Alter Onboarding

io.github.AlterAIDev由 GitHub 账号 AlterAIDev 发布v0.4.2更新于 Oct 29, 2026

Guide developers from setup through a verified, policy-aware, audited Alter API call.

已验证Streamable HTTP可网页运行知识与记忆开发者工具

概览

AI 生成的概览

Alter 的入门引导服务器,帮助助手完成 Alter API 集成的搭建、验证与排错,并提供 SDK 接线与供应商 API 规格。

可以做什么
  • 按阶段和流程引导集成,返回下一步骤与初始集成文档
  • 按语言和目标生成 SDK 接线代码与可运行的调用模式
  • 按 slug 或关键词检索 Alter 文档
  • 浏览供应商、其 API 操作及完整操作 schema
  • 解释运行时策略语言,并把 CLI 错误或退出码映射为修复建议
  • 提供首次调用与多用户隔离的验证配方
适用场景
适合开发者在代码库中接入 Alter 时使用:需要分步指引、生成的 SDK 代码、供应商操作细节、策略规则,或排查集成失败原因。
运行要求
远程端点 mcp.alterauth.com,使用 streamable HTTP;未声明认证、环境变量或请求头。服务器只返回指引和代码,命令与 CLI 需由开发者在本地执行。
安装前请注意
返回的代码和命令需由开发者自行运行,验证配方会发起真实 API 调用并检查审计记录,应用生成的接线前应先审阅。供应商操作 schema 与策略语法来自 Alter 线上后端,结果反映该服务的当前状态。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Alter Onboarding,将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Web executable,通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。

交给智能体安装

把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体,或 SourceWeft 对话中。智能体会读取该服务器的安装指南,先向你展示发布者、端点和登录方式,经你同意后再把它添加到你的客户端。密钥不会写进任何命令。

阅读 https://sourceweft.com/mcp/io.github.AlterAIDev%2Falter-onboarding/install.md,并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前,先告诉我它的发布者、端点和登录方式,等我确认。不要把 API 密钥写进命令或我会提交的文件;问我密钥应从哪里获取。

查看智能体所依据的安装指南

其他 MCP 客户端

把它添加到你客户端的 mcpServers 配置中。

{
  "mcpServers": {
    "alter-onboarding": {
      "type": "http",
      "url": "https://mcp.alterauth.com/mcp"
    }
  }
}

README

该仓库没有 README。

工具

14

list_phases

List the lifecycle phases this server serves (setup, modify) and what each is for.

无需输入参数。

list_skills

List the guidance Skills available on this server, with the phase each serves. Read a skill via its resource (skill://alter/<name>).

无需输入参数。

get_started

Begin or change an Alter integration. Without args: lists the phases. With `phase`: returns that phase's flows + a heuristic hint — classify the use case YOURSELF and call again with `goal` for the plan. If the use case spans multiple flows, run them sequentially.

输入参数goalphaseuse_case

next_step

Return the next step for a flow. Pass the goal (flow id) and the id of the last completed step (omit `after` for the first step). Run each step's detect command FIRST and skip the run command when detection passes. The design step also returns that flow's complete starter ALTER_INTEGRATION.md.

输入参数goal必填after

sdk_integration

Return the Alter SDK wiring (install + client init + request) to write into the developer's codebase, for a language and setup goal.

输入参数goal必填language必填

sdk_pattern

Return a runnable Alter SDK call pattern for a language: `proxy-call` (zero-egress proxy_request + HITL), `resolve-grant-by-user` (call as an end user via their delegated grant), `delegate-managed-secret` (the operator-side delegation step), or `resolve-ambiguous-grant` (an identity-mode call matched several of one user's grants: choose deliberately, never the first, and persist it; ask the developer at design time whether users can hold several accounts per provider). Use AFTER `sdk_integration` has wired the client.

输入参数pattern必填language必填

troubleshoot

Map a @alter-ai/cli exit code or error message to a remediation.

输入参数errorexit_code

verify_integration

Return a copy-pasteable recipe to VERIFY an integration works: `first-call` (code↔design, an audit row, correct attribution) or `per-user-isolation` (a multi-user/broker server runs two users under different credentials and rejects cross-user access). Guidance only — you run the commands.

输入参数scenario必填

fetch_doc

Fetch Alter documentation by slug (e.g. "quickstart"). Guides, indexes and skills are served in-band; generated provider operation and model pages link to the full public reference. Accepts any spelling the docs use: a bare slug, a leading slash, a #section anchor, a full docs.alterauth.com URL, or an older path that now redirects. Omit the slug to list every page.

输入参数slug

search_docs

Search every bundled page of the Alter documentation (docs and skill pages) by keywords: returns the best-matching pages with the section and a snippet that matched. Use it when a flow step or doc did not point you at the page you need, instead of guessing slugs or listing every page; then read one with fetch_doc and its slug.

输入参数limitquery必填

list_providers

List every provider with an ingested API spec in Alter's provider-spec catalog, with each spec's source and freshness. Optionally filter by `kind`. Start here, then call list_operations for a provider's operations.

输入参数kind

list_operations

List the API operations a provider exposes, live from Alter's provider-spec catalog (e.g. "what can I call on google?"). Returns operation ids + methods/paths, plus the spec's source and freshness. Omit `kind` to auto-detect the provider family; when the id exists in both oauth and managed you'll be asked to pass `kind`. Machine-readable rows ride in `structuredContent` (see this tool's outputSchema) — read those rather than parsing the prose.

输入参数kindlimitoffsetsearchprovider_id必填

get_operation_schema

Fetch one provider API operation's full contract — method, path, parameters, request/response schemas — live from Alter's provider-spec catalog, plus the spec's source and freshness. Get operation ids from list_operations first.

输入参数kindprovider_id必填operation_id必填

policy_language

The authoritative grammar of Alter's runtime-policy language, live from the deployed backend: every authorable rule type with its JSON body schema, caps, authorable levels, worked examples, and fail-closed semantics. Call with no arguments for the overview; pass `rule_type` (e.g. "content_match") for one type's full grammar. Use it before authoring rules with `alter policy rules create` — never guess a body shape. Vocabulary: the dashboard's "Runtime policies" surface, the docs' "policy", and `alter policy` are one feature, and the dashboard's "Require human approval" type is the `require_approval` rule type (its grant-editor block is the grant-level baseline of the same gate). The same grammar is what policy files carry: `alter policy validate|test|plan|apply` review rules in Git and CI, and a rule with a `code_owner` is changed through its file, never with `rules update`. Workflow prose: the `set-policy` modify flow (`get_started` with phase=modify), fetch_doc("guides/set-policies"), fetch_doc("guides/add-human-in-the-loop-approvals"), fetch_doc("guides/policy-as-code"), and fetch_doc("reference/cli/commands/policy").

输入参数rule_type

版本历史

8
  1. v0.4.2最新Oct 29, 2026
  2. v0.4.0Oct 20, 2026
  3. v0.3.0Oct 15, 2026
  4. v0.2.8Sep 29, 2026
  5. v0.2.7Sep 22, 2026
  6. v0.2.6Sep 22, 2026
  7. v0.2.5Sep 18, 2026
  8. v0.2.4Sep 16, 2026

评分

已满足适用检查项的 75%

该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。

  • 近 30 天内可连通必需25 分
  • 已声明认证方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 图标10 分
  • 文档15 分

    请声明包含 README 的 GitHub 仓库,或在 OAuth 受保护资源元数据中提供 resource_documentation。

  • 许可证10 分

    请在仓库或注册中心条目中声明许可证。