AI SDK — Watchlist | MCP100 Index

MCP100 Assessment

Watchlist / Tracking

Why we’re tracking it

Follow-up value is specific to AI SDK model calls consuming MCP tools, resources, prompts and elicitation: Does the AI SDK keep MCP tool approval and definition-drift handling consistent with its model-call APIs?

Reviewed Oct 5, 2026 · Documentation review; complete setup workflow not independently tested

Best fit

TypeScript applications that need provider-agnostic AI generation, tool use and agent workflows.

What we know

AI SDK is Vercel's TypeScript toolkit for building AI applications across multiple model providers, frameworks and Node.js environments.

Maintenance / activity evidence

ai 7.0.127 published 2026-10-01T19:20:23.718Z

Tracking evidence observed Oct 5, 2026. These dated signals do not establish current maintenance. Reviewed enrichment confidence: high.

Verification gaps / watch-outs

Installation and comprehensive security have not been independently audited.
Library-level; actual authority depends on provider and tools supplied by the application. Writes: Depends on developer-supplied tools.
Provider-specific API credentials.
Sensitive access: Model-provider credentials, Application data passed to models/tools

The SDK itself is a library; data exposure and authority depend on the configured model providers and tool integrations.

Full authority, access and evidence limits are available in Review context and Access & risk.

Popularity

27,149 shared-repository stars · 110.3M package downloads / 30 days

Stars observed Oct 6, 2026. Downloads observed Oct 6, 2026.

All limitations / Review context

Does the AI SDK keep MCP tool approval and definition-drift handling consistent with its model-call APIs?

The bounded review of the publisher's documented AI SDK model calls consuming MCP tools, resources, prompts and elicitation and release notices identified no disclosed material condition preventing an accurately scoped public tracking entry. The resource's operational permissions remain uncertainty; this assessment does not certify installation safety.

The SDK itself is a library; data exposure and authority depend on the configured model providers and tool integrations.
Library-level; actual authority depends on provider and tools supplied by the application.
Provider-specific API credentials.
Prompts and application data may be sent to configured model providers.
Reviewed write actions: Depends on developer-supplied tools
Sensitive access: Model-provider credentials, Application data passed to models/tools
Installation, client compatibility and comprehensive security have not been independently audited. Authentication and access depend on the configured services.
Runtime behavior, dependencies and undisclosed vulnerabilities were not independently audited.
Documented tool authority and any remote data handling must be checked before installation or use.
Tool inventory, client matrix and permissions completeness were not requirements for this Radar tracking review.
This general SDK/UI package is MCP-relevant integration infrastructure; its separately published MCP client/manager module remains a distinct identity.
This is an SDK, not an MCP server.
Provider authentication, costs and data handling depend on the connected model provider.

Original activity observations

ai 7.0.127 published 2026-10-01T19:20:23.718Z

Technical identity

npm/ai

Exact implementation source: https://www.npmjs.com/package/ai ↗
Reviewed resource type: SDK
Repository identity: vercel/ai
Package identity: npm:ai

Evidence & Sources

Evidence basis: Recorded source evidence
Setup runtime verification: Not independently runtime-tested by MCP100 for this setup workflow.

Reviewed Oct 5, 2026 · Latest source observation Oct 6, 2026

Package registry ↗
ai
Recorded package identity, distribution or download evidence.
Includes references whose attribution is not established.
Evidence source ↗
ai-sdk.dev/docs/ai-sdk-core/mcp-tools
Source material retained for this review.
GitHub repository ↗
vercel/ai
Repository reference; implementation attribution is not established for every document.
Includes references whose attribution is not established.

Setup · Watchlist

SDK setup

Publisher instructions.

Source evidence observed Oct 14, 2026.

Additional setup details required — see the specific gaps below.

Warning

Not runtime tested, no third-party installation, network authorization, paid calls, or mutation executed.
Do not claim production service is available based on README alone.
Vercel AI SDK package, not standalone MCP Server; integrate in application code
Targeted 2026-10-13 re-research: Vercel AI SDK package, not standalone MCP Server; npm install ai only adds a library.
Vercel AI SDK package, not standalone MCP Server; npm install ai only adds a library.
Official npm publisher package page README inspected for this exact npm identity; static research only. Some setup statements are conservatively summarized; no source code or live client execution checked. V2 review did not run any live client.
Avoid write, payment, token transfer, publishing, sending, booking and remote account changes as tests.
Vercel AI SDK; app dependency only. Integrate through application code, not MCP client registration.
Replace credential, action and registration placeholders; follow the matching publisher/client prerequisites. No execution performed.
Use the matching host, actual registration name and original installation environment; this does not revoke credentials.

Install SDK / application integration
Publisher instructions
Vercel AI SDK package, not standalone MCP Server; integrate in application code | Publisher npm README revisited on 2026-10-14; exact identity retained.
Reviewed setup example · Publisher instructions
npm install ai
Configure / authenticate
MCP100 setup guide
Vercel AI SDK library, not a standalone MCP server. Install in Node project and configure the specific model provider integration separately.
Check connection
Suggested check
Verify project import and SDK application example; no standalone MCP tools should appear.
Remove / uninstall / revoke
MCP100 setup guide
Remove the framework/library from the consuming application using its package manager and undo its generated integration configuration. This is NOT a client-registered standalone MCP server.
Remove installed package / application · MCP100 composed guide
npm uninstall ai

Official Documentation & Sources

What it does

AI SDK is Vercel's TypeScript toolkit for building AI applications across multiple model providers, frameworks and Node.js environments.

Capability: AI & Reasoning
Resource type: SDK
Industry: Software & Technology
Best fit: TypeScript applications that need provider-agnostic AI generation, tool use and agent workflows.

Representative uses

Generate text and structured data
Build tool-using agents
Connect model providers
Build generative user interfaces

Limitations

This is an SDK, not an MCP server.
Provider authentication, costs and data handling depend on the connected model provider.

Reviewed access

Access & risk

Review the exact access boundary before connecting this MCP to accounts, credentials, or sensitive data.

Authentication: Provider-specific API credentials.
Permissions: Library-level; actual authority depends on provider and tools supplied by the application.
Data handling: Prompts and application data may be sent to configured model providers.
Cost: usage_based
Risk and cautions: The SDK itself is a library; data exposure and authority depend on the configured model providers and tool integrations.

Access scope and cautions

Write actions: Depends on developer-supplied tools
Sensitive access: Model-provider credentials Application data passed to models/tools
Risk level: moderate

FAQ

Based on reviewed evidence as of 2026-10-06. Watchlist tracking is not a recommendation or a security certification.

Which tasks are documented for this implementation?

The reviewed tasks include: Generate text and structured data; Build tool-using agents; Connect model providers; Build generative user interfaces.

What authentication is documented?

Provider-specific.

Can it modify data or perform write operations?

Documented write actions include: Depends on developer-supplied tools. Recorded permission boundary: Library-level; actual authority depends on provider and tools supplied by the application.

What data-handling boundary should I consider?

Prompts and application data may be sent to configured model providers. Recorded sensitive-access context: Model-provider credentials; Application data passed to models/tools.

What limitations and risks should I check before use?

The SDK itself is a library; data exposure and authority depend on the configured model providers and tool integrations. This is an SDK, not an MCP server. Provider authentication, costs and data handling depend on the connected model provider. Runtime behavior, dependencies and undisclosed vulnerabilities were not independently audited. Documented tool authority and any remote data handling must be checked before installation or use.

What cost model is recorded?

The reviewed cost model is usage based. This classification does not establish current prices, quotas or the cost of every downstream operation. Check the applicable service terms before authorizing paid actions.

Is this an official MCP?

Vercel is listed as First-party MCP in MCP100’s current evidence.