SWI-Prolog
SWI-Prolog MCP server by Peter Trebing that provides AI assistants with secure access to Prolog logic programming through dual query modes: standard call_nth/2 for step-by-step solution retrieval and engine mode for true backtracking control. The implementation features a sandboxed execution environment with whitelisted predicates, dynamic knowledge base management (assert/retract facts and rules), file consultation with directive blocking, and unified session management that prevents mode conflicts while supporting mathematical operations, list processing, and recursive rule evaluation. Built with TypeScript and designed for educational use cases, logic puzzle solving, knowledge representation tasks, and AI reasoning workflows that benefit from Prolog's declarative programming paradigm with safety controls that block dangerous system calls and file operations.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-02.
Scan details: Circle-IR · 2026-09-02 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- productivity
- Source
- PulseMCP
- Repository
- github.com/vpursuit/model-context-lab
- Author type
- human
- Last scanned
- 2026-09-02
- Updated
- 2026-09-02
Use via MCP
Resolve SWI-Prolog from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.