Semgrep MCP Server for Vercel AI SDK 10 tools — connect in under 2 minutes
The Vercel AI SDK is the TypeScript toolkit for building AI-powered applications. Connect Semgrep through Vinkius and every tool is available as a typed function. ready for React Server Components, API routes, or any Node.js backend.
ASK AI ABOUT THIS MCP SERVER
Vinkius supports streamable HTTP and SSE.
import { createMCPClient } from "@ai-sdk/mcp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";
async function main() {
const mcpClient = await createMCPClient({
transport: {
type: "http",
// Your Vinkius token. get it at cloud.vinkius.com
url: "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
},
});
try {
const tools = await mcpClient.tools();
const { text } = await generateText({
model: openai("gpt-4o"),
tools,
prompt: "Using Semgrep, list all available capabilities.",
});
console.log(text);
} finally {
await mcpClient.close();
}
}
main();
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
About Semgrep MCP Server
Connect the Semgrep AppSec platform directly to your AI agent to radically accelerate code security triaging. Instead of forcing developers to jump between their IDE and the Semgrep dashboard, empower your AI to pull 'Findings', analyze the vulnerable syntax, and instantly close false positives.
The Vercel AI SDK gives every Semgrep tool full TypeScript type inference, IDE autocomplete, and compile-time error checking. Connect 10 tools through Vinkius and stream results progressively to React, Svelte, or Vue components. works on Edge Functions, Cloudflare Workers, and any Node.js runtime.
What you can do
- Triage Findings (Bugs) — Instruct the agent to grab the latest CI vulnerability findings and immediately push a status update to mark it as fixed, ignored, or mitigated (
update_finding_status) - Rule Management — Request the AI to look at a newly discovered bad coding pattern and command it to write and deploy a matching custom semantic rule (
create_rule) to your organizational deployment - Project & Deployment Scoping — Map out all repositories running Semgrep actions and check their overarching security health scores in milliseconds
- Comprehensive Forensics — Fetch granular SCA and SAST semantic flaw definitions, including exact snippets, CVE links, and the specific bad lines causing the trigger
The Semgrep MCP Server exposes 10 tools through the Vinkius. Connect it to Vercel AI SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.
How to Connect Semgrep to Vercel AI SDK via MCP
Follow these steps to integrate the Semgrep MCP Server with Vercel AI SDK.
Install dependencies
Run npm install @ai-sdk/mcp ai @ai-sdk/openai
Replace the token
Replace [YOUR_TOKEN_HERE] with your Vinkius token
Run the script
Save to agent.ts and run with npx tsx agent.ts
Explore tools
The SDK discovers 10 tools from Semgrep and passes them to the LLM
Why Use Vercel AI SDK with the Semgrep MCP Server
Vercel AI SDK provides unique advantages when paired with Semgrep through the Model Context Protocol.
TypeScript-first: every MCP tool gets full type inference, IDE autocomplete, and compile-time error checking out of the box
Framework-agnostic core works with Next.js, Nuxt, SvelteKit, or any Node.js runtime. same Semgrep integration everywhere
Built-in streaming UI primitives let you display Semgrep tool results progressively in React, Svelte, or Vue components
Edge-compatible: the AI SDK runs on Vercel Edge Functions, Cloudflare Workers, and other edge runtimes for minimal latency
Semgrep + Vercel AI SDK Use Cases
Practical scenarios where Vercel AI SDK combined with the Semgrep MCP Server delivers measurable value.
AI-powered web apps: build dashboards that query Semgrep in real-time and stream results to the UI with zero loading states
API backends: create serverless endpoints that orchestrate Semgrep tools and return structured JSON responses to any frontend
Chatbots with tool use: embed Semgrep capabilities into conversational interfaces with streaming responses and tool call visibility
Internal tools: build admin panels where team members interact with Semgrep through natural language queries
Semgrep MCP Tools for Vercel AI SDK (10)
These 10 tools become available when you connect Semgrep to Vercel AI SDK via MCP:
create_rule
Allows developers to forbid project-specific bad patterns securely and continuously across the enterprise repositories. Create a customized Semgrep security rule within the platform
delete_rule
Delete a custom Semgrep security rule from the deployment
get_finding_details
Explains the exact malicious code block, suggests semantic fixes, states whether it is blocking PRs in CI, and links to CVE data (if an SCA supply chain defect). Get atomic details for a specific Semgrep flaw
get_metrics
Typically consumed to render executive security dashboards. Get AppSec metrics and compliance stats for Semgrep
get_project
Search for a precise Semgrep project by exact repository name
list_deployments
The primary key is the deployment slug identifier. Almost all subsequent API operations targeting rules, projects, or findings will require this deployment slug to define the scope. List Semgrep organizational deployments
list_findings
Findings provide snippet details, file line numbers, severity, and rule types. Fetch global static analysis security findings for a deployment
list_projects
Projects maintain a link between developers and static security scan outputs over time. List Semgrep projects (repositories) monitored in a deployment
list_rules
The rules are structured YAML definitions that search for semantic anti-patterns in codebases (e.g., unparameterized SQL queries, hardcoded AWS keys). List Semgrep semantic rules deployed globally
update_finding_status
Valid states generally include active, fixed, false_positive, ignored, mitigated. Resolving findings through this API cleans up the developer experience when managing compliance queues. Mark a Semgrep finding state (e.g., fixed, false positive)
Example Prompts for Semgrep in Vercel AI SDK
Ready-to-use prompts you can give your Vercel AI SDK agent to start working with Semgrep immediately.
"List the most severe unmitigated findings currently breaking our CI/CD pipeline on the 'vinkius/cloud' repository."
"Mark vulnerability issue ID #58032 as a 'false_positive' using the update finding tool."
"Review the company's Semgrep performance metrics focusing on fix rate."
Troubleshooting Semgrep MCP Server with Vercel AI SDK
Common issues when connecting Semgrep to Vercel AI SDK through the Vinkius, and how to resolve them.
createMCPClient is not a function
npm install @ai-sdk/mcpSemgrep + Vercel AI SDK FAQ
Common questions about integrating Semgrep MCP Server with Vercel AI SDK.
How does the Vercel AI SDK connect to MCP servers?
createMCPClient from @ai-sdk/mcp and pass the server URL. The SDK discovers all tools and provides typed TypeScript interfaces for each one.Can I use MCP tools in Edge Functions?
Does it support streaming tool results?
useChat and streamText that handle tool calls and display results progressively in the UI.Connect Semgrep with your favorite client
Step-by-step setup guides for every MCP-compatible client and framework:
Anthropic's native desktop app for Claude with built-in MCP support.
AI-first code editor with integrated LLM-powered coding assistance.
GitHub Copilot in VS Code with Agent mode and MCP support.
Purpose-built IDE for agentic AI coding workflows.
Autonomous AI coding agent that runs inside VS Code.
Anthropic's agentic CLI for terminal-first development.
Python SDK for building production-grade OpenAI agent workflows.
Google's framework for building production AI agents.
Type-safe agent development for Python with first-class MCP support.
TypeScript toolkit for building AI-powered web applications.
TypeScript-native agent framework for modern web stacks.
Python framework for orchestrating collaborative AI agent crews.
Leading Python framework for composable LLM applications.
Data-aware AI agent framework for structured and unstructured sources.
Microsoft's framework for multi-agent collaborative conversations.
Connect Semgrep to Vercel AI SDK
Get your token, paste the configuration, and start using 10 tools in under 2 minutes. No API key management needed.