictions
  • Dangerous predicate blocking
  • Pre-execution validation
  • Timeout protection
  • Module isolation

Supply Chain Security:

  • Published with npm provenance attestation for build transparency
  • OIDC-based publishing (no long-lived tokens)
  • Cryptographically signed packages via Sigstore

See SECURITY.md for complete security documentation and reporting.

📄 License

All packages in this monorepo are licensed under BSD-3-Clause.

See LICENSE file for details.

🔗 Links

Getting Started

For end users: Install the complete MCP server

npx @vpursuit/swipl-mcp-server

For monorepo developers: Work with the plugin system

git clone https://github.com/vpursuit/model-context-lab.git
cd model-context-lab
npm install
npm run build

For contributors: Set up the development environment

git clone https://github.com/vpursuit/model-context-lab.git
cd model-context-lab
npm install
npm run build
npm test

Questions? Open an issue or see our documentation.

Alternatives

Related Skills

Browse all skills
ui-design-system

UI design system toolkit for Senior UI Designer including design token generation, component documentation, responsive design calculations, and developer handoff tools. Use for creating design systems, maintaining visual consistency, and facilitating design-dev collaboration.

6
cli-builder

Guide for building TypeScript CLIs with Bun. Use when creating command-line tools, adding subcommands to existing CLIs, or building developer tooling. Covers argument parsing, subcommand patterns, output formatting, and distribution.

2
openai-knowledge

Use when working with the OpenAI API (Responses API) or OpenAI platform features (tools, streaming, Realtime API, auth, models, rate limits, MCP) and you need authoritative, up-to-date documentation (schemas, examples, limits, edge cases). Prefer the OpenAI Developer Documentation MCP server tools when available; otherwise guide the user to enable `openaiDeveloperDocs`.

0
api-documenter

Master API documentation with OpenAPI 3.1, AI-powered tools, and modern developer experience practices. Create interactive docs, generate SDKs, and build comprehensive developer portals. Use PROACTIVELY for API documentation or developer portal creation.

0
ydc-ai-sdk-integration

Integrate Vercel AI SDK applications with You.com tools (web search, AI agent, content extraction). Use when developer mentions AI SDK, Vercel AI SDK, generateText, streamText, or You.com integration with AI SDK.

0
mcp-developer

Use when building MCP servers or clients that connect AI systems with external tools and data sources. Invoke for MCP protocol compliance, TypeScript/Python SDKs, resource providers, tool functions.

0