Skip to main content
Glama

website-search

by com.zeltser
OverviewDiscussionsAdmin

aidefense_cross_map

Read-onlyIdempotent

Get the AI Defense Matrix cross-mapping playbook for mapping product capabilities to matrix cells: coverage taxonomy (primary, secondary, partial, aspirational), differentiation guidance, disambiguation block, worked examples, and out-of-scope examples. The response always includes an inScopeCheck. Products that USE AI to solve a non-AI security problem (deepfake detection, AI-for-fraud, AI features added to existing SIEM, SOAR, or EDR tools) belong in the Cyber Defense Matrix at https://cyberdefensematrix.com. Pairs naturally with product_load_context(productFocus: 'ai_security') for follow-on positioning and GTM work. This server never requests your program docs or product roadmap and instructs your AI to keep them local—the matrix, framework alignments, and playbooks flow to your AI for local analysis.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
frameworkNoOptional: include only one external framework's cross-mapping (e.g., 'owasp-llm-top10') alongside the playbook.
whitespaceNoOptional: when true, surface a `whitespace.sparseCells` block scoped to cells with at most one product in the AI Defense Matrix Catalog where a product can plausibly succeed (vendorDensity <= 1 AND coverageType in {tooling, hybrid}). Process and cdm-rollup cells are excluded by default because their emptiness does not indicate market opportunity. The block names the count source and catalog date, and returns no cells when counts are missing.
include_process_shapedNoOptional: when true with whitespace, lift the coverageType filter so process and cdm-rollup cells with at most one cataloged product appear too. Use when you want to see all sparse cells regardless of whether a product is the right answer there.
include_framework_alignmentNoOptional: when false, the framework alignment block (~half the response) is omitted in favor of a short note pointing to aidefense_get_framework_alignment. Use when the caller will fetch alignment separately and wants a slim cross_map response. Default: true.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / include_process_shaped / description
      Previous value: -"Optional: when true with whitespace, include process-shaped sparse cells in the result. Use when you want to see all empty cells regardless of whether a product is the right answer there."New value: +"Optional: when true with whitespace, lift the coverageType filter so process and cdm-rollup cells with at most one cataloged product appear too. Use when you want to see all sparse cells regardless of whether a product is the right answer there."
    • changedInput schema / properties / whitespace / description
      Previous value: -"Optional: when true, surface a `whitespace.sparseCells` block scoped to vendor-empty cells where a product can plausibly succeed (vendorDensity <= 1 AND coverageType in {tooling, hybrid}). Process-shaped sparse cells are excluded by default because their emptiness does not indicate market opportunity."New value: +"Optional: when true, surface a `whitespace.sparseCells` block scoped to cells with at most one product in the AI Defense Matrix Catalog where a product can plausibly succeed (vendorDensity <= 1 AND coverageType in {tooling, hybrid}). Process and cdm-rollup cells are excluded by default because their emptiness does not indicate market opportunity. The block names the count source and catalog date, and returns no cells when counts are missing."
  2. Changed1 schema field changed
    • changedInput schema / properties / framework / enum
      Previous value: -[
-  "nist-ir-8596",
-  "csa-aicm",
-  "iso-42001",
-  "google-saif",
-  "mitre-atlas",
-  "owasp-ai-exchange",
-  "owasp-llm-top10",
-  "owasp-asi"
-]New value: +[
+  "nist-ir-8596",
+  "csa-aicm",
+  "iso-42001",
+  "google-saif",
+  "sans-caisg",
+  "mitre-atlas",
+  "owasp-ai-exchange",
+  "owasp-llm-top10",
+  "owasp-asi"
+]
  3. Changed1 schema field changed
    • addedInput schema / properties / include_framework_alignment
      Added value: +{
+  "description": "Optional: when false, the framework alignment block (~half the response) is omitted in favor of a short note pointing to aidefense_get_framework_alignment. Use when the caller will fetch alignment separately and wants a slim cross_map response. Default: true.",
+  "type": "boolean"
+}
  4. Changed2 schema fields changed
    • addedInput schema / properties / include_process_shaped
      Added value: +{
+  "description": "Optional: when true with whitespace, include process-shaped sparse cells in the result. Use when you want to see all empty cells regardless of whether a product is the right answer there.",
+  "type": "boolean"
+}
    • addedInput schema / properties / whitespace
      Added value: +{
+  "description": "Optional: when true, surface a `whitespace.sparseCells` block scoped to vendor-empty cells where a product can plausibly succeed (vendorDensity <= 1 AND coverageType in {tooling, hybrid}). Process-shaped sparse cells are excluded by default because their emptiness does not indicate market opportunity.",
+  "type": "boolean"
+}
  5. Added

TDQS

A4.1/5.0
Behavior4/5

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

With annotations already marking readOnly, idempotent, and non-destructive behavior, the description adds meaningful traits: 'The response always includes an inScopeCheck' and 'This server never requests your program docs or product roadmap... keep them local.' These details go beyond what annotations convey and set correct expectations for the AI's handling of sensitive data.

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 four sentences and every sentence carries distinct value: content outline, guaranteed return field, scope boundary, and privacy behavior. It is slightly dense but well structured, with the core purpose front-loaded before secondary guidance.

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 read-only playbook retrieval tool with no output schema, the description adequately covers what is returned (playbook components, inScopeCheck), who should not use it (AI-for-non-AI-security products), and how to pair it with other tools. The detailed parameter documentation fills the remaining gaps.

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% for all 4 parameters, including detailed explanations for whitespace, include_process_shaped, and include_framework_alignment. The tool description itself adds no parameter-specific semantics beyond that, which is acceptable given the schema's thoroughness. Baseline 3 applies.

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 names a specific verb and resource ('Get the AI Defense Matrix cross-mapping playbook for mapping product capabilities to matrix cells') and enumerates the playbook's components (coverage taxonomy, differentiation guidance, disambiguation block, worked examples, out-of-scope examples). It clearly distinguishes itself from siblings like aidefense_get_matrix by focusing on cross-mapping rather than the matrix itself.

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?

The description gives an explicit out-of-scope rule ('Products that USE AI to solve a non-AI security problem... belong in the Cyber Defense Matrix') and suggests a companion workflow ('Pairs naturally with product_load_context(productFocus: 'ai_security')'). It doesn't directly name alternatives for all cases, but the parameter hint to fetch alignment separately further guides routing.

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

All website-search toolsInspect
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