Search verified Claude Code plugins and skills; fetch portable SKILL.md sources. Read-only.
Scored across 9 tools
Tools cleanly partition by resource: plugins (get_plugin, search_plugins), skills (get_skill, search_skills), scorecards (get_scorecard, list_scorecards), and categories (list_categories). The only mild overlap is between check_mcp_app and verify_plugin, both of which return audit/verification recipes, but they target distinct artifacts (MCP Apps vs. plugins) so confusion is limited.
Every tool follows a consistent verb_noun snake_case pattern (get_*, list_*, search_*, verify_plugin, check_mcp_app). The convention is predictable and readable throughout, with no mixing of styles.
Nine tools is well-scoped for a read-only catalog: it covers discovery, retrieval, and verification across three artifact types without redundancy. Each tool earns its place.
The catalog lifecycle is well covered: search/list for discovery and get_* for detailed retrieval across plugins, skills, and scorecards, plus verification recipes. Minor gap is the lack of a direct list_plugins or bulk/version listing, though search_plugins largely fills that role for a read-only surface.
Get the Sigistry MCP App safety criteria to audit an MCP App (MCP Apps / SEP-1865: a tool that returns an interactive ui:// HTML resource the host renders in a sandboxed iframe) BEFORE shipping it. Returns two groups of checks: spec conformance (ui:// scheme, the text/html;profile=mcp-app mimeType, tool-to-UI linkage via _meta.ui.resourceUri, a text fallback, visibility values, and CSP coverage of external origins) and security hygiene the iframe sandbox does not cover (unsafe DOM sinks, embedded secrets, host-message origin handling, remote scripts). Call this when the user is building or reviewing an MCP App; then apply each check to the app source you have in context and report findings. Nothing is sent to this server; an interactive browser version is at https://sigistry.com/mcp-app-checker.
Inputs: no named parameters. Returns: steps, checks, hubUrl, specUrl, +5 more
Get the full details of a single Sigistry plugin by its id, including install commands, component counts, and its security-audit result (per-check pass/fail from the Verified by Sigistry methodology).
Inputs: id (required). Returns: id, name, tags, agents, +13 more
Get the full scorecard for one graded MCP server by its id: the overall grade, per-axis pass/partial/fail with cited evidence, hardening notes, the rubric version, and the exact commit graded. Grades describe the pinned commit only; a re-grade at a newer commit can be requested via an issue on the marketplace repo.
Inputs: id (required). Returns: id, axes, date, name, +8 more
Get one Sigistry skill by name, including the full raw SKILL.md source. The source is portable: it can be applied directly in any SKILL.md-aware agent (Claude Code, Claude Desktop, and others) without installing anything, or installed natively in Claude Code via the parent plugin, which keeps it verified and updated. The returned skill passed the Sigistry skill-safety check at the parent plugin's verification date.
Inputs: name (required). Returns: name, repo, commit, plugin, +9 more
List the distinct plugin categories in the Sigistry marketplace with a count of plugins in each, plus the total plugin count.
Inputs: no named parameters. Returns: total, categories
List the public MCP servers Sigistry has independently graded against its scorecard rubric (transport, stateless core, lifecycle, authorization, tool design, security hygiene), each with an overall grade A-F and the exact commit graded. Useful before connecting an agent to a third-party MCP server: check whether it has been assessed and how it scored. Use get_scorecard for the full per-axis breakdown.
Inputs: no named parameters. Returns: total, rubricUrl, scorecards, rubricVersion
Search the Sigistry marketplace of Claude Code plugins by keyword and/or category. Returns matches with their install command and verification status (the registry runs an eight-check security audit; prefer "verified" plugins when recommending an install).
Inputs: query, category. Returns: results
Search the Sigistry catalog of verified skills (SKILL.md instruction sets for AI agents) by keyword, optionally filtered to one parent plugin. Every skill passed the skill-safety check: no command shadowing, honestly-scoped triggers, no injection or concealment language, no unsafe scripts. Use get_skill to fetch the full portable source of a match.
Inputs: query, plugin. Returns: results
Get the recipe to run the Sigistry verification methodology (the eight static checks that gate the Verified badge: manifest integrity, hook safety, agent tool scopes, command hygiene, skill structure, skill safety, no secrets, documentation) against a plugin BEFORE publishing it. The verification runs entirely on the local machine via a dependency-free open-source Node script; the plugin code never leaves the user's computer and this server performs no computation. Call this when the user wants their plugin or skill checked, then follow the returned steps: download the script, run it against the plugin directory, and fix any FAIL findings it reports.
Inputs: pluginPath. Returns: steps, checks, commands, nextSteps, +4 more
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Find AI agent skills: public previews and source links. Read-only discovery; no account required.
Search and load AI agent skills. Free metadata; full content requires a Pro or Studio account.
Search and load free AI skills, workflows, agents and prompts. Read-only, no sign-in.
Anonymous catalogue of curated agent skills (SKILL.md); premium bodies via OAuth account endpoint.
Add one secure layer between your agents and this server.
