Skip to main content
Glama
Sign In
MCP Server for OSCAL

MCP Server for OSCAL

by dfkunstler
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

text_search_oscal

Search loaded OSCAL documents and control prose by relevance to find specific compliance text. Retrieve child elements using entity IDs and parent document UUIDs.

Instructions

Search loaded OSCAL documents and child elements, including control prose, ranked by relevance. Pass a child hit's entity ID and parentDocumentUuid to get_child_element.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query_text": "<query_text>"
    },
    "name": "text_search_oscal"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMaximum items per page, 1-100. A page may hold fewer to fit the response budget.
offsetNoZero-based index of the first item.
query_textYesFull-text search terms.
oscal_model_typeNoOSCAL model name from list_oscal_models, e.g. "catalog". Omit for all models.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changedv0.7.1
    • addedInput schema / properties / limit / description
      Added value: +"Maximum items per page, 1-100. A page may hold fewer to fit the response budget."
    • addedInput schema / properties / offset / description
      Added value: +"Zero-based index of the first item."
    • addedInput schema / properties / oscal_model_type / description
      Added value: +"OSCAL model name from list_oscal_models, e.g. \"catalog\". Omit for all models."
    • removedInput schema / properties / query_text / default
      Removed value: -""
    • addedInput schema / properties / query_text / description
      Added value: +"Full-text search terms."
    • addedInput schema / required
      Added value: +[
+  "query_text"
+]
  2. First observedv0.1.0

TDQS

A3.8/5.0
Behavior3/5

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

With no annotations, the description carries the full burden. It adds useful behavior: results are relevance-ranked, child elements and control prose are included, and "loaded" documents are the scope. It still omits details such as read-only assurance, pagination behavior, and result shape beyond the entity-ID follow-up hint.

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 two compact sentences with the primary purpose front-loaded. Every sentence contributes either search scope/ranking or follow-up guidance, with no repetition 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?

The tool is a search operation, the input schema is fully documented, and the description supplies key context: relevance ranking, child-element coverage, and that child hits expose an entity ID plus parentDocumentUuid for get_child_element. Details of the full result payload are not described, but the essential behavior and follow-up path are covered.

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 schema already explains query_text, limit, offset, and oscal_model_type. The description adds no additional parameter semantics for this tool; its mention of parentDocumentUuid refers to get_child_element rather than a parameter here, so baseline 3 is appropriate.

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 uses a specific verb and resource: "Search loaded OSCAL documents and child elements, including control prose." It also distinguishes this as a relevance-ranked text search and mentions the follow-up tool for child hits, so an agent can tell what it 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 Guidelines3/5

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

The description implies usage through "Search loaded OSCAL documents" and explains a follow-up path to get_child_element for child hits. However, it does not explicitly say when to choose this over structured siblings like query_catalog, query_ssp, or query_oscal_documentation.

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

Deploy Server

Other Tools