Agentic Web Wiki — standards reference, probe, validate, template
概览
作者提供的说明(英文原文)
Look up 133 agentic-web standards, live-probe any domain, validate manifests, generate boilerplate.
PopNx MCP 的三大支柱
这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。
- 用户评价i暂无评价评价功能将在后续阶段与账户功能一起开放
- 我们的基础检查i3 项中通过 3 项依据公开信息检查;尚未扫描代码
- 使用情况i非常新★ –
它能帮你做什么
我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。
- 连接方式: 在云端运行
- 传输方式: Streamable HTTP
- 分类: 文档、表格与办公
安装
选择你使用的 AI 应用,然后复制设置。
安装之前
- 基础检查:3 项中通过 3 项
- 在作者的服务器上运行:你向它提出的内容会经过他们的服务器。
- 可以做 11 件事(工具) define, get, search, has …
- 注册中心没有列出需要填写的密钥。
你需要
- 在云端运行无需安装任何东西,通过互联网连接
你用的是哪个应用?
在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。
适用于网页版、桌面版和手机版 Claude:
- 打开 Settings → Connectors
- 点击 Add custom connector
- 粘贴下面的地址,然后点击 Add
- 如果要求登录,请登录作者的服务
https://agenticweb.wiki/mcp在终端中运行这条命令
claude mcp add --transport http probe https://agenticweb.wiki/mcp或者自己复制设置
粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"probe": {
"url": "https://agenticweb.wiki/mcp"
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
或者自己复制设置
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"probe": {
"type": "http",
"url": "https://agenticweb.wiki/mcp"
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
ChatGPT 只能连接互联网上的服务器:
- 打开网页版 ChatGPT → Settings → Connectors (Apps)
- 点击 Create 或 Add(部分套餐需要先在 Advanced 中开启 Developer mode)
- 粘贴下面的地址,起个名字,然后保存
- 如果要求登录,请登录作者的服务
https://agenticweb.wiki/mcp菜单名称可能因套餐和版本不同而略有差异。
你的选择通过 Cookie 保存在这台设备上,无需账户。
这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
它能做什么
工具名称和描述与服务器在 2026年11月7日 报告的完全一致。这些内容由作者撰写,不是我们写的;我们以纯文本形式显示。
defineDefine an agentic-web glossary term or standard by id, name, or alias. Returns { kind, id, name, definition_md, related_protocols, url } (or nearest-term hints on unknown-term error). Use define for concept definitions; use get when you need a standard's full specification record
getFetch one standard's complete specification record by id, acronym, filename, or RFC number. Returns { id, name, step, status, governance, version, spec_url, probe, adoption, summary_md, url } (or unknown-id error with nearest matches). Use get for a known standard; use search to
searchSearch 132 standards and 52 glossary terms by keyword, acronym, alias, or 'A vs B' pair (pass q or alias query, 2–200 chars). Returns { results (top 10 ranked by title/alias/body match), matching_terms, comparison_url } or nearest_ids hints when empty. Use search for keyword disc
hasCheck one public origin over HTTPS for a single standard or manifest (rate-limited to 120/min). Returns { origin, id, found, outcome, status, url, reason, article } without grading the full site. Use has for a fast single-file check; use probe to scan all 37 paths at once, or val
probeScan a public origin across 37 agent-facing paths and headers (24h KV cache by default; pass fresh: true to re-probe live with a 5-min per-origin cooldown, rate-limited to 30/min). Returns { found_ids, found, absent, coverage, extracted, connect_recipe }; pass brief: true for fou
changesList machine-verified specification changes since a YYYY-MM-DD date or ISO-8601 timestamp (newest first, default 50, max 200). Returns { since, count, entries: [{ date, record_id, field, old, new, source }] } filtered optionally by lifecycle step or record_id. Use changes for fie
staleList standards whose last_verified date is older than N days (default 30, oldest first), optionally filtered by lifecycle step. Returns { threshold_days, count, records: [{ id, name, step, last_verified, days_since_verified }] }. Use stale to audit verification freshness; use cha
validate_manifestAudit a public origin across 37 agent manifests (24h KV cache; fresh: true re-probes live with 5-min cooldown, 30/min limit) or validate local file text in-memory before deploy (pass id + content, no network fetch). Returns { grade (A+ to F), score, subscores, conformance_summary
templateGenerate in-memory starter boilerplate for any of the 12 supported manifest ids (ard, ai-catalog-well-known-file, llms-txt, agents-md, anthropic-agent-skills-format, mcp-server-cards, a2a, ai-crawler-tokens-robots, api-catalog-rfc9727, security-txt, auth-md, okf) without writing
askRecommend and rank standards to implement for an engineering goal (pass question/q and/or use_case + audience filters), or compare named protocols head-to-head when the query names 2+ standards. Returns { use_case, audience, standards (ranked by tier and adoption), starter_bundle
digestFetch the curated daily agentic-web news and adoption digest for a YYYY-MM-DD date (defaults to latest). Returns { date, headline, highlights, new_instances, spec_changes, stats }; pass list: true to return available dates only, or compact: true (alias: include_stats: false) to o
基础检查i
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月10日
- ✓ 通过
作者与仓库一致
注册名称已通过域名 agenticweb.wiki 验证(注册中心会核实域名所有权)
- … 尚未检查
仍在维护
我们还没有从 GitHub 读取这个仓库
- … 尚未检查
有许可证
我们还没有从 GitHub 读取这个仓库
- ✓ 通过
端点有响应
在 310 毫秒内响应(HTTP 200)
- – 不适用
使用 OAuth 登录
无需登录
- ✓ 通过
工具描述中没有隐藏指令
已读取 11 个工具描述,未发现针对 AI 的隐藏指令
与“文档、表格与办公”中的其他服务器比较i
- 星标数多于此分类中其他 3651 个服务器的 0%
- 发布到注册中心的时间比此分类中其他 3651 个服务器的 67% 更新
- 基础检查结果等于或优于此分类中其他 3651 个服务器的 100%
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
常见问题
Agentic Web Wiki — standards reference, probe, validate, template 安全吗?
它在 3 项适用的基础检查中通过了 3 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
它需要哪些密钥或代码?
注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。
它在我的电脑上运行还是在云端?
它在作者的云端运行。通过互联网连接,无需安装,但你发送的内容会经过作者的服务器。
它还在维护吗?
GitHub 仓库最后更新于–,最新版本(1.3.0)于15天前进入注册中心。
哪些应用可以使用它?
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接,所以接受远程 MCP 服务器的应用也可以使用,例如开启开发者模式的 ChatGPT。
有什么可以替代它?
同一分类中有:Agent-Native Calendar, Excel MCP Server, MCP Server for Excel
替代选择
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:↓ 每周下载量i★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
Excel MCP Server
Create and edit Excel files with AI: charts, PivotTables, formulas. No Excel needed.
MCP Server for Excel
Excel automation for AI - Sheets, Power Query, DAX, VBA, Tables, Ranges and more. Windows only.
作者的 README
打开 README
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
agenticweb-data (wiki.agenticweb/probe)
Canonical Open Dataset, JSON Schemas, Bi-Temporal Change Log, Executable Probe Rules & Stateless MCP Server (`https://agenticweb.wiki/mcp`) for [`agenticweb.wiki`](https://agenticweb.wiki)
Maintained by Belgravia Labs LLC (info@belgravialabs.com), agenticweb-data is the verified, schema-enforced ground-truth repository powering agenticweb.wiki and its public Model Context Protocol (MCP) server `wiki.agenticweb/probe` at `https://agenticweb.wiki/mcp`.
Every merged commit on main is validated in CI against strict JSON Schemas and automatically ingested to rebuild the public registry (132 standards, 51 glossary terms, 151 head-to-head comparisons, 1,137+ probed origins) and the 11-tool stateless Streamable HTTP MCP server.
Connect to the MCP Server (https://agenticweb.wiki/mcp)
- Transport: Stateless Streamable HTTP (
POST https://agenticweb.wiki/mcp, MCP2026-07-28specification; also backward-compatible with2025-11-25,2025-06-18, and2025-03-26). - Authentication: None required (public read-only endpoint).
- SEP-2127 Server Card:
https://agenticweb.wiki/mcp/server-card(application/mcp-server-card+json) - ARD 1.0 Manifest:
https://agenticweb.wiki/.well-known/ard.json
Quick Configuration (claude_desktop_config.json / .mcp.json / Cursor)
{
"mcpServers": { "agenticweb": { "type": "http", "url": "https://agenticweb.wiki/mcp" } } }
claude mcp add --transport http agenticweb https://agenticweb.wiki/mcp
Tools (tools/list & tools/call — 11 Tools)
All 11 tools are deterministic, read-only (readOnlyHint: true, destructiveHint: false, idempotentHint: true), and execute at the Cloudflare edge in <15 ms.
| Tool | Parameters | Description |
|---|---|---|
| `define` | term: string | Define an agentic-web glossary term (51 terms) or standard (132 protocols) by id, name, or alias. Returns definition_md, related_protocols, and standard_summary_md. |
| `get` | id: string | Fetch one standard's complete record by id ("mcp"), acronym ("A2A"), RFC ("RFC 9421"), or well-known path ("llms.txt", "/.well-known/ard.json"): status, governance, version, spec URL, probe rule, evidence, disputes, and freshness. |
| `search` | q?: string, query?: string | Search all 132 standards and 51 glossary terms by name, acronym, alias, question, or use case ("A2A vs MCP", "mcp.auth"). Returns top 10 matches plus nearest_ids and nearest_terms on misses. |
| `ask` | question?: string, q?: string, use_case?: string, audience?: string | Recommend and rank standards to implement for an engineering goal ("let agents pay per request"), or compare named protocols head-to-head with /compare/ / links. |
| `has` | origin: string, id: string | Live-check a public origin for one standard ("llms-txt", "ard", "mcp-server-cards"). Returns found, url, status, reason, and article. |
| `probe` | origin: string, brief?: boolean, compact?: boolean | Live-scan a public origin across 35 agent-facing standards in parallel (24h KV cached). Pass brief: true for found_ids + extracted resources only, or compact: true to return absent_ids[] instead of full absent/skipped maps (~85% smaller). |
| `validate_manifest` | origin?: string, id?: string, content?: string, verify?: boolean, bridge?: boolean, brief?: boolean, compact?: boolean | Validate an origin's 12 agent manifests (ard, ai-catalog-well-known-file, mcp-server-cards, a2a, llms-txt, agents-md, anthropic-agent-skills-format, api-catalog-rfc9727, ai-crawler-tokens-robots, security-txt, auth-md, okf) live or validate local content pre-commit, grade readiness (A+ to F), and return agent_routing + connect_recipe. |
| `template` | id: string, domain?: string, from_live?: boolean, name?: string, description?: string, mcp_url?: string, api_url?: string, agent_url?: string, contact?: string | Generate spec-compliant starter boilerplate (contents, target_path, content_type, recommended_headers) for any of the 10 publishable agent manifests (or pass from_live: true to pre-populate from the origin's live files). |
| `changes` | since: string, step?: string, record_id?: string, limit?: number | Query machine-verified changelog diffs (old -> new, summary, evidence URL, date) since YYYY-MM-DD. |
| `stale` | days?: number, step?: string | List standards whose last_verified date is older than days (default 30), optionally filtered by lifecycle step. |
| `digest` | date?: string, list?: boolean, compact?: boolean, include_stats?: boolean | Fetch the daily Agentic Web Digest (date: "latest" or "YYYY-MM-DD"), list all published dates (list: true), or pass compact: true / include_stats: false to omit the stats block. |
Example JSON-RPC 2.0 Calls
# 1. Define a term or protocol
curl -sS -X POST https://agenticweb.wiki/mcp \ -H "Content-Type: application/json" -H "Accept: application/json" \ -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"define","arguments":{"term":"MCP"}}}'
2. Validate a domain in compact mode
curl -sS -X POST https://agenticweb.wiki/mcp \ -H "Content-Type: application/json" -H "Accept: application/json" \ -d '{"jsonrpc":"2.0","id":2,"method":"tools/call","params":{"name":"validate_manifest","arguments":{"origin":"cloudflare.com","compact":true}}}'
MCP Resources (resources/list & resources/read — 6 Resources)
agenticweb://standards/all— All 132 protocol records + the 9-step facet vocabulary (https://agenticweb.wiki/data/standards.json).agenticweb://glossary/all— All 51 glossary terms with definitions, aliases, and sources (https://agenticweb.wiki/data/terms.json).agenticweb://use-cases/all— All 15 engineering use cases mapped to the standards that serve them.agenticweb://probes/all— All 132 probe rules and skip reasons (https://agenticweb.wiki/data/probes.json).agenticweb://versions/all— Spec versions, canonical paths, deprecated paths, and legacy shapes (https://agenticweb.wiki/data/versions.json).agenticweb://census/summary— Empirical adoption census summary across 1,137+ probed origins and 906 panel domains.
MCP Prompts (prompts/list & prompts/get — 3 Workflows)
audit-domain({ domain }) — Audit a domain's manifests, explain spec violations, and recommend the 3 highest-impact missing files.make-repo-agent-ready({ domain, project_type? }) — Generate all agent-facing files for a repository usingtemplate().compare-protocols({ first, second }) — Compare two standards side-by-side across all 12 schema dimensions.
Repository Contents
| File / Directory | Description | Schema |
|---|---|---|
| `protocols.json` | Canonical records for 132 agentic-web standards, specifications, IETF drafts, and conventions across 9 lifecycle steps (discover, identify, permit, read, act, coordinate, pay, present, account). | schema/protocols.schema.json |
| `terms.json` | 51 technical glossary terms with multi-paragraph definitions, aliases, related protocol IDs, and verified sources. | schema/terms.schema.json |
| `probes.json` | Executable HTTP probe rules (35 active GET/HEAD rules + skip reasons) used by /check/ /, probe, has, and validate_manifest. | schema/probes.schema.json |
| `changes.json` | Bi-temporal change ledger recording specification version bumps, draft renewals, and status transitions. | schema/changes.schema.json |
| `instances.json` | Verified live production deployments implementing agentic-web protocols in the wild. | schema/instances.schema.json |
| `census.json` & `ecosystem-census.json` | Empirical origin-probe adoption census across 1,137+ probed domains and 906 readiness panel domains. | — |
| `digests/` & `stats/` | Daily cited Agentic Web Digest issues and panel adoption telemetry snapshots. | schema/digest.schema.json |
| `server.json` | Official MCP Registry descriptor (wiki.agenticweb/probe, v1.20261025.0). | — |
Security & License
- Security Policy: See SECURITY.md or
https://agenticweb.wiki/.well-known/security.txt. - License: Code, JSON Schemas, probe rules, and MCP definitions are licensed under the MIT License. Dataset records and editorial prose summaries are licensed under Creative Commons Attribution 4.0 International (CC BY 4.0).