Can the AI resolve or close findings in Semgrep natively?

Yes. This server supports mutable actions. By invoking `update_finding_status`, your AI agent can shift a specific semantic flaw to 'mitigated', 'fixed', 'ignored', or 'false_positive' updating the registry in real-time.

How can I deploy a new custom SAST rule via chat?

Simply ask the LLM: 'Draft a semantic grep rule to ban hardcoded API keys in Python and deploy it'. The agent will natively format the JSON structure required and call `create_rule`, sending it directly to all repositories.

Do I need to supply a 'Deployment Slug' for every request?

Most API queries require the deployment context. To ensure smooth interactions, just tell the agent your organization slug once (or let it query `list_deployments` to fetch the default one). The agent will remember it for the rest of the conversation loop.

Semgrep MCP Server for OpenAI Agents SDK 10 tools — connect in under 2 minutes

Name: Semgrep
Availability: InStock
Author: Vinkius

openai.github.io/openai-agents-python/mcp

Built by Vinkius GDPR 10 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Semgrep through the Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails — no manual schema definitions required.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp

async def main():
    # Your Vinkius token — get it at cloud.vinkius.com
    async with MCPServerStreamableHttp(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as mcp_server:

        agent = Agent(
            name="Semgrep Assistant",
            instructions=(
                "You help users interact with Semgrep. "
                "You have access to 10 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from Semgrep"
        )
        print(result.final_output)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* 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 OpenAI Agents SDK auto-discovers all 10 tools from Semgrep through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns — chain multiple agents where one queries Semgrep, another analyzes results, and a third generates reports, all orchestrated through the Vinkius.

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 OpenAI Agents 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 OpenAI Agents SDK via MCP

Follow these steps to integrate the Semgrep MCP Server with OpenAI Agents SDK.

Install the SDK

Run pip install openai-agents in your Python environment

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Run the script

Save the code above and run it: python agent.py

Explore tools

The agent will automatically discover 10 tools from Semgrep

Why Use OpenAI Agents SDK with the Semgrep MCP Server

OpenAI Agents SDK provides unique advantages when paired with Semgrep through the Model Context Protocol.

Native MCP integration via `MCPServerSse` — pass the URL and the SDK auto-discovers all tools with full type safety

Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure

Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate

First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output

Semgrep + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the Semgrep MCP Server delivers measurable value.

Automated workflows: build agents that query Semgrep, process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents — one queries Semgrep, another analyzes results, a third generates reports

Data enrichment pipelines: stream data through Semgrep tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query Semgrep to resolve tickets, look up records, and update statuses without human intervention

Semgrep MCP Tools for OpenAI Agents SDK (10)

These 10 tools become available when you connect Semgrep to OpenAI Agents 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 OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents 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 OpenAI Agents SDK

Common issues when connecting Semgrep to OpenAI Agents SDK through the Vinkius, and how to resolve them.

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

Semgrep + OpenAI Agents SDK FAQ

Common questions about integrating Semgrep MCP Server with OpenAI Agents SDK.

How does the OpenAI Agents SDK connect to MCP?

Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.