TanStack AI is a TypeScript SDK for building applications that stream AI responses, call tools, run agents, produce structured output, and handle multimodal or realtime interactions. Developers use it across frameworks and AI providers through shared typed interfaces and provider adapters. The catalogue entries are add-ons for working with this SDK.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add TanStack/ai --skill ai-mcpgit clone --depth 1 https://github.com/TanStack/aiWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/tanstack/ai/ai-mcp)<a href="https://agentmods.dev/skills/tanstack/ai/ai-mcp"><img src="https://agentmods.dev/badge/skills/tanstack/ai/ai-mcp/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/tanstack/ai/ai-mcp"><img src="https://agentmods.dev/badge/skills/tanstack/ai/ai-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 207 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 650 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00077 | $0.14075 |
| Opus 5.5 | $0.00031 | $0.05630 |
| Sonnet 5.5 | $0.00015 | $0.02815 |
| Haiku 4.5 | $0.00008 | $0.01408 |
Grade A, and why
ai-mcp scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Call `server.fetch(request)` in your HTTP route. How it starts
The opening of the file, as written. The whole thing — 1,497 lines — stays where its author put it; the contents beside it link to each section on GitHub.
@tanstack/ai-mcp
This skill covers the @tanstack/ai-mcp package. Read ai-core/tool-calling/SKILL.md
first — MCP tools flow into chat() the same way hand-written tools do.
If you host the tools yourself, use createMCPServer.
When to use this package
Use @tanstack/ai-mcp when:
- A third-party MCP server exposes tools you want an agent or chat loop to call.
- You want to read MCP server resources (files, text, data) or prompts into a
chat()message list. - You want generated TypeScript types for an external MCP server's tool
signatures (via the bundled
generateCLI). - You are running tool execution on the server side and want to connect to MCP servers with HTTP (Streamable HTTP or SSE) or stdio transports.
- You want to expose your own tools as an MCP server over HTTP or stdio.
Do NOT use this package for browser/client-side code — MCP connections are server-side only.
Install
pnpm add @tanstack/ai-mcp
The package has these subpaths:
.exportscreateMCPClient,createMCPClients, converters, and types../stdioexports the Node-only client transportstdioTransport../serverexportscreateMCPServer../server/stdioexportsserveMCPStdio../appsexportscreateMcpAppCallHandler../harnessexportscreateHarnessMcpServerand themcp()harness plugin.createHarnessMcpServerserves a TanStack AI harness as an MCP server. Seedocs/harness/mcp-server.md, and "mcp(): MCP servers in a harness" below../connectorexportsmcpConnector: one OAuth MCP server as a harness plugin. Seedocs/harness/mcp.md../eventsexportscreateMCPEventWebhook,inMemoryMCPEventStore, andcreateMCPEventSecret(experimental MCP Events / SEP-3415).
Import ./stdio and ./server/stdio only from Node code.
Those entries use Node I/O.
Host an MCP server
Import createMCPServer from @tanstack/ai-mcp/server.
Pass tools from toolDefinition().server().
Call server.fetch(request) in your HTTP route.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago Changed · +157 lines ede11c6411de
- 12d ago Changed · +53 lines 06917fa46594
- 19d ago Changed · +4 lines b2c5f9112030
- 23d ago Changed · +9 lines 3ea5160e3fb1
- 28d ago Changed · +299 lines · +8 tokens per session 599325162685
- 1mo ago Changed · +29 lines b02ece93bf91
- 1mo ago Changed · +3 lines 780519e0b036
- 1mo ago Changed · +88 lines 4e8488b60fa5
- 1mo ago First seen · 855 lines · 69 tokens per session scan A 21e582367454
ai-mcp is a skill published in the GitHub repository TanStack/ai (3,247 stars, last pushed today), licensed MIT. It adds 77 tokens to every session and 14,075 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
tech-design
A guided process for writing a backend technical design from a product requirements document or feature description. A technical design explains how a feature should work in code and services.
claude-api
Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude…
setup-writing-style
Learns how the user writes from their own sent messages and docs, and builds a voice profile so future drafts sound like them instead of generic AI. The profile is saved as the my-writing-style skill. Use when the user asks to set up, learn, or capture their writing voice, or complains that drafts sound generic or…
stripe-projects
Provision SaaS services + sync creds via Stripe Projects.
facebook_cli
Use when the user provides a Facebook URL or asks to read personal posts, comments, reactions, friends, timelines, profiles, stories, feeds, groups, events, or saved items, or to discover public events happening near a place, nearby, or in a local area on a date, or to create, edit, publish, or delete their own…
keybindings-help
Use when the user wants to customize keyboard shortcuts, rebind keys, add chord bindings, or modify /.claude/keybindings.json. Examples: "rebind ctrl+s", "add a chord shortcut", "change the submit key", "customize keybindings".