Kyma API

com.kymaapi由 kymaapi.com 发布官方发布者v1.0.3更新于 Nov 2, 2026

Live model catalog with prices and measured uptime, rankings, credits and spend, spend-capped chat.

已验证Streamable HTTP可网页运行数据与分析AI 与机器学习

概览

AI 生成的概览

Kyma API 的 MCP 服务器提供 LLM 网关的实时模型目录、价格、排名、可用率和你的消费数据,并带一个受消费上限保护的聊天工具。

可以做什么
  • 浏览模型目录:列出模型、查看单个模型详情、比较价格、查看基于真实流量的排名与实测 30 天可用率,并获取面向编程代理的模型推荐。
  • 估算与查询成本:预估一次调用的费用、搜索 Kyma 文档、执行健康检查。
  • 查看账户情况:余额、本连接的额度上限、已用与剩余、按模型统计的用量、单次请求记录和额度流水,以及账单页面链接。
  • 可选地以掩码形式列出 REST API 密钥,并设置低余额邮件提醒。
  • 通过任意模型发送聊天补全,可指定 token 与费用上限,每次回复都会报告本次费用和剩余额度。
适用场景
适合让助手按价格和实测可用率挑选模型、查看 Kyma 余额与消费上限,或通过一个网关偶尔发起计费聊天调用,而无需把 API 密钥粘贴到客户端中。
运行要求
远程端点,使用 OAuth 2.1 登录(PKCE、动态客户端注册);仅支持 stdio 的客户端可用 npx 运行 npm 桥接包。需要 Kyma 账户;桥接方式可在 KYMA_MCP_KEY 中填入 Kyma MCP 密钥以跳过浏览器登录。需要能访问托管端点。
安装前请注意
send_message 是唯一会消耗额度的工具;每个连接有独立密钥,默认上限为每 30 天 10 美元(可在 1 至 500 美元间调整),达到上限后调用会被拒绝。请保持客户端对 send_message 的确认提示开启,并把模型输出视为不可信文本。可选的 KYMA_MCP_KEY 是机密;REST 密钥会被有意拒绝。请求日志保留 90 天。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Kyma API,将其添加到工作区。
  2. 连接 所需的 凭据。它们会被私密存储,绝不会在公开页面上展示。
  3. 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/com.kymaapi%2Fkyma/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。 客户端会在首次连接时完成 OAuth 登录。

{
  "mcpServers": {
    "kyma-api": {
      "type": "http",
      "url": "https://mcp.kymaapi.com/mcp"
    }
  }
}

README

[Kyma API]

Kyma API MCP Server

Kyma API is an LLM API gateway that routes one key to 100+ models and publishes measured uptime per model.
Every model behind one endpoint, with public rankings and a spend cap you set.
https://mcp.kymaapi.com/mcp

[MCP Registry] [npm] [Docs] [License]

Install · Tools · Security and spend · Examples · Troubleshooting · Registries

Kyma API is an LLM gateway: one OpenAI-compatible endpoint (plus an Anthropic-compatible one) in front of open and frontier models, with uptime measured per model from real traffic and scheduled probes. This server gives any MCP client the live catalog, prices, rankings, uptime and your own spend as read tools, and one chat tool that is guarded by a per-connection spend cap.

  • Hosted, remote, OAuth sign-in. Streamable HTTP with OAuth 2.1, PKCE and dynamic client registration. No API key is pasted into the client.
  • A dedicated key per connection. Separate from your REST API keys, capped at $10 per 30 days by default (adjustable from $1 to $500 on the approval screen or at kymaapi.com/integrations), revocable at any time.
  • Read tools never charge. Catalog, pricing, rankings, uptime, credits, spend, your usage and your requests are free to call and auto-approved by most clients.
  • send_message is priced before it spends. The client must allow it first; max_cost_usd is enforced by deriving a max_tokens that fits the ceiling from the catalog price, so a call above it is refused before anything is sent. Every reply reports what the call cost, what has been spent and the cap.
  • Measured uptime, not a promise. get_model_uptime returns the 30-day rate per model from kymaapi.com/status. If a route fails mid-request, Kyma retries the same model on another route.
  • A read-only endpoint for reviewers. https://mcp.kymaapi.com/mcp/readonly accepts the same tokens but keeps only read scopes for the request: no send_message, no set_low_balance_alert, whatever the grant was approved with. Metadata: /.well-known/oauth-protected-resource/mcp/readonly.
  • Beyond chat. The same Kyma key covers speech-to-text, text-to-speech, embeddings, rerank, image and video through the REST API; list_models shows all of them.

Install

Claude Code
bash
claude mcp add --transport http kyma https://mcp.kymaapi.com/mcp

Run /mcp to sign in. This repository is also a Claude Code plugin (.claude-plugin/plugin.json + .mcp.json).

Claude.ai and Claude Desktop

Settings → Connectors → Add custom connector → paste https://mcp.kymaapi.com/mcp → sign in with Kyma.

Cursor

One click: Add to Cursor

Or in .cursor/mcp.json:

json
{ "mcpServers": { "kyma": { "url": "https://mcp.kymaapi.com/mcp" } } }
VS Code (GitHub Copilot)

One click: Install in VS Code

Or in .vscode/mcp.json:

json
{ "servers": { "kyma": { "type": "http", "url": "https://mcp.kymaapi.com/mcp" } } }
Codex CLI
toml
# ~/.codex/config.toml[mcp_servers.kyma]url = "https://mcp.kymaapi.com/mcp"
bash
codex mcp login kyma
Cline

Cline → MCP Servers → Configure MCP Servers:

json
{ "mcpServers": { "kyma": { "url": "https://mcp.kymaapi.com/mcp", "type": "streamableHttp" } } }

Cline CLI: cline mcp add kyma https://mcp.kymaapi.com/mcp --transport streamableHttp --yes. Cline asks you to sign in with Kyma on first use.

Gemini CLI
bash
gemini extensions install https://github.com/kyma-api/kyma-mcp-plugin

The first tool call opens a browser for OAuth sign-in, handled by Gemini CLI.

Grok
  • grok.com: Connectors → New Connector → Custom → paste the URL.
  • Grok Build: this repository is a Claude Code format plugin; Grok Build loads it as-is.
ChatGPT (Developer Mode)

Settings → Connectors (Plus, Pro, Business, Enterprise, Edu) → add the URL → sign in. ChatGPT connections never see get_topup_link.

Any stdio-only client
json
{ "mcpServers": { "kyma": { "command": "npx", "args": ["-y", "@kyma-api/mcp-server"] } } }

The bridge runs mcp-remote against the hosted URL, so the tools are exactly the hosted ones. Set KYMA_MCP_KEY=km-… (a Kyma MCP key from kymaapi.com/integrations, not a REST kyma-… key) to skip the browser. Source: bridge/.

Tools

18 tools. 16 appear on a default connection; list_keys and set_low_balance_alert appear when their optional scopes are granted on the approval screen.

ToolWhat it doesScopeApproval
list_modelsLive model catalog with prices, context window and capabilitiesmodels.readauto, read-only
get_modelOne model's detailsmodels.readauto, read-only
list_pricingPrices across the catalogmodels.readauto, read-only
list_rankingsTop models and apps from real trafficmodels.readauto, read-only
get_model_uptimeMeasured 30-day uptime per modelmodels.readauto, read-only
recommend_modelBest model and config for Cline, Cursor, Claude Code and other agentsmodels.readauto, read-only
search_docsSearch Kyma docsmodels.readauto, read-only
pingHealth checkmodels.readauto, read-only
get_creditsYour balanceusage.readauto, read-only
get_spendThis connection's cap, spent, remaining and reset dateusage.readauto, read-only
get_usageYour requests, tokens and cost by model over a windowusage.readauto, read-only
get_requestOne request by id: model served, tokens, cost, routes triedusage.readauto, read-only
estimate_costWhat a call would cost before you make itmodels.readauto, read-only
get_transactionsRecent credit ledger entriesusage.readauto, read-only
get_topup_linkBalance and the billing page (a link, never a checkout)usage.readauto, read-only
list_keysYour REST API keys by name, maskedkeys.read (optional)auto, read-only
set_low_balance_alertBalance at which Kyma emails youbilling.alerts (optional)asks once
send_messageA chat completion through any model; the only tool that spends credit; optional max_tokens and max_cost_usdchat.completionsasks once; no charge without your Allow

Every send_message reply carries cost, spent_usd and spend_cap_usd, plus structuredContent with the model that served it and the routes tried. get_spend shows what is left before you call it.

Security and spend

  • What a connection can do: read the catalog, prices, rankings, uptime, your balance and this connection's spend; send chat completions up to its cap; with optional scopes, list your keys masked and set a low-balance alert.
  • What it can never do: create or delete API keys, change billing or payment methods, buy credits, register accounts, or see provider internals. Those scopes do not exist on this server.
  • Spend cap: each connection gets a dedicated key with its own cap, $10 per 30 days by default, adjustable from $1 to $500. The cap is enforced on the server; when it is reached send_message returns an error until the window resets or you raise the cap at kymaapi.com/integrations.
  • Tokens and keys: access tokens live 7 days, refresh tokens 90 days and rotate on use; connection keys are stored hashed (SHA-256) and can be revoked without touching your REST API keys.
  • Prompt injection: model output that reaches your agent is untrusted text. Keep your client's confirmation prompt on for send_message, and do not let the agent paste keys or balances into other tools.
  • Data: request logs are kept 90 days for billing reconciliation and abuse handling, then deleted. Kyma does not train on customer data. Privacy: kymaapi.com/privacy.

Skills

Three skills teach an agent how to use the tools well: pick-a-model (compare price, measured uptime and fit), check-spend-and-credits (balance, cap, remaining, reset date), send-a-test-completion (one billed call, only after an explicit Allow). They live in skills/ and install into any agent that reads skills:

bash
npx skills add kyma-api/kyma-mcp-plugin

Examples

Prompts you can paste once connected:

  • "Which models under $1 per million output tokens have the best 30-day uptime?"
  • "Recommend a model and config for Cline, then show its price."
  • "How much of this connection's budget is left, and when does it reset?"
  • "Send 'summarize this in one line' to qwen-3.6-plus and tell me what it cost."
  • "Show the top apps on Kyma rankings this week."

Troubleshooting

  • Sign-in loops or "connector failed": remove the connection and add it again; the client's stored token may belong to a revoked connection. Check kymaapi.com/integrations for the active list.
  • send_message says the cap is reached: raise the cap at kymaapi.com/integrations or wait for the 30-day window to reset; get_spend shows the date.
  • A tool returns 403 insufficient scope: the connection was approved without that optional scope. Reconnect and tick it on the approval screen.
  • Stdio bridge cannot sign in: set KYMA_MCP_KEY to a Kyma MCP key (km-…) created at kymaapi.com/integrations; REST kyma-… keys are rejected on purpose.
  • Remote connections drop: some clients need a reconnect after long idle periods; the server itself is stateless.

Registries and marketplaces

  • Official MCP Registry: com.kymaapi/kyma (server.json in this repo, published with mcp-publisher, namespace verified by DNS on kymaapi.com)
  • Smithery: kyma-api/kyma
  • npm stdio bridge: @kyma-api/mcp-server
  • Gemini CLI extensions gallery: gemini-extension.json and the repo topic gemini-cli-extension
  • Submitted, pending review: Cursor Marketplace, xAI Grok Build marketplace, Docker MCP Catalog, Cline Marketplace, mcp.so

About Kyma API

Kyma is an LLM API gateway: open and frontier models, one endpoint, pay per token, with automatic failover across providers and per-model measured uptime published at kymaapi.com/models. New accounts start with free credit.

来源:README.md,提交 ace8e75

工具

0
该服务器需要登录,因此 SourceWeft 无法在没有账号的情况下读取其工具,也未收录。已连接账号所能看到的内容可能因账号及其权限而异。

版本历史

1
  1. v1.0.3最新Sep 16, 2026

评分

已满足适用检查项的 85%

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15 分

    请让服务器在无凭据时响应 tools/list,或发布可在沙箱中无凭据启动的软件包。

  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分