이 MCP로 할 수 있는 일
Searches, recommends, retrieves, downloads, and lists safety-reviewed Agent Skills and SKILL.md files from a registry.
도구
입력 스키마
{'type': 'object', 'required': ['slug'], 'properties': {'slug': {'type': 'string', 'pattern': '^[^/]+/[^/]+$', 'description': 'Skill identifier as owner/name, e.g. anthropic/pdf'}}, 'additionalProperties': False}
출력 스키마
{'type': 'object', 'required': ['slug', 'files'], 'properties': {'slug': {'type': 'string', 'description': 'owner/name of the skill'}, 'files': {'type': 'array', 'items': {'type': 'object', 'required': ['path'], 'properties': {'note': {'type': 'string', 'description': 'How to treat this entry when content is not inlined'}, 'path': {'type': 'string', 'description': 'Relative path inside the skill folder'}, 'content': {'type': 'string', 'description': 'UTF-8 text content'}, 'source_url': {'type': 'string', 'description': 'Fetch URL for large or binary companions not inlined'}, 'content_base64': {'type': 'string', 'description': 'Base64 content for binary files'}}}, 'description': 'Every file in the skill, SKILL.md first'}}}
입력 스키마
{'type': 'object', 'required': ['slug'], 'properties': {'slug': {'type': 'string', 'pattern': '^[^/]+/[^/]+$', 'description': 'Skill identifier as owner/name, e.g. anthropic/pdf'}}, 'additionalProperties': False}
출력 스키마
{'type': 'object', 'required': ['slug', 'title', 'description'], 'properties': {'slug': {'type': 'string', 'description': 'owner/name identifier, e.g. anthropic/pdf'}, 'tags': {'type': 'array', 'items': {'type': 'object', 'additionalProperties': True}}, 'type': {'enum': ['single', 'pack'], 'type': 'string', 'description': 'single SKILL.md or a multi-file pack'}, 'files': {'type': 'array', 'items': {'type': 'object', 'additionalProperties': True}, 'description': 'Companion files for packs'}, 'title': {'type': 'string', 'description': 'Human-readable skill title'}, 'raw_md': {'type': ['string', 'null'], 'description': 'Verbatim SKILL.md including frontmatter when stored'}, 'body_md': {'type': 'string', 'description': 'Markdown body of SKILL.md'}, 'license': {'type': ['string', 'null'], 'description': 'SPDX license id when declared'}, 'category': {'type': 'string', 'description': 'Category name'}, 'verified': {'type': 'boolean', 'description': 'Published by a verified publisher'}, 'categories': {'type': 'array', 'items': {'type': 'object', 'additionalProperties': True}}, 'commit_sha': {'type': ['string', 'null'], 'description': 'Pinned upstream commit'}, 'owner_name': {'type': 'string', 'description': 'Publisher display name'}, 'repo_stars': {'type': ['number', 'null'], 'description': 'GitHub stars of the source repository'}, 'description': {'type': 'string', 'description': 'What the skill does and when an agent should use it'}, 'source_repo': {'type': ['string', 'null'], 'description': 'Upstream repository'}, 'owner_handle': {'type': 'string', 'description': 'Publisher handle'}, 'security_flags': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Capability flags: docs_only, network_calls, executes_scripts, reads_secrets, untrusted_install'}, 'install_snippet': {'type': 'string', 'description': 'One-line install command'}, 'ai_audit_verdict': {'type': ['string', 'null'], 'description': 'Safety review verdict: pass, caution, warning, fail or inconclusive'}}, 'description': 'Full skill record.', 'additionalProperties': True}
입력 스키마
{'type': 'object', 'properties': {'limit': {'type': 'integer', 'maximum': 100, 'minimum': 1, 'description': 'Maximum number of results (default 10)'}, 'based_on': {'type': 'string', 'pattern': '^[^/]+/[^/]+$', 'description': 'Skill slug (owner/name) to base recommendations on'}}, 'additionalProperties': False}
출력 스키마
{'type': 'object', 'required': ['items'], 'properties': {'items': {'type': 'array', 'items': {'type': 'object', 'required': ['slug'], 'properties': {'slug': {'type': 'string', 'description': 'owner/name identifier, e.g. anthropic/pdf'}, 'title': {'type': 'string', 'description': 'Human-readable skill title'}, 'license': {'type': ['string', 'null'], 'description': 'SPDX license id when declared'}, 'category': {'type': 'string', 'description': 'Category name'}, 'owner_name': {'type': 'string', 'description': 'Publisher display name'}, 'repo_stars': {'type': ['number', 'null'], 'description': 'GitHub stars of the source repository'}, 'description': {'type': 'string', 'description': 'What the skill does and when an agent should use it'}, 'owner_handle': {'type': 'string', 'description': 'Publisher handle'}, 'security_flags': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Capability flags: docs_only, network_calls, executes_scripts, reads_secrets, untrusted_install'}, 'install_snippet': {'type': 'string', 'description': 'One-line install command'}, 'ai_audit_verdict': {'type': ['string', 'null'], 'description': 'Safety review verdict: pass, caution, warning, fail or inconclusive'}}, 'description': 'A skill as listed in search and leaderboard results.', 'additionalProperties': True}, 'description': 'Matching skills, best first'}}}
입력 스키마
{'type': 'object', 'required': ['query'], 'properties': {'type': {'enum': ['single', 'pack'], 'type': 'string', 'description': 'Restrict to single-file skills or multi-file packs'}, 'limit': {'type': 'integer', 'maximum': 100, 'minimum': 1, 'description': 'Maximum number of results (default 20)'}, 'query': {'type': 'string', 'description': 'Natural-language query or keywords describing the task or skill'}, 'category': {'type': 'string', 'description': 'Restrict to one category slug, e.g. coding, devops, data, security'}, 'min_rating': {'type': 'number', 'maximum': 5, 'minimum': 0, 'description': 'Minimum average rating, 0 to 5'}, 'verified_only': {'type': 'boolean', 'description': 'Return only skills from verified publishers (default false)'}}, 'additionalProperties': False}
출력 스키마
{'type': 'object', 'required': ['items'], 'properties': {'items': {'type': 'array', 'items': {'type': 'object', 'required': ['slug'], 'properties': {'slug': {'type': 'string', 'description': 'owner/name identifier, e.g. anthropic/pdf'}, 'title': {'type': 'string', 'description': 'Human-readable skill title'}, 'license': {'type': ['string', 'null'], 'description': 'SPDX license id when declared'}, 'category': {'type': 'string', 'description': 'Category name'}, 'owner_name': {'type': 'string', 'description': 'Publisher display name'}, 'repo_stars': {'type': ['number', 'null'], 'description': 'GitHub stars of the source repository'}, 'description': {'type': 'string', 'description': 'What the skill does and when an agent should use it'}, 'owner_handle': {'type': 'string', 'description': 'Publisher handle'}, 'security_flags': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Capability flags: docs_only, network_calls, executes_scripts, reads_secrets, untrusted_install'}, 'install_snippet': {'type': 'string', 'description': 'One-line install command'}, 'ai_audit_verdict': {'type': ['string', 'null'], 'description': 'Safety review verdict: pass, caution, warning, fail or inconclusive'}}, 'description': 'A skill as listed in search and leaderboard results.', 'additionalProperties': True}, 'description': 'Matching skills, best first'}}}
입력 스키마
{'type': 'object', 'properties': {'limit': {'type': 'integer', 'maximum': 100, 'minimum': 1, 'description': 'Maximum number of results (default 20)'}, 'range': {'enum': ['30d', 'all'], 'type': 'string', 'description': 'Ranking window: last 30 days or all time (default all)'}, 'category': {'type': 'string', 'description': 'Restrict to one category slug, e.g. coding, devops, data, security'}}, 'additionalProperties': False}
출력 스키마
{'type': 'object', 'required': ['items'], 'properties': {'items': {'type': 'array', 'items': {'type': 'object', 'required': ['slug'], 'properties': {'slug': {'type': 'string', 'description': 'owner/name identifier, e.g. anthropic/pdf'}, 'title': {'type': 'string', 'description': 'Human-readable skill title'}, 'license': {'type': ['string', 'null'], 'description': 'SPDX license id when declared'}, 'category': {'type': 'string', 'description': 'Category name'}, 'owner_name': {'type': 'string', 'description': 'Publisher display name'}, 'repo_stars': {'type': ['number', 'null'], 'description': 'GitHub stars of the source repository'}, 'description': {'type': 'string', 'description': 'What the skill does and when an agent should use it'}, 'owner_handle': {'type': 'string', 'description': 'Publisher handle'}, 'security_flags': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Capability flags: docs_only, network_calls, executes_scripts, reads_secrets, untrusted_install'}, 'install_snippet': {'type': 'string', 'description': 'One-line install command'}, 'ai_audit_verdict': {'type': ['string', 'null'], 'description': 'Safety review verdict: pass, caution, warning, fail or inconclusive'}}, 'description': 'A skill as listed in search and leaderboard results.', 'additionalProperties': True}, 'description': 'Matching skills, best first'}}}
최근 도구 변경
유사한 MCP 서버
hyperion
Acts as a paid MCP tool marketplace and utility gateway with server discovery, HTTP and JavaScript tools, research, data conversi…
XGR MCP Gateway
Provides an MCP gateway for XGRChain and XDaLa workflows, including blockchain explorer queries, session inspection, transaction …
aaaa-nexus — Formally Verified AI Safety APIs
Provides formally constrained agent safety and governance APIs for tool authorization, prompt-injection-resistant execution, iden…
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
Resolves missing agent capabilities and provides MCP and HTTP endpoint checks, tool compatibility analysis, OpenAPI selection, en…
Aziel Runtime
Provides a governed MCP runtime with registry discovery, controlled tool execution, provenance receipts, integrity checks, memory…
agent-exec
Provides pay-per-use sandbox code execution, temporary storage, distributed locks, attestations, durable watches, and process han…
HeyClaude — Claude & AI workflow directory
Searches and evaluates a registry of Claude Code agents, MCP servers, skills, and tools, providing entry details, compatibility, …