Agnes

Get the SBOM

get_sbom

Read-only

The software bill of materials of a project's latest successful analysis (or the given run) as CycloneDX 1.6 JSON: every installed package with its purl, licence where known and dependencies, and the known vulnerabilities that affect them. Large for big projects; save it to a file rather than reading it all.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "project": "<project>"
    },
    "name": "get_sbom"
  }
}

Input Schema

Name	Required	Description	Default
`runId`	No	A specific run's id; leave out for the latest successful analysis
`project`	Yes	The project: its id from list_projects, or "owner/repo", or "owner/repo@branch" when the repository has several branches as projects

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 12, 2026

TDQS

A4/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the description is free to add what they cannot: the serialization format, that the payload can be very large for big projects, and the recommended handling (write to file). It doesn't mention error behaviour for projects with no successful analysis, which is the main residual gap.

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

Conciseness5/5

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

Two dense sentences that front-load the resource and format, then the contents, then the size caveat. Nothing is redundant and no sentence could be dropped without losing information.

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

Completeness4/5

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

With no output schema, the description carries the burden of describing the return value, and it does so well by naming the format and the fields present. Only minor gaps remain, such as whether dev/test dependencies are included or what happens when no successful analysis exists.

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

Parameters3/5

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

Schema description coverage is 100% and both parameters already document their formats, including the uuid pattern for runId and the id/owner-repo/owner-repo@branch forms for project. The description only restates the runId default ('or the given run'), adding no syntax or edge-case detail beyond the schema, so the baseline 3 applies.

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

Purpose4/5

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

States a specific resource (the project's SBOM), a precise output format (CycloneDX 1.6 JSON), and exactly what it contains: packages with purls, licences, dependencies and known vulnerabilities. Scope (latest successful analysis vs a given run) is explicit. It never names a sibling, so an agent must infer why it should pick this over get_findings for vulnerability data.

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

Usage Guidelines4/5

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

Gives concrete operational guidance: default to the latest successful analysis, pass runId for a specific run, and save the payload to a file rather than reading it when projects are large. It stops short of routing guidance — nothing says when to use get_findings or get_report instead.

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

All Agnes tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?