Skip to main content
Glama

pentest-mcp-server

by io.github.cyanheads
OverviewDiscussionsAdmin

Pentest Generate Payloads

pentest_generate_payloads
Read-onlyIdempotent

Generate context-specific payload templates for authorized systems. Each template includes its vulnerability category, context rationale, WAF/IDS detection signature, mitigation, optional WAF research note, and optional encoded variant.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
countNoNumber of payload variants to return (1–20, default 5). More variants cover different bypass approaches for the same context.
categoryYesVulnerability category for payload generation.
encodingNoOptional encoding chain applied left to right to each returned template.
waf_profileNoWAF or filter in front of the authorized test target. When a specific WAF is named, bypass variants referencing known public research are included.none
injection_contextYesPrecise injection context. Critical for XSS: an HTML attribute payload differs from a JS string payload. Provide the most specific context for the best results.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
errorNoPresent when the call failed. Absent on success.
categoryNoRequested payload category.
payloadsNoPayload templates ordered by coverage breadth, each annotated with offense and defense context.
injection_contextNoRequested injection context.
authorized_use_reminderNoReminder that these templates are for authorized testing only.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed9 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
    • changedInput schema / properties / encoding / description
      Previous value: -"Apply an encoding chain to payloads at generation time. Applied in order (left to right). Use pentest_encode for more control over per-payload encoding."New value: +"Optional encoding chain applied left to right to each returned template."
    • 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": [
+      "category",
+      "injection_context",
+      "authorized_use_reminder",
+      "payloads"
+    ]
+  },
+  {
+    "required": [
+      "error"
+    ]
+  }
+]
    • 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.",
+          "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 / payloads / items / properties / detection_signature / description
      Previous value: -"Signature a WAF or IDS might match (e.g., specific keywords, patterns). Useful for blue team rule-writing."New value: +"Signature a WAF or IDS might match, such as keywords or patterns."
    • changedOutput schema / properties / payloads / items / properties / mitigation / description
      Previous value: -"How the target application should validate or encode input to prevent this class of payload."New value: +"Input validation or encoding control that prevents this payload class."
    • removedOutput schema / required
      Removed value: -[
-  "category",
-  "injection_context",
-  "authorized_use_reminder",
-  "payloads"
-]
  2. Changed1 schema field changed
    • changedInput schema / properties / waf_profile / enum
      Previous value: -[
-  "cloudflare",
-  "aws_waf",
-  "modsecurity_crs",
-  "imperva",
-  "akamai",
-  "none",
-  "unknown"
-]New value: +[
+  "cloudflare",
+  "aws_waf",
+  "modsecurity_crs",
+  "imperva",
+  "akamai",
+  "f5_bigip_asm",
+  "nginx_modsecurity",
+  "fortinet_fortiwaf",
+  "none",
+  "unknown"
+]
  3. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and idempotentHint=true, covering safety and deterministic output. The description adds valuable detail about what each template includes (category, rationale, detection signature, mitigation, optional research note and encoded variant), which is beyond annotations and helps agents understand output structure.

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?

The description is a single, efficient sentence that front-loads the primary action and scope, then briefly enumerates output contents. Every clause earns its place with no redundancy or filler.

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 tool's complexity (5 parameters, enums, output schema present), the description provides enough context about the returned templates and ties to the 'context rationale' element. It does not explicitly mention parameters like count or encoding, but those are fully documented in the schema, and the output schema is present, so nothing critical is missing.

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%, so the description does not need to elaborate on parameters. It adds no parameter-specific details beyond the schema, and the baseline of 3 is appropriate when schema carries the full load.

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 clearly states the tool's verb ('Generate') and resource ('context-specific payload templates'), with a scope qualifier ('for authorized systems'). It is easily distinguished from siblings like pentest_analyze_response (analysis) or pentest_encode (encoding), so an agent knows exactly what this tool does without opening the schema.

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 implicitly frames usage as part of an authorized pentest workflow, but does not explicitly state when to prefer this tool over alternatives such as pentest_guide or pentest_map_techniques. The context is clear, yet exclusions or alternative routing are left to inference.

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
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