10 actions in 5 pieces of software · ranked by words, meaning and measured trust · 443 ms
- 1@loomweaver/mcpfound in code, not yet checkedno passport yet
- list_generators
List the available LoomWeaver scaffolding generators.
- validate_manifest
Validate a plugin manifest (id, capabilities). Returns findings.
- validate_i18n
Validate i18n key parity across languages. Input: bundles = { <lang>: <nested object> }.
- validate_commands
Say, per command a plugin registers, whether an agent is offered it, what would leave the agent guessing, and what the command states about an agent's word being enough to run it. Input: files = { <path>: <TypeScript or JavaScript source> }. Only a callable command without a description is a warning
- validate_catalog
Validate a plugin store catalog (the parsed JSON array). The host parses catalogs defensively, so bad fields and whole entries disappear without a word; each finding names that consequence. Returns findings.
- list_generators
- 2loom-mcpfound in code, not yet checkedno passport yet
MCP serverkarbassi/mcp-loom
- move_folders
Move one or more Loom folders into a different parent folder.
- search_folders
Search your Loom folders by name.
- move_folders
skillapify/mcpcrecord
- mcpc
Use the mcpc CLI to work with MCP (Model Context Protocol) servers from the shell - connect to a server as a persistent session, then list and call tools, read resources, get prompts, and run async tasks. Use --json for scripting and code mode. Reach for this whenever interacting with MCP servers, c
- mcpc
skillvercel-labs/json-renderrecord
- mcp
MCP Apps integration for json-render. Use when building MCP servers that render interactive UIs in Claude, ChatGPT, Cursor, or VS Code, or when integrating json-render with the Model Context Protocol.
- mcp
- mcp-builder
Build, modify, debug, migrate, review, or verify TypeScript MCP servers and MCP Apps with mcp-use. Use for tools, resources, prompts, middleware, Views, authentication, Skills over MCP, scaffolding, and advanced features.
- mcp-builder
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.