TraceGuardDocs

MCP server

Connect Claude or an IDE to your supply-chain data over MCP.

TraceGuard ships a Model Context Protocol server, so an AI assistant (Claude, an IDE) can read and act on your supply-chain data — bounded by the same scopes and row-level security as everything else. A token can never see or change anything its owner couldn't.

Connect

The server speaks Streamable HTTP at https://mcp.traceguard.io. In the app this lives under Integrations → AI Agents — pick your client below to get the server URL and a ready-to-paste config (the same flow as the product):

Connect your agent
Pick your client, then sign in — no token to create or manage.
Server URL
https://mcp.traceguard.io
  1. 1. In Claude: Settings → Connectors → Add custom connector.
  2. 2. Paste the Server URL above.
  3. 3. Sign in to TraceGuard and approve — pick read-only vs read & write and which orgs/projects.

Works on claude.ai and Claude Desktop.

On first connect you sign in to TraceGuard and choose scope — read-only vs read & write, and which orgs/projects. See OAuth for the flow, or expand Use an API token above for headless/CI setups (tgm_…).

First call

Run whoami first — it reports the token's identity, granted scopes, and any org/project restrictions, so you know exactly what this connection can do.

Tool catalog

Read tools are available whenever the matching read scope is present; write tools (create_vex, record_finding_decision, trigger_scan) only appear when the token holds the corresponding write scope.

GroupTools
Navigationwhoami, list_organizations, list_projects
Inventorylist_sboms, get_sbom, list_components, list_dependencies
Vulnerabilitieslist_vulnerabilities
Findings & triagelist_findings, list_finding_decisions, list_vex, list_exclusions
Dashboard & searchorg_dashboard_stats, kev_epss, search
Write (scope-gated)create_vex, record_finding_decision, trigger_scan

Getting oriented

Data is hierarchical: organizations contain projects. Most tools take an organization_id (from list_organizations); many also accept a project_id (from list_projects). Use the list_*, search, and dashboard tools to find ids before calling a write tool — and confirm specifics with the user first.

Always confirm before invoking a write tool. create_vex, record_finding_decision, and trigger_scan change your data.