Skip to main content
Glama

Exposure Paths

exposure_paths
Read-onlyIdempotent

Returns ranked attack paths with KEV, severity, risk, and credential exposure, explaining why each path ranks where it does.

Instructions

Return the attack-path queue in the dashboard's order, with why each path ranks where it does.

    Ranking is ``ranking.order`` (evidence tier, KEV, severity, evidence confidence,
    composite risk, credential count); every path carries ``rank``, ``evidenceTier``,
    ``isKev``, ``severity``, ``evidenceConfidence`` and ``rankingFactors``. Totals,
    filters and cursor pages match ``/v1/graph/attack-paths``. With ``result_id`` the
    paths are that session scan result's, unfiltered and labelled ``session_scan_result``.
    

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": "exposure_paths"
  }
}

Input Schema

NameRequiredDescriptionDefault
kevNoOnly paths through a known-exploited finding (true) or none (false).
viewNosummary (default): rank, risk, KEV, evidence tier, endpoints, finding/credential ids. full adds hops, relationships, nodes and edges.summary
limitNoMaximum ranked exposure paths to return.
cursorNopagination.next_cursor; keep the filters unchanged.
node_idNoAny graph node the path passes through.
scan_idNoOptional historical scan ID. Omit for the current tenant estate.
min_riskNoMinimum composite path risk (0-100).
result_idNoresult_id from a scan response in this session. Answers from that scan result instead of the persisted estate graph; omitted, the caller's newest scan result is consulted first.
target_idNoOnly paths ending at this graph node id.
tenant_idNoTenant scope. Defaults to 'default'.default
finding_idNoCVE, advisory or finding node id on the path.
source_typeNoEntrypoint entity type, e.g. 'agent'.
min_severityNoWorst on-path finding at least this severe.
credential_idNoCredential name or node id exposed on the path.
has_credentialNoOnly paths that do (true) or do not (false) expose a credential.

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.0.15
    • addedInput schema / properties / result_id
      Added value: +{
      +  "anyOf": [
      +    {
      +      "maxLength": 128,
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "result_id from a scan response in this session. Answers from that scan result instead of the persisted estate graph; omitted, the caller's newest scan result is consulted first.",
      +  "title": "Result Id"
      +}
  2. Changed13 schema fields changedv1.0.12
    • addedInput schema / properties / credential_id
      Added value: +{
      +  "anyOf": [
      +    {
      +      "maxLength": 512,
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "Credential name or node id exposed on the path.",
      +  "title": "Credential Id"
      +}
    • changedInput schema / properties / cursor / description
      Previous value: -"Continue with pagination.next_cursor; keep the risk filter unchanged."New value: +"pagination.next_cursor; keep the filters unchanged."
    • addedInput schema / properties / finding_id
      Added value: +{
      +  "anyOf": [
      +    {
      +      "maxLength": 512,
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "CVE, advisory or finding node id on the path.",
      +  "title": "Finding Id"
      +}
    • addedInput schema / properties / has_credential
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "boolean"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "Only paths that do (true) or do not (false) expose a credential.",
      +  "title": "Has Credential"
      +}
    • addedInput schema / properties / kev
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "boolean"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "Only paths through a known-exploited finding (true) or none (false).",
      +  "title": "Kev"
      +}
    • changedInput schema / properties / limit / description
      Previous value: -"Maximum number of ranked exposure paths to return."New value: +"Maximum ranked exposure paths to return."
    • changedInput schema / properties / min_risk / description
      Previous value: -"Minimum path risk score to include."New value: +"Minimum composite path risk (0-100)."
    • addedInput schema / properties / min_severity
      Added value: +{
      +  "anyOf": [
      +    {
      +      "enum": [
      +        "critical",
      +        "high",
      +        "medium",
      +        "low"
      +      ],
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "Worst on-path finding at least this severe.",
      +  "title": "Min Severity"
      +}
    • addedInput schema / properties / node_id
      Added value: +{
      +  "anyOf": [
      +    {
      +      "maxLength": 512,
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "Any graph node the path passes through.",
      +  "title": "Node Id"
      +}
    • addedInput schema / properties / source_type
      Added value: +{
      +  "anyOf": [
      +    {
      +      "maxLength": 64,
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "Entrypoint entity type, e.g. 'agent'.",
      +  "title": "Source Type"
      +}
    • addedInput schema / properties / target_id
      Added value: +{
      +  "anyOf": [
      +    {
      +      "maxLength": 512,
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "Only paths ending at this graph node id.",
      +  "title": "Target Id"
      +}
    • changedInput schema / properties / tenant_id / description
      Previous value: -"Tenant ID for the graph snapshot. Defaults to 'default'."New value: +"Tenant scope. Defaults to 'default'."
    • addedInput schema / properties / view
      Added value: +{
      +  "default": "summary",
      +  "description": "summary (default): rank, risk, KEV, evidence tier, endpoints, finding/credential ids. full adds hops, relationships, nodes and edges.",
      +  "enum": [
      +    "summary",
      +    "full"
      +  ],
      +  "title": "View",
      +  "type": "string"
      +}
  3. Changed1 schema field changedv1.0.11
    • changedInput schema / properties / scan_id / description
      Previous value: -"Optional graph scan ID. Omit to use the latest snapshot."New value: +"Optional historical scan ID. Omit for the current tenant estate."
  4. Changed1 schema field changed
    • addedInput schema / properties / cursor
      Added value: +{
      +  "anyOf": [
      +    {
      +      "maxLength": 4096,
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "Continue with pagination.next_cursor; keep the risk filter unchanged.",
      +  "title": "Cursor"
      +}
  5. Addedv0.88.4
  6. Removedv0.88.1
  7. Addedv0.87.1

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, open world), so the description correctly spends its budget elsewhere: it discloses that cursor pages must keep filters unchanged and, importantly, that result_id answers are unfiltered and labelled 'session_scan_result' – a genuine gotcha the schema alone does not convey. It does not mention pagination limits beyond the schema or any rate/latency behavior, so not a 5.

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?

Front-loaded with the core behavior, then ranking order, then the result_id exception. Dense but every clause carries information; the backticked field-name list is slightly noisy but ties the prose to actual response keys.

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?

For a 15-parameter, fully documented read tool with an output schema, the description covers purpose, ordering, pagination, and the one mode switch that changes filtering semantics. Return shapes needn't be explained since an output schema exists. Missing only sibling routing guidance.

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% across all 15 parameters, so the baseline is 3 and the schema already carries per-filter meaning. The description adds only marginal semantics beyond it – chiefly that result_id bypasses the filters entirely, which the schema's wording does not make explicit.

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 verb+resource ('Return the attack-path queue') plus the non-obvious ordering guarantee (dashboard order, ranking.order composition). An agent knows exactly what it gets back. It does not explicitly distinguish itself from siblings like scan or intel_lookup, which is the only thing keeping it off a 5.

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

Usage Guidelines3/5

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

Usage is implied rather than stated: the description explains what the queue is and the result_id override, but never says when to prefer this tool over scan/intel_lookup/remediate, nor when not to call it. The result_id note is the closest thing to a usage rule (use it for a session's in-flight scan result instead of the persisted estate graph).

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