Common Lisp REPL
This Common Lisp MCP server by cxxxr provides a REPL evaluation tool that allows AI assistants to execute Lisp code safely with read-time evaluation disabled to prevent security issues from constructs like #.(). Built using ASDF with dependencies on Alexandria, Yason, usocket, and bordeaux-threads, it supports both stdio and TCP transport modes with structured JSON logging and comprehensive test coverage using the Rove framework. The implementation features a single repl-eval tool that evaluates Common Lisp forms sequentially and returns the last value as printed text, making it valuable for AI assistants that need to perform mathematical calculations, data processing, or symbolic computation tasks using the expressive power of Lisp while maintaining security through disabled reader macros.
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 2026-09-19.
Scan details: Circle-IR · 2026-09-19 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- monitoring
- Source
- PulseMCP
- Repository
- github.com/cl-ai-project/cl-mcp
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve Common Lisp REPL 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.