Skip to main content
Glama

pentest-mcp-server

by io.github.cyanheads

Pentest Map Techniques

pentest_map_techniques
Read-onlyIdempotent

Rank ATT&CK techniques and OWASP test cases against an authorized target profile of technology stack, exposed services, authentication type, and operating system. Results include profile-specific relevance, detection opportunities, mitigations, and associated methodology vectors.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
osNoTarget operating system. Narrows to OS-specific techniques.
limitNoMaximum number of techniques to return (1–50, default 15). Higher values give broader coverage; lower values focus on highest-relevance items.
stackNoTechnology stack components (e.g., ["Node.js", "Express", "PostgreSQL", "Redis"]). Each element matched against technique platform and procedure examples.
servicesNoExposed services and interfaces (e.g., ["REST API", "GraphQL", "file upload", "admin panel"]). Narrows technique relevance.
auth_typeNoAuthentication mechanism in use. Surfaces auth-specific attack techniques.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
capNoThe limit applied to ranked_techniques.
errorNoPresent when the call failed. Absent on success.
shownNoNumber of ranked techniques returned.
truncatedNoTrue when ranked_techniques was capped by limit.
attack_versionNoATT&CK dataset version used for technique data.
profile_summaryNoOne-sentence normalized summary of the supplied target profile.
owasp_test_casesNoRelevant OWASP Testing Guide test cases for the profile (up to 10).
ranked_techniquesNoTechniques ordered by relevance_score descending.
authorized_use_reminderNoReminder that technique mapping is for authorized testing engagements only. Rendered first.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed13 schema fields changed
    • changedInput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
    • addedInput schema / additionalProperties
      Added value: +false
    • changedOutput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
    • addedOutput schema / anyOf
      Added value: +[
+  {
+    "not": {
+      "required": [
+        "error"
+      ]
+    },
+    "required": [
+      "authorized_use_reminder",
+      "ranked_techniques",
+      "owasp_test_cases",
+      "profile_summary",
+      "attack_version",
+      "truncated",
+      "shown",
+      "cap"
+    ]
+  },
+  {
+    "required": [
+      "error"
+    ]
+  }
+]
    • addedOutput schema / properties / cap
      Added value: +{
+  "description": "The limit applied to ranked_techniques.",
+  "type": "number"
+}
    • addedOutput schema / properties / error
      Added value: +{
+  "additionalProperties": {},
+  "description": "Present when the call failed. Absent on success.",
+  "properties": {
+    "code": {
+      "description": "JSON-RPC error code for this failure.",
+      "maximum": 9007199254740991,
+      "minimum": -9007199254740991,
+      "type": "integer"
+    },
+    "data": {
+      "additionalProperties": {},
+      "properties": {
+        "reason": {
+          "description": "Machine-readable failure mode. Declared by this tool: `no_profile`: No profile fields were provided. Other values are possible when a failure originates below the handler.",
+          "examples": [
+            "no_profile"
+          ],
+          "type": "string"
+        },
+        "recovery": {
+          "additionalProperties": {},
+          "description": "Actionable next step for the caller.",
+          "properties": {
+            "hint": {
+              "type": "string"
+            }
+          },
+          "required": [
+            "hint"
+          ],
+          "type": "object"
+        },
+        "retryable": {
+          "description": "Whether retrying may succeed.",
+          "type": "boolean"
+        }
+      },
+      "type": "object"
+    },
+    "message": {
+      "description": "Human-readable description of what went wrong.",
+      "type": "string"
+    }
+  },
+  "required": [
+    "code",
+    "message"
+  ],
+  "type": "object"
+}
    • changedOutput schema / properties / profile_summary / description
      Previous value: -"One-sentence summary of the target profile as interpreted by the ranking algorithm."New value: +"One-sentence normalized summary of the supplied target profile."
    • changedOutput schema / properties / ranked_techniques / items / properties / detection_opportunity / description
      Previous value: -"Primary detection opportunity for defenders (truncated to 200 chars)."New value: +"Primary observable detection opportunity (truncated to 200 characters)."
    • changedOutput schema / properties / ranked_techniques / items / properties / pentest_guide_vector / description
      Previous value: -"Pentest_guide vector name for follow-up methodology. Absent when no direct mapping exists."New value: +"Associated pentest_guide methodology vector. Absent when no direct mapping exists."
    • changedOutput schema / properties / ranked_techniques / items / properties / relevance_score / description
      Previous value: -"Relevance score based on profile match factors: 1 point per matching platform, 2 per matching service, 2 for auth type match. Higher = more applicable to this profile."New value: +"Relative relevance to the supplied target profile; higher scores indicate stronger matches."
    • addedOutput schema / properties / shown
      Added value: +{
+  "description": "Number of ranked techniques returned.",
+  "type": "number"
+}
    • addedOutput schema / properties / truncated
      Added value: +{
+  "description": "True when ranked_techniques was capped by limit.",
+  "type": "boolean"
+}
    • removedOutput schema / required
      Removed value: -[
-  "authorized_use_reminder",
-  "ranked_techniques",
-  "owasp_test_cases",
-  "profile_summary",
-  "attack_version"
-]
  2. First observed

TDQS

A3.9/5.0
Behavior3/5

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

Annotations already declare this as a read-only, idempotent operation, so the description does not need to repeat safety traits. It adds useful behavioral context by explaining the output includes relevance, detection opportunities, mitigations, and methodology vectors, though some of this is redundant with the existing output schema. It does not clarify whether this is a local knowledge-base ranking rather than a live scan, but the 'authorized target profile' framing partially signals a planning-oriented operation.

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 two sentences with no filler, front-loading the verb, resource, and target context. The phrase 'associated methodology vectors' is somewhat vague and imprecise, which keeps it from being perfectly concise, but overall every sentence earns its place.

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?

Given the output schema exists and input schema fully documents parameters, the description covers the essential invocation context well. It does not mention behavior when no profile parameters are provided, but because all parameters are optional and the schema documents defaults, this is a minor omission rather than a critical gap.

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 the schema already documents every parameter including defaults and enum constraints. The description restates four of the five profile dimensions (stack, services, auth_type, os) but adds no new semantic detail beyond what the schema provides, matching the baseline for high schema coverage.

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 ('Rank') and a precise resource ('ATT&CK techniques and OWASP test cases'), then scopes it to a target profile composed of concrete dimensions. This clearly separates it from siblings like pentest_lookup_technique and pentest_generate_payloads by indicating a multi-technique prioritization operation rather than a single lookup or payload construction.

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?

It provides clear situational context: use when you need profile-specific ranking of attack techniques and test cases against a target's stack, services, auth type, and OS. It does not explicitly name alternatives or state when not to use it, but the described use case is unambiguous enough for an agent to select it correctly.

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

All pentest-mcp-server toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.1/5.0
Disambiguation5/5

Each tool has a clearly distinct purpose: response analysis, payload encoding, payload generation, methodology guidance, ATT&CK group lookup, ATT&CK technique lookup, and technique mapping. There is no meaningful overlap or ambiguity between tool boundaries.

Naming Consistency4/5

All tools share the pentest_ prefix and most follow a verb_noun pattern such as analyze_response, generate_payloads, and lookup_technique. However, pentest_encode and pentest_guide are verb-only, creating a minor inconsistency in the naming convention.

Tool Count5/5

Seven tools is a well-scoped size for a pentest assistance server. Each tool covers a distinct capability without unnecessary duplication or bloat.

Completeness4/5

The tool set covers the main pentest workflow areas: response analysis, payload generation/encoding, methodology guidance, and ATT&CK reference/mapping. Minor gaps exist, such as no explicit reporting or active scanning tool, but the surface is coherent and usable for its apparent purpose.

Resources