MacTech CMMC / NIST 800-171

Calculate an SPRS score

calculate_sprs_score

Read-onlyIdempotent

Compute an exact SPRS score per the DoD Assessment Methodology: start at 110 and subtract each unimplemented requirement's Annex A weight (floor −203). Pass the control numbers that are NOT implemented; optionally pass 3.5.3 and/or 3.13.11 as partially implemented for their sliding-scale values (MFA for privileged/remote only = −3; encryption present but not FIPS-validated = −3). Also reports whether the score clears the 88-point conditional CMMC Level 2 certification threshold and flags a missing SSP (3.12.4), which blocks SPRS submission entirely.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`not_implemented`	Yes	Rev 2 control numbers not implemented, e.g. ["3.5.3", "3.11.2"]. An empty array means all 110 implemented (score 110). Rev 3 identifiers are rejected - there is no DoD scoring methodology for Rev 3.
`partially_implemented`	No	Sliding-scale controls at their partial value: 3.5.3 (MFA for privileged and remote users only) and/or 3.13.11 (encryption employed but not FIPS-validated). Deducts 3 instead of 5.

Output Schema

TableJSON Schema

Name	Required	Description
`scale`	Yes
`deductions`	Yes
`sprs_score`	Yes	The computed score, from 110 down to the -203 floor.
`missing_ssp`	No	Present when 3.12.4 is unimplemented, in which case no score can be submitted to SPRS at all.
`conditional_note`	No
`unknown_controls`	No	Inputs that matched no requirement - treat as caller error, not as implemented.
`total_points_deducted`	Yes
`meets_conditional_level_2_threshold`	Yes	Whether the score reaches 88. Clearing it is necessary but not sufficient - every open item must also be POA&M-eligible.

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedAug 9, 2026

changedInput schema / properties / not_implemented / description

Previous value: -"Rev 2 control numbers not implemented, e.g. [\"3.5.3\", \"3.11.2\"]. An empty array means all 110 implemented (score 110). Rev 3 identifiers are rejected — there is no DoD scoring methodology for Rev 3."New value: +"Rev 2 control numbers not implemented, e.g. [\"3.5.3\", \"3.11.2\"]. An empty array means all 110 implemented (score 110). Rev 3 identifiers are rejected - there is no DoD scoring methodology for Rev 3."

changedOutput schema / properties / meets_conditional_level_2_threshold / description

Previous value: -"Whether the score reaches 88. Clearing it is necessary but not sufficient — every open item must also be POA&M-eligible."New value: +"Whether the score reaches 88. Clearing it is necessary but not sufficient - every open item must also be POA&M-eligible."

changedOutput schema / properties / unknown_controls / description

Previous value: -"Inputs that matched no requirement — treat as caller error, not as implemented."New value: +"Inputs that matched no requirement - treat as caller error, not as implemented."

Changed2 schema fields changedAug 9, 2026

changedInput schema / properties / not_implemented / description

Previous value: -"Control numbers not implemented, e.g. [\"3.5.3\", \"3.11.2\"]. An empty array means all 110 implemented (score 110)."New value: +"Rev 2 control numbers not implemented, e.g. [\"3.5.3\", \"3.11.2\"]. An empty array means all 110 implemented (score 110). Rev 3 identifiers are rejected — there is no DoD scoring methodology for Rev 3."

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "additionalProperties": false,
+  "properties": {
+    "conditional_note": {
+      "type": "string"
+    },
+    "deductions": {
+      "items": {
+        "additionalProperties": false,
+        "properties": {
+          "id": {
+            "type": "string"
+          },
+          "points": {
+            "type": "number"
+          },
+          "requirement": {
+            "type": "string"
+          }
+        },
+        "required": [
+          "id",
+          "requirement",
+          "points"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "meets_conditional_level_2_threshold": {
+      "description": "Whether the score reaches 88. Clearing it is necessary but not sufficient — every open item must also be POA&M-eligible.",
+      "type": "boolean"
+    },
+    "missing_ssp": {
+      "description": "Present when 3.12.4 is unimplemented, in which case no score can be submitted to SPRS at all.",
+      "type": "string"
+    },
+    "scale": {
+      "type": "string"
+    },
+    "sprs_score": {
+      "description": "The computed score, from 110 down to the -203 floor.",
+      "type": "number"
+    },
+    "total_points_deducted": {
+      "type": "number"
+    },
+    "unknown_controls": {
+      "description": "Inputs that matched no requirement — treat as caller error, not as implemented.",
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    }
+  },
+  "required": [
+    "sprs_score",
+    "scale",
+    "total_points_deducted",
+    "meets_conditional_level_2_threshold",
+    "deductions"
+  ],
+  "type": "object"
+}

First observedAug 8, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations already declare readOnly, idempotent, and non-destructive, so the description is free to add behavioral detail. It does so richly: sliding-scale values, the 88-point threshold, SSP-blocking behavior, and the floor of −203. These are not inferable from the schema or annotations.

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 fairly long but packed with necessary operational detail. It front-loads the core purpose and then layers on edge cases. Some redundancy exists (e.g., repeating the 3.5.3/3.13.11 values in both description and schema), 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.

Completeness5/5

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

With an output schema present, the description doesn't need to define the return shape. It fully covers the scoring algorithm, valid inputs, exclusions (Rev 3), threshold logic, and a blocking condition (SSP missing). No critical information is missing for correct invocation.

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

Parameters4/5

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

Schema coverage is 100%, so baseline is 3. The description adds value by explaining the meaning of an empty array ('all 110 implemented') and clarifies that partial controls deduct 3 instead of 5, which is not obvious from the schema alone.

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 opens with a specific verb+resource: 'Compute an exact SPRS score per the DoD Assessment Methodology'. It immediately distinguishes the tool from siblings like determine_cmmc_level and crosswalk_control by focusing on the SPRS scoring algorithm with exact starting point and floor.

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 explicit input guidance: 'Pass the control numbers that are NOT implemented' and notes optional partial implementation of specific controls. It also flags that Rev 3 identifiers are rejected. It doesn't name alternative tools, but the context makes the use case unambiguous.

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

All MacTech CMMC / NIST 800-171 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?