Skip to main content
Glama

supply_chain_scan

Read-only

Scan a whole repo archive (a ZIP of manifests, lockfiles and MCP server configs) for packages, MCP servers and extensions listed in a known-compromise catalog (Bumblebee threat intel). Use this for a repo, many lockfiles or MCP configs; use dependency_check instead to lint a few pasted manifests for pinning and hygiene. Send exactly one of archive_base64 or archive_url; neither or both is 400 exactly_one_of_archive_base64_or_archive_url. Read-only: the ZIP is sent to QuassLabs (archive_url is fetched server-side), unpacked to a temp dir deleted after the call, never executed or installed. 5 credits. Failed calls are not billed: input, fetch and archive errors (invalid_ecosystems, not_a_zip, unsafe_path_in_archive, too_many_entries, archive_expands_too_large) are rejected before any charge, and 5xx is refunded. Bearer key required. Returns verdict CLEAR or FINDINGS, findings with severity, source_file and remediation, and scanned counts; CLEAR is not a guarantee of safety.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "supply_chain_scan"
  }
}

Input Schema

NameRequiredDescriptionDefault
ecosystemsNoLimit the scan to these ecosystems. Omitted, null or empty: all of them. Anything other than a list of the values above is 400 invalid_ecosystems, rejected before any charge.
archive_urlNohttps:// URL to the same kind of ZIP, readable with no credentials (typically presigned), for archives too big to inline. Max 25 MiB download, 200 MiB extracted. The host must resolve only to public addresses on HTTPS port 443, and every redirect (up to 3) is re-validated the same way, otherwise 400 archive_url_blocked. The download shares the 29 s request budget with the scan, so it must finish within a few seconds, otherwise 400 archive_url_too_slow; a presigned S3 URL in a nearby region is ideal. Send exactly one of archive_url or archive_base64.
archive_base64NoBase64 ZIP of the repo, or of its manifests, lockfiles and MCP configs. Max 10 MiB decoded (about 7.5 MiB of ZIP in practice under the 10 MB request limit), 10,000 entries, 200 MiB extracted. Send exactly one of archive_base64 or archive_url.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • changedInput schema / properties / archive_base64 / description
      Previous value: -"Base64-encoded ZIP of manifests/lockfiles/MCP configs."New value: +"Base64 ZIP of the repo, or of its manifests, lockfiles and MCP configs. Max 10 MiB decoded (about 7.5 MiB of ZIP in practice under the 10 MB request limit), 10,000 entries, 200 MiB extracted. Send exactly one of archive_base64 or archive_url."
    • changedInput schema / properties / archive_url / description
      Previous value: -"Presigned HTTPS URL to a ZIP (for large archives)."New value: +"https:// URL to the same kind of ZIP, readable with no credentials (typically presigned), for archives too big to inline. Max 25 MiB download, 200 MiB extracted. The host must resolve only to public addresses on HTTPS port 443, and every redirect (up to 3) is re-validated the same way, otherwise 400 archive_url_blocked. The download shares the 29 s request budget with the scan, so it must finish within a few seconds, otherwise 400 archive_url_too_slow; a presigned S3 URL in a nearby region is ideal. Send exactly one of archive_url or archive_base64."
    • changedInput schema / properties / ecosystems / description
      Previous value: -"Optional ecosystem filter."New value: +"Limit the scan to these ecosystems. Omitted, null or empty: all of them. Anything other than a list of the values above is 400 invalid_ecosystems, rejected before any charge."
    • addedInput schema / properties / ecosystems / items / enum
      Added value: +[
      +  "npm",
      +  "pypi",
      +  "go",
      +  "rubygems",
      +  "packagist",
      +  "mcp",
      +  "editor-extension",
      +  "browser-extension"
      +]
  2. First observed

TDQS

A4.8/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=true, but the description adds substantial non-obvious context: the ZIP is transmitted to a third party (QuassLabs), archive_url is fetched server-side, contents go to a temp dir deleted after the call, and nothing is executed or installed. It also discloses cost (5 credits), the billing/refund policy for input, fetch and 5xx failures, and Bearer-key auth — none of which the annotations convey.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with purpose and the sibling contrast before operational details, and most sentences earn their place. It is long and the enumerated error codes (invalid_ecosystems, not_a_zip, unsafe_path_in_archive, etc.) partially restate what the schema's parameter descriptions already say, which is mild redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, and the description compensates by describing the return contract: verdict CLEAR or FINDINGS, findings carrying severity, source_file and remediation, plus scanned counts, and the caveat that CLEAR is not a guarantee of safety. Combined with the disclosed limits, cost, auth and failure modes, an agent has everything needed to invoke and interpret this tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds a genuine cross-parameter constraint the schema does not encode (required is empty and there is no oneOf): exactly one of archive_base64 or archive_url, with 400 exactly_one_of_archive_base64_or_archive_url otherwise. That mutual exclusivity is the main value-add; size and ecosystem semantics are largely already in the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource ('Scan a whole repo archive ... for packages, MCP servers and extensions') and names the intel source (Bumblebee threat intel). It explicitly contrasts with the sibling dependency_check, so an agent can route correctly without opening either schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It states the positive selection criteria ('a repo, many lockfiles or MCP configs') and the negative case with the named alternative ('use dependency_check instead to lint a few pasted manifests for pinning and hygiene'). It also gives the parameter-selection rule ('Send exactly one of archive_base64 or archive_url') and the exact error code for violating it.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.