Agent Discovery Doctor - llms.txt, agent card, mcp.json
此 MCP 可以做什么
Checks agent-discovery documents on hosts and validates llms.txt files, A2A agent cards, and related discovery metadata.
工具
输入模式
{'type': 'object', 'examples': [{'host': 'example.com'}], 'required': ['host'], 'properties': {'host': {'type': 'string', 'description': 'Hostname to check. https is assumed.'}, 'groups': {'type': 'string', 'description': 'Subset: agent, mcp, api, web, or all (default).'}, 'mcp_path': {'type': 'string', 'description': 'MCP endpoint path, e.g. /mcp: also checks documents relative to it.'}}, 'additionalProperties': False}
输入模式
{'type': 'object', 'examples': [{}], 'required': [], 'properties': {}, 'additionalProperties': False}
输出模式
{'type': 'object', 'required': ['ran', 'input_came_from', 'what_it_shows', 'answer', 'reproduce', 'this_is_not_a_mock', 'answered_by', 'license'], 'properties': {'ran': {'type': 'object', 'description': 'The tool name and the exact arguments that were run.'}, 'answer': {'type': 'object', 'description': 'The real structuredContent of that call, not a mock.'}, 'license': {'type': 'string'}, 'reproduce': {'type': 'string', 'description': 'A command that reproduces this answer.'}, 'answered_by': {'type': 'object'}, 'what_it_shows': {'type': 'string'}, 'input_came_from': {'type': 'string', 'description': "Where the canned input came from — always this host's own data."}, 'this_is_not_a_mock': {'type': 'string'}}, 'description': "This server's own worked example, executed for real on a canned input from this host's own data.", 'additionalProperties': True}
输入模式
{'type': 'object', 'examples': [{'name': 'owners.json'}], 'properties': {'name': {'type': 'string', 'description': 'Document name or path, e.g. owners.json. Omit for the catalogue.'}}, 'additionalProperties': False}
输入模式
{'type': 'object', 'examples': [{'xml': 'https://e.com/docs/a\nhttps://e.com/blog/b'}], 'required': ['xml'], 'properties': {'xml': {'type': 'string', 'description': 'The sitemap XML, or a plain list of URLs.'}, 'title': {'type': 'string', 'description': 'H1 to use; default from the hostname.'}, 'summary': {'type': 'string', 'description': 'The blockquote line.'}, 'max_per_section': {'type': 'integer', 'maximum': 200, 'minimum': 1, 'description': 'Links per section, default 40.'}}, 'additionalProperties': False}
输入模式
{'type': 'object', 'examples': [{}], 'required': [], 'properties': {}, 'additionalProperties': False}
输出模式
{'type': 'object', 'required': ['takes_no_arguments', 'what_this_is', 'this_hosts_discovery_documents', 'what_is_missing_here', 'who_has_been_observed_asking_for_these', 'no_request_was_made', 'answered_by', 'this_call_touched', 'reproduce', 'caveats', 'license', 'independent'], 'properties': {'caveats': {'type': 'array', 'items': {'type': 'string'}}, 'license': {'type': 'string'}, 'reproduce': {'type': 'string'}, 'answered_by': {'type': 'object'}, 'independent': {'type': 'boolean'}, 'what_this_is': {'type': 'string'}, 'this_call_touched': {'type': 'object'}, 'takes_no_arguments': {'type': 'boolean'}, 'no_request_was_made': {'type': 'string'}, 'what_is_missing_here': {'type': 'array'}, 'to_do_this_for_your_own_host': {'type': 'string'}, 'this_hosts_discovery_documents': {'type': 'object', 'description': 'Per-document verdicts, the group rollup and the score.'}, 'who_has_been_observed_asking_for_these': {'type': 'object'}}, 'description': 'Every agent-discovery document this server tracks, checked against this host with no network request, plus the clients observed asking for each.', 'additionalProperties': True}
输入模式
{'type': 'object', 'examples': [{'json': '{"name":"My Agent"}'}], 'required': ['json'], 'properties': {'json': {'type': 'string', 'description': 'The agent card JSON itself, not a URL.'}}, 'additionalProperties': False}
输入模式
{'type': 'object', 'examples': [{'text': '# Site\n\n> One line.\n\n## Docs\n\n- [Guide](https://e.com/g): start here.'}], 'required': ['text'], 'properties': {'text': {'type': 'string', 'description': 'The llms.txt content itself, not a URL.'}}, 'additionalProperties': False}
输入模式
{'type': 'object', 'examples': [{}], 'required': [], 'properties': {}, 'additionalProperties': False}
输出模式
{'type': 'object', 'required': ['you', 'we_book_you_as', 'we_have_seen_you', 'answered_by', 'this_call_touched', 'caveats', 'license', 'independent'], 'properties': {'you': {'type': 'object', 'description': 'The user-agent you sent and the address you came from.'}, 'caveats': {'type': 'array', 'items': {'type': 'string'}, 'description': 'What this answer does NOT establish — a user-agent is a claim.'}, 'license': {'type': 'string'}, 'answered_by': {'type': 'object', 'description': 'Which server answered, at which endpoint.'}, 'independent': {'type': 'boolean', 'description': 'This host is independent and unaffiliated.'}, 'we_book_you_as': {'type': 'object', 'description': "The class this host's own instrument records for that user-agent."}, 'we_have_seen_you': {'type': 'object', 'description': 'Whether this user-agent appears in the published observation window.'}, 'this_call_touched': {'type': 'object', 'description': 'Exactly which files were read to answer. No third party is contacted.'}}, 'description': 'Facts about the caller, derived only from the headers of this request and from files this host already publishes.', 'additionalProperties': True}
近期工具变更
类似的 MCP 服务器
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, …