MCP 服务器
Sigistry Plugin Catalog (formerly Claude Registry)
com.clauderegistry/plugin-catalog
此 MCP 可以做什么
Catalogs Claude Code plugins, portable agent skills, and MCP server scorecards, with search, verification details, and installation information.
功能
工具
8
工具
get_plugin
Get a Claude Code plugin
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).
只读
幂等
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['id'], 'properties': {'id': {'type': 'string', 'description': 'the plugin id, e.g. "sql-safety-net"'}}, 'additionalProperties': False}
输出模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['id', 'name', 'tags', 'commands', 'agents', 'skills', 'counts', 'installMarketplace', 'installCommand', 'searchableText'], 'properties': {'id': {'type': 'string'}, 'name': {'type': 'string'}, 'tags': {'type': 'array', 'items': {'type': 'string'}, 'description': 'keywords from the marketplace entry'}, 'agents': {'type': 'array', 'items': {'type': 'string'}, 'description': 'relative paths to agent files'}, 'author': {'type': 'object', 'properties': {'url': {'type': 'string'}, 'name': {'type': 'string'}}, 'additionalProperties': False}, 'counts': {'type': 'object', 'required': ['commands', 'agents', 'skills'], 'properties': {'agents': {'type': 'integer'}, 'skills': {'type': 'integer'}, 'commands': {'type': 'integer'}}, 'description': 'component counts', 'additionalProperties': False}, 'skills': {'type': 'array', 'items': {'type': 'string'}, 'description': 'relative paths to skill manifests'}, 'license': {'type': 'string'}, 'version': {'type': 'string'}, 'category': {'type': 'string'}, 'commands': {'type': 'array', 'items': {'type': 'string'}, 'description': 'relative paths to command files'}, 'homepage': {'type': 'string'}, 'description': {'type': 'string'}, 'verification': {'anyOf': [{'type': 'object', 'required': ['status', 'checks'], 'properties': {'date': {'type': 'string', 'description': 'date of the last audit run'}, 'repo': {'type': 'string', 'description': 'external repo (owner/name), when externally hosted'}, 'checks': {'type': 'array', 'items': {'type': 'object', 'required': ['id', 'title', 'status'], 'properties': {'id': {'type': 'string'}, 'title': {'type': 'string'}, 'detail': {'type': 'string'}, 'status': {'type': 'string', 'description': 'pass | fail | n/a'}}, 'additionalProperties': False}, 'description': 'per-check results of the security audit'}, 'commit': {'type': 'string', 'description': 'pinned commit the verification applies to'}, 'status': {'type': 'string', 'description': 'verified | listed | stale | failed'}, 'hosting': {'type': 'string', 'description': 'registry (vendored) | external (author repo)'}, 'badgeUrl': {'type': 'string', 'description': 'SVG badge for this plugin'}, 'firstSeen': {'type': 'string', 'description': 'date the plugin entered the registry'}, 'methodologyUrl': {'type': 'string'}, 'methodologyVersion': {'type': 'string'}}, 'additionalProperties': False}, {'type': 'null'}], 'description': 'security-audit result for this plugin (null when never audited)'}, 'installCommand': {'type': 'string', 'description': 'command to install this plugin'}, 'searchableText': {'type': 'string', 'description': 'lowercased text used for matching'}, 'installMarketplace': {'type': 'string', 'description': 'command to add the marketplace to Claude Code'}}, 'additionalProperties': False}
get_scorecard
Get an MCP server scorecard
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.
只读
幂等
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['id'], 'properties': {'id': {'type': 'string', 'description': 'scorecard id, e.g. "sigistry-catalog" (find ids via list_scorecards)'}}, 'additionalProperties': False}
输出模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['id', 'name', 'grade', 'axes'], 'properties': {'id': {'type': 'string'}, 'axes': {'type': 'array', 'items': {'type': 'object', 'required': ['id', 'title', 'status', 'evidence'], 'properties': {'id': {'type': 'string'}, 'title': {'type': 'string'}, 'status': {'type': 'string', 'description': 'pass | partial | fail | n/a'}, 'evidence': {'type': 'string', 'description': 'the file/behavior the result rests on'}}, 'additionalProperties': False}, 'description': 'per-axis results with evidence'}, 'date': {'anyOf': [{'anyOf': [{'not': {}}, {'type': 'string'}]}, {'type': 'null'}]}, 'name': {'type': 'string'}, 'repo': {'anyOf': [{'anyOf': [{'not': {}}, {'type': 'string'}]}, {'type': 'null'}]}, 'grade': {'type': 'string'}, 'notes': {'type': 'array', 'items': {'type': 'string'}, 'description': 'hardening suggestions and context'}, 'commit': {'anyOf': [{'anyOf': [{'not': {}}, {'type': 'string'}]}, {'type': 'null'}]}, 'endpoint': {'anyOf': [{'anyOf': [{'not': {}}, {'type': 'string'}]}, {'type': 'null'}]}, 'rubricUrl': {'anyOf': [{'anyOf': [{'not': {}}, {'type': 'string'}]}, {'type': 'null'}]}, 'rubricVersion': {'anyOf': [{'anyOf': [{'not': {}}, {'type': 'string'}]}, {'type': 'null'}]}, 'selfAssessment': {'type': 'boolean'}}, 'additionalProperties': False}
get_skill
Get a verified skill (with portable source)
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.
只读
幂等
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['name'], 'properties': {'name': {'type': 'string', 'description': 'the skill name, e.g. "assessment-scoring" (find names via search_skills)'}}, 'additionalProperties': False}
输出模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['name', 'description', 'plugin', 'verification', 'installCommand', 'detailUrl', 'pluginCategory', 'verifiedDate', 'hosting', 'sourceUrl', 'source'], 'properties': {'name': {'type': 'string', 'description': 'stable skill name, e.g. "assessment-scoring"'}, 'repo': {'type': 'string', 'description': 'author repo (owner/name), when externally hosted'}, 'commit': {'type': 'string', 'description': 'pinned commit the source is served from, when externally hosted'}, 'plugin': {'type': 'string', 'description': 'parent plugin id that ships this skill'}, 'source': {'type': ['string', 'null'], 'description': 'the complete raw SKILL.md (frontmatter + body); null only if the fetch failed'}, 'hosting': {'type': 'string', 'description': '"registry" (vendored here) or "external" (author repo, verified at a pinned commit)'}, 'detailUrl': {'type': 'string', 'description': 'human-readable page for this skill'}, 'sourceUrl': {'type': 'string', 'description': 'GitHub location of the skill directory'}, 'description': {'type': 'string', 'description': 'the skill trigger: when an agent should load it'}, 'verification': {'type': 'string', 'description': 'verification status of the parent plugin; prefer "verified"'}, 'verifiedDate': {'type': ['string', 'null'], 'description': 'date of the verification run covering this skill'}, 'installCommand': {'type': 'string', 'description': 'Claude Code command installing the parent plugin (skill loads automatically)'}, 'pluginCategory': {'type': ['string', 'null'], 'description': 'category of the parent plugin'}}, 'additionalProperties': False}
list_categories
List plugin categories
List the distinct plugin categories in the Sigistry marketplace with a count of plugins in each, plus the total plugin count.
只读
幂等
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}}
输出模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['categories', 'total'], 'properties': {'total': {'type': 'integer', 'description': 'total number of plugins'}, 'categories': {'type': 'array', 'items': {'type': 'object', 'required': ['category', 'count'], 'properties': {'count': {'type': 'integer', 'description': 'plugins in this category'}, 'category': {'type': 'string'}}, 'additionalProperties': False}, 'description': 'categories sorted by descending plugin count'}}, 'additionalProperties': False}
list_scorecards
List MCP server scorecards
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.
只读
幂等
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}}
输出模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['rubricVersion', 'rubricUrl', 'total', 'scorecards'], 'properties': {'total': {'type': 'integer'}, 'rubricUrl': {'type': ['string', 'null']}, 'scorecards': {'type': 'array', 'items': {'type': 'object', 'required': ['id', 'name', 'grade', 'repo', 'commit', 'endpoint', 'date', 'selfAssessment'], 'properties': {'id': {'type': 'string'}, 'date': {'type': ['string', 'null']}, 'name': {'type': 'string'}, 'repo': {'type': ['string', 'null']}, 'grade': {'type': 'string', 'description': 'overall grade A-F'}, 'commit': {'type': ['string', 'null'], 'description': 'the graded commit'}, 'endpoint': {'type': ['string', 'null']}, 'selfAssessment': {'type': 'boolean', 'description': "true for Sigistry's own servers"}}, 'additionalProperties': False}}, 'rubricVersion': {'type': ['string', 'null']}}, 'additionalProperties': False}
search_plugins
Search Claude Code plugins
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).
只读
幂等
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {'query': {'type': 'string', 'description': 'keywords, e.g. "database migration"'}, 'category': {'type': 'string', 'description': 'e.g. "database", "devops", "git"'}}, 'additionalProperties': False}
输出模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['results'], 'properties': {'results': {'type': 'array', 'items': {'type': 'object', 'required': ['id', 'name', 'installCommand', 'verification'], 'properties': {'id': {'type': 'string', 'description': 'stable plugin id, e.g. "sql-safety-net"'}, 'name': {'type': 'string', 'description': 'human-readable plugin name'}, 'category': {'type': 'string', 'description': 'marketplace category'}, 'description': {'type': 'string', 'description': 'one-line summary'}, 'verification': {'type': 'string', 'description': 'verification status: "verified" (passed the eight-check security methodology), "stale" (verified at a pinned commit the repo has since moved past), "listed" (in the registry but not audited), "failed", or "unknown". Prefer verified plugins. Methodology: https://sigistry.com/verification'}, 'installCommand': {'type': 'string', 'description': 'Claude Code install command'}}, 'additionalProperties': False}, 'description': 'up to 15 matching plugins, best matches first'}}, 'additionalProperties': False}
search_skills
Search verified Claude Code skills
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.
只读
幂等
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {'query': {'type': 'string', 'description': 'keywords, e.g. "changelog" or "security review"'}, 'plugin': {'type': 'string', 'description': 'restrict to skills shipped by this plugin id'}}, 'additionalProperties': False}
输出模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['results'], 'properties': {'results': {'type': 'array', 'items': {'type': 'object', 'required': ['name', 'description', 'plugin', 'verification', 'installCommand', 'detailUrl'], 'properties': {'name': {'type': 'string', 'description': 'stable skill name, e.g. "assessment-scoring"'}, 'plugin': {'type': 'string', 'description': 'parent plugin id that ships this skill'}, 'detailUrl': {'type': 'string', 'description': 'human-readable page for this skill'}, 'description': {'type': 'string', 'description': 'the skill trigger: when an agent should load it'}, 'verification': {'type': 'string', 'description': 'verification status of the parent plugin; prefer "verified"'}, 'installCommand': {'type': 'string', 'description': 'Claude Code command installing the parent plugin (skill loads automatically)'}}, 'additionalProperties': False}, 'description': 'up to 20 matching skills, best matches first'}}, 'additionalProperties': False}
verify_plugin
Verify a Claude Code plugin (pre-publish, runs locally)
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.
只读
幂等
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {'pluginPath': {'type': 'string', 'description': 'local path to the plugin directory, used to fill in the run command (optional)'}}, 'additionalProperties': False}
输出模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['runsWhere', 'methodologyVersion', 'methodologyUrl', 'checks', 'steps', 'commands', 'interpreting', 'nextSteps'], 'properties': {'steps': {'type': 'array', 'items': {'type': 'string'}, 'description': 'what the agent should do, in order'}, 'checks': {'type': 'array', 'items': {'type': 'object', 'required': ['id', 'title', 'what'], 'properties': {'id': {'type': 'string'}, 'what': {'type': 'string'}, 'title': {'type': 'string'}}, 'additionalProperties': False}, 'description': 'the eight checks the script will run'}, 'commands': {'type': 'object', 'required': ['macos_linux', 'windows', 'alternative_clone'], 'properties': {'windows': {'type': 'string', 'description': 'download + run one-liner for PowerShell'}, 'macos_linux': {'type': 'string', 'description': 'download + run one-liner for bash/zsh'}, 'alternative_clone': {'type': 'string', 'description': 'equivalent via cloning the marketplace repo'}}, 'additionalProperties': False}, 'nextSteps': {'type': 'string'}, 'runsWhere': {'type': 'string', 'description': 'always "local": verification executes on the user\'s machine'}, 'interpreting': {'type': 'string'}, 'methodologyUrl': {'type': 'string'}, 'methodologyVersion': {'type': 'string'}}, 'additionalProperties': False}
历史
近期工具变更
已添加
verify_plugin
2026年9月17日 12:34
已添加
get_scorecard
2026年9月17日 12:34
已添加
list_scorecards
2026年9月17日 12:34
已添加
get_skill
2026年9月17日 12:34
已添加
search_skills
2026年9月17日 12:34
已添加
list_categories
2026年9月17日 12:34
已添加
get_plugin
2026年9月17日 12:34
已添加
search_plugins
2026年9月17日 12:34
发现
类似的 MCP 服务器
hyperion
com.thetempleofdoom.hyperion/hyperion
Acts as a paid MCP tool marketplace and utility gateway with server discovery, HTTP and JavaScript tools, research, data conversi…
XGR MCP Gateway
io.github.xgr-network/xdala-workflow-builder
Provides an MCP gateway for XGRChain and XDaLa workflows, including blockchain explorer queries, session inspection, transaction …
aaaa-nexus — Formally Verified AI Safety APIs
io.github.atomadictech/aaaa-nexus
Provides formally constrained agent safety and governance APIs for tool authorization, prompt-injection-resistant execution, iden…
Slid Phi Labs
io.github.ceedot-rock/slid-phi-labs
Provides searchable catalogs and documentation for agent services, issues agent API keys, exposes x402-purchasable SKUs, and offe…
AgentResolver — Agent Commerce Health Monitoring
io.github.waxsway/agentresolver
Resolves missing agent capabilities and provides MCP and HTTP endpoint checks, tool compatibility analysis, OpenAPI selection, en…
Aziel Runtime
io.github.AzielEliab/aziel-runtime
Provides a governed MCP runtime with registry discovery, controlled tool execution, provenance receipts, integrity checks, memory…
agent-exec
io.sslip.128.221.67.45.agent-exec/agent-exec
Provides pay-per-use sandbox code execution, temporary storage, distributed locks, attestations, durable watches, and process han…
HeyClaude — Claude & AI workflow directory
io.github.JSONbored/heyclaude
Searches and evaluates a registry of Claude Code agents, MCP servers, skills, and tools, providing entry details, compatibility, …