@ai-sdk/mcp

Name: @ai-sdk/mcp Review
Item: @ai-sdk/mcp
Rating: 3.8
Author: Aaron Matthews

Connector Development Solid

Works inClaude Code Claude Cowork Claude Chat

Solid Scanned — metadata only

Enables AI SDK applications to access external tools and data sources through a standardized protocol, reducing integration friction and expanding LLM capabi…

The **Model Context Protocol (MCP) client** for the [AI SDK](https://ai-sdk.dev/docs) lets you connect to MCP servers and use their tools with AI SDK functions like `generateText` and `streamText`.

Connect Claude to MCP servers and execute remote tools within your application code
Integrate external tool capabilities into AI SDK text generation workflows automatically
Build multi-tool AI systems where Claude accesses specialized services via MCP protocols

25,740 starsApache-2.0 (commercial OK)FreeNo code needed

Why it matters

Enables AI SDK applications to access external tools and data sources through a standardized protocol, reducing integration friction and expanding LLM capabilities without rewriting agent logic.

Best for

Development teams building agentic applications that need to connect AI models to external APIs, databases, or custom services via MCP servers.

Works in

Claude Code Claude Cowork Claude Chat

Source

https://www.npmjs.com/package/@ai-sdk/mcp

By GitHub Actions

How to Get It

Option 1: Claude Desktop AppOpen the Customize panel in the sidebar → browse connectors → search and add. Works in Claude Code, Claude Cowork, and Claude Chat.

Option 2: Paste into Claude CodeCopy the command below and paste it into a Claude Code conversation. Claude will run it for you.

Command

npx -y @ai-sdk/mcp

Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.

Auto-generated from the tool's public listing — not hands-on verified. Cross-check against the source repo's README before running.

First thing to try

Once it’s connected, paste this into Claude:

Help me connect Claude to MCP servers and execute remote tools within my application code

CostFree

Trust Signals Auto-scanned

Stars25,740Last updated2026-07-23LicenseApache-2.0 (OK for commercial use)Weekly downloads1,805,900Known CVEsNone foundSources: GitHub Advisory Database + OSV.dev · Scanned 2026-07-23 · scanner v1

Data & Access

Data processingPrompts sent to Anthropic API. Enterprise/Team plans exclude training.

Community Pulse New

Direct OS level API to control computers using AI (MCP server/client template) — Hacker News · 2 pts
Add MCP Apps to Your AI SDK Application — Hacker News · 1 pts
Addressing security and quality issues with MCP tools in AI Agents — Hacker News · 1 pts

3 mentions across 1 sources

Reviewer notes

Auto-scanned review. These are observations, not a security certification.

Scored from trust signals (evidence-eval-v1): 25,740 GitHub stars; contributors unknown; last commit 0d ago; license Apache-2.0.

Things to check

Scanned, not hands-on tested — this entry was auto-scanned from public metadata (GitHub metrics, license, security flags). No reviewer has run it, and no tool-specific limitations have been documented yet.

How to evaluate tools before deploying →

Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.

Evaluation Scores

Evaluation

Ease of Use

4/5

Versatility

5/5

Reliability

3/5

Security

3/5

Overall score3.85 / 5.00 SolidEvaluatedJul 2026

Scored from trust signals (evidence-eval-v1): 25,740 GitHub stars; contributors unknown; last commit 0d ago; license Apache-2.0.

← Back to the Claude Observatory