360 Secure SkillHub
360 安全技能中心

Kyma API: connect my tool

该 Skill 指导把 Cursor、Cline、Claude Code、Codex CLI 等编码工具，以及 LangChain、Vercel AI SDK、OpenAI SDK 配置到 Kyma 的兼容端点或 MCP 服务，并调用模型推荐接口填入模型 ID。

kyma-api
热度 7.65
最近更新 2026-09-13 09:38:58
分类：开发依赖：第三方 API / 读写文件应用场景：API 集成 / 代码生成 / 模板

安装技能

复制下面的话术发给你的 Agent，它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill： npx secure-skills-cli add kyma-connect-my-tool
Metadata
name
connect-my-tool
description
Write the exact config to point a coding agent, IDE, SDK or framework at Kyma API. Covers Cursor, Cline, Claude Code, Codex CLI, Continue, Roo Code, Aider, OpenClaw, LangChain, the Vercel AI SDK and the raw OpenAI SDK. Use when the user names one of these tools and asks to connect it, add Kyma as a provider, point it at Kyma, or set a base URL and key.

Connect my tool to Kyma API

Kyma is an OpenAI-compatible endpoint (plus an Anthropic-compatible one) in front of open and frontier models, and a hosted MCP server. Most tools below take a base URL and a key; a few also speak MCP directly, which needs no key in the config at all.

Get a key

  • No account yet: https://kymaapi.com/signup?src=skill:connect-my-tool (starts with free credit).
  • Already have one: https://kymaapi.com/keys?src=skill:connect-my-tool. Keys start with kyma-.

Steps

  1. Identify the tool from the table below. If it is not listed, it almost certainly still works: see the any-OpenAI-client guide: base URL https://api.kymaapi.com/v1, key kyma-your-api-key.
  2. Write the exact field names and values from that row into the file, env var or settings screen the tool reads. Do not rename a field or guess a flag that is not shown here.
  3. Recommend a model: if the tool has an agent profile in the table, call https://api.kymaapi.com/v1/models/recommend?agent=<agent>. If it does not, call https://api.kymaapi.com/v1/models/recommend?usecase=coding (swap coding for another value from the response's available_usecases if the user's job is not coding). Never pass an agent value that is not in the table; the endpoint will just fall through to a generic answer.
  4. Paste the returned recommended.model id (or one of its alternatives) into the config.

OpenAI-compatible tools

Tool Where Fields Agent profile
Cursor Settings (Cmd/Ctrl+,) → search "OpenAI" API Key kyma-your-api-key, API Base URL https://api.kymaapi.com/v1, add a custom model id cursor
Cline Settings gear → provider "OpenAI Compatible" Base URL https://api.kymaapi.com/v1, API Key kyma-your-api-key, Model ID <model id>. CLI: cline auth -p openai -k kyma-your-api-key -m <model> -b https://api.kymaapi.com/v1 cline
Roo Code Settings → provider "OpenAI Compatible" Base URL https://api.kymaapi.com/v1, API Key kyma-your-api-key, Model ID <model id> roo-code
Aider Shell env, then run export OPENAI_API_KEY="kyma-your-api-key" and export OPENAI_API_BASE="https://api.kymaapi.com/v1", then aider --model openai/<model id> aider
Continue config.yaml provider: openai, model: <model id>, apiBase: https://api.kymaapi.com/v1, apiKey: kyma-your-api-key, roles: [chat, edit, apply] (or [autocomplete]) none, use usecase=coding
OpenClaw ~/.openclaw/openclaw.json Under models.providers.kyma: "baseUrl": "https://api.kymaapi.com/v1", "apiKey": "kyma-your-api-key", "api": "openai-completions", a models array of {id, name}; set agents.defaults.model.primary to "kyma/<model id>" openclaw
LangChain (Python) ChatOpenAI(...) base_url="https://api.kymaapi.com/v1", api_key="kyma-your-api-key", model="<model id>" none, use usecase=coding
LangChain (JS) new ChatOpenAI({...}) configuration: { baseURL: "https://api.kymaapi.com/v1" }, apiKey: "kyma-your-api-key", model: "<model id>" none, use usecase=coding
Vercel AI SDK npm install @kyma-api/ai-sdk ai import { createKyma } from "@kyma-api/ai-sdk"; const kyma = createKyma({ apiKey: "kyma-your-api-key" }), or set KYMA_API_KEY and import the default kyma export; pick a model with kyma("<model id>") none, use usecase=coding
OpenAI SDK (Python) OpenAI(...) base_url="https://api.kymaapi.com/v1", api_key="kyma-your-api-key" none, use usecase=coding
OpenAI SDK (JS) new OpenAI({...}) baseURL: "https://api.kymaapi.com/v1", apiKey: "kyma-your-api-key" none, use usecase=coding

Any tool reading plain env vars (most CLIs and scripts) takes OPENAI_API_KEY="kyma-your-api-key" and OPENAI_BASE_URL="https://api.kymaapi.com/v1".

MCP-native tools

These speak MCP directly: no key goes in the config, sign-in happens through OAuth on first use.

  • Claude Code: claude mcp add --transport http kyma https://mcp.kymaapi.com/mcp, then /mcp to sign in.
  • Cursor: one-click at https://mcp.kymaapi.com/mcp, or add to .cursor/mcp.json: { "mcpServers": { "kyma": { "url": "https://mcp.kymaapi.com/mcp" } } }.
  • Codex CLI: in ~/.codex/config.toml: [mcp_servers.kyma] then url = "https://mcp.kymaapi.com/mcp"; then run codex mcp login kyma.
  • Cline: MCP Servers → Configure MCP Servers: { "mcpServers": { "kyma": { "url": "https://mcp.kymaapi.com/mcp", "type": "streamableHttp" } } }, or cline mcp add kyma https://mcp.kymaapi.com/mcp --transport streamableHttp --yes.

MCP gives read tools (catalog, pricing, uptime, spend) plus one chat tool guarded by a spend cap the user sets on first connect (default $10 / 30 days). For a tool in this section, offer MCP as the option, and fall back to its OpenAI-compatible config above only if the user does not want to sign in through OAuth.

Claude Code needs the bare host

Claude Code reads an Anthropic-shaped API, not the OpenAI-compatible one, and ANTHROPIC_BASE_URL takes the host without /v1 (Claude Code appends the path itself):

export ANTHROPIC_BASE_URL="https://api.kymaapi.com"
export ANTHROPIC_AUTH_TOKEN="kyma-your-api-key"

https://api.kymaapi.com/v1 here makes every request 404. This is the one tool in this whole skill whose base URL does not match the OpenAI-compatible one. Recommend a model for it with https://api.kymaapi.com/v1/models/recommend?agent=claude-code.

Do not

  • Do not invent a config field, CLI flag, or file path not shown above or in docs.kymaapi.com/guides. If the user's tool is not listed and is not plain OpenAI-compatible, say so and point at the docs site instead of guessing.
  • Do not pass an agent= value to /v1/models/recommend that is not in the table above.
  • Do not name or speculate about which inference backend serves a model.
  • Do not hardcode a price or uptime number in your answer; call /v1/models or /v1/models/recommend and quote what comes back.