TCL UDF
This MCP server provides AI assistants with a complete TCL scripting environment and dynamic tool management system, built by Cyberdione Labs using Rust with the Molt TCL interpreter. The implementation offers both direct TCL script execution and a sophisticated tool framework where users can create, persist, and execute custom tools with parameter validation, namespace organization (bin/sbin/user), and filesystem-based tool discovery. Built with privileged/restricted execution modes, file-based persistence, and support for both inline TCL scripts and executable .tcl files with metadata annotations, it serves developers needing programmable automation capabilities, system administrators requiring scriptable tools with proper isolation, and teams building custom workflow automation where TCL's text processing and system integration capabilities can be leveraged through conversational AI interfaces.
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 2026-09-28.
Scan details: Circle-IR · 2026-09-28 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- file-system
- Source
- PulseMCP
- Repository
- github.com/cyberdione/mcp-tcl-udf-server
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve TCL UDF 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.