supply_chain
Supply chain: SBOM generation, cosign artifact signing, SLSA provenance verification
This record as markdown: /tools/defense/supply-chain.md
What supply_chain does on Defense
AI agents use supply_chain to create or update resources in Defense, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Defense environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
path | string | — | Directory to scan |
action | string | Yes | Supply chain security action |
dryRun | boolean | — | Preview only |
format | string | — | SBOM output format |
source | string | — | Expected source repository URI |
keyPath | string | — | Path to private key, omit for keyless |
artifact | string | — | Image reference or file path to sign/verify |
Parameters from the server's own tool schema.
Why supply_chain is rated Medium
The primary actions—generating SBOMs, signing artifacts, and recording provenance—all create or modify metadata and cryptographic attestations. While these operations support security, they are Write-category because they create/modify data structures reversibly.
From the tool's definition Tool performs 'SBOM generation' (creates software bill of materials), 'cosign artifact signing' (adds/modifies cryptographic signatures), and 'SLSA provenance verification' (creates or updates provenance records).
Risk signalsAccepts file system path (path)
Attacks that exploit this kind of access
The rule that runs supply_chain safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Defense, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For supply_chain, this is the rule to start with:
supply_chain stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Defense, apply this rule, and every supply_chain call is checked against it from then on.
Questions about supply_chain
Supply chain: SBOM generation, cosign artifact signing, SLSA provenance verification. It is categorised as a Write tool in the Defense MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
supply_chain accepts 7 parameters: path, action, dryRun, format, source, keyPath, artifact. Required: action. The full parameter table on this page comes from the server's own tool schema.
Register the Defense MCP server in PolicyLayer and add a rule for supply_chain: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Defense. Nothing to install.
supply_chain is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the supply_chain rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for supply_chain. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
supply_chain is provided by the Defense MCP server (defense-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Defense, and thousands of servers like it.
This server
Across the catalogue