Lawve AI

Call a tool by name with the given arguments. Use this to execute tools discovered via search_tools.

Get a prompt by name with optional arguments. Returns the rendered prompt as JSON with a messages array. Arguments should be provided as a dict mapping argument names to values.

Return the full SKILL.md content of a single public skill plus a structured manifest: file tree (path, size, sha256, content_type, executable), declared dependencies, licence URL, and the legal disclaimer. Prefer `resources/read skill://{slug}/SKILL.md` when your client supports MCP Resources; use this tool when you need the richer metadata envelope in one round-trip.

Return the available filter values for `lawvable_search_skills`: categories, jurisdictions, and languages — each with a count of skills tagged with that value. Useful when a search returns no results and you need to suggest valid filter combinations to the user, or when the user asks 'what categories are available?'.

Search the public Lawvable marketplace catalogue. Returns a ranked markdown list of matching skills with title, description, category, jurisdictions and a link to the marketplace page. Prefer this when the user asks for something not already listed in the `<lawvable_skills>` catalogue injected at handshake.

List all available prompts. Returns JSON with prompt metadata including name, description, and optional arguments.

List all available resources and resource templates. Returns JSON with resource metadata. Static resources have a 'uri' field, while templates have a 'uri_template' field with placeholders like {name}.

Read a resource by its URI. For static resources, provide the exact URI. For templated resources, provide the URI with template parameters filled in. Returns the resource content as a string. Binary content is base64-encoded.

Search for tools using natural language. Returns matching tool definitions ranked by relevance, in the same format as list_tools.