Safeguard
ChatGPT Integration

Safeguard for ChatGPT.

Connect Safeguard’s MCP server to ChatGPT by OpenAI and ask about your software supply chain security in natural language. Query vulnerabilities, SBOMs, packages, licenses, and compliance data — and let ChatGPT reason over your real security posture.

Add this connector URL
https://mcp.safeguard.sh/mcp/openai

This is Safeguard’s MCP server endpoint purpose-built for ChatGPT. Add it as a custom connector, then sign in to Safeguard and click Authorize access. Nothing to install.

Connector: Safeguard Security70+ security toolsOAuth 2.0 or MCP key
◈ the round trip — ask chatgpt, answered from your Safeguard workspace
Capabilities

What you can do in ChatGPT.

Once the Safeguard Security connector is enabled, ChatGPT can call 35+ security tools and read MCP resources and prompts on your behalf.

01

Query vulnerabilities & findings

Ask about CVEs, severities, and open findings across your projects in plain language — no query syntax required.

02

Explore SBOMs, packages & licenses

Inspect components, package versions, transitive dependencies, and license obligations pulled straight from your SBOMs.

03

AI-powered remediation plans

Generate concrete fix plans for npm, pip, Maven, Go, and Cargo projects — upgrade paths, breaking-change notes, and all.

04

Compare & analyze SBOMs

Diff and analyze SBOMs in both CycloneDX and SPDX formats to see what changed between builds and releases.

05

SCM integrations

Reach repositories across GitHub, GitLab, Bitbucket, and Azure DevOps to scope security questions to real code.

06

Risk scoring & compliance reporting

Surface risk scores and compliance posture, then turn the answers into reports your stakeholders can read.

07

Policy-gate enforcement

Evaluate policy gates for deployment readiness and understand exactly why a build would pass or be blocked.

08

Multi-tenant for enterprise

Built multi-tenant from the ground up, so large organizations can keep teams and data cleanly isolated.

Connect ChatGPT

Enable it in a few steps.

  1. 01

    Create your Safeguard account

    Register an account at app.safeguard.sh — or sign in if you already have one.

  2. 02

    In ChatGPT, create a Custom GPT

    Open ChatGPT → create a Custom GPT → Configure → Actions.

  3. 03

    Import the OpenAPI schema

    Import the OpenAPI schema from https://mcp.safeguard.sh/openapi.json.

  4. 04

    Set authentication

    Under Authentication, choose API Key with Auth Type Bearer, then paste a Safeguard MCP key (sg_sk_…) from Settings → Developer.

  5. ✓

    That’s it — you’re done

    Safeguard’s 70+ security tools are now available to ChatGPT. Start asking questions.

Prefer ChatGPT’s own MCP support? Open Plugins, select +, then Add custom MCP server with the URL https://mcp.safeguard.sh/mcp/openai and sign in with OAuth. Nothing to install, and no key to copy.

Auth is simple: you just need a Safeguard account. Create one at app.safeguard.sh if you don’t have one, then click Authorize access when ChatGPT sends you to Safeguard. A client that can only send a fixed header uses an MCP key instead: create one under Settings → Developer (key type MCP key) and send it as Authorization: Bearer sg_sk_…. If you don’t see it, ask your Safeguard administrator: API-key access to MCP is turned on per workspace.

Try these

Example prompts.

“List my security projects”
“Find critical vulnerabilities across my projects”
“Show me all SBOMs”
“Generate a remediation plan for my npm project”
“Which packages violate my license policy?”
Get started

Bring your supply chain into ChatGPT.

Add the Safeguard Security connector, sign in with OAuth, and start asking ChatGPT about your vulnerabilities, SBOMs, and compliance in seconds.

Self-healing security runs on Safeguard.

Your first fix PR is minutes away.

No sales call required, even your agent can complete the purchase over MCP.