Skip to main content
Glama
Mipiti

Mipiti MCP Server

by Mipiti
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

Get Scan Prompt

get_scan_prompt

Retrieve security or functional scan briefs that identify missing evidence and unverified tests, guiding agents through gap discovery and test implementation.

Instructions

Get guidance prompts for scanning a codebase. Read-only; no side effects.

kind selects which scan brief to return:

  • "security" (default) — prompts telling the agent what evidence to look for per security control; only NOT_IMPLEMENTED controls are included (implemented ones need no scan). Use this to drive a gap-discovery pass, then record what is missing with submit_findings and what is present with submit_assertions. Pass control_id to scope the prompt to one control; empty (default) returns prompts for all not-yet-implemented controls.

  • "functional" — the agent brief for implementing functional-conformance tests. Generation specifies the functional tests, so for each test not yet verified this returns its implementation brief and the objectives it proves; it also reports objectives_without_tests (regenerate or add a test) and missing_objectives (applicable conditions with no objective yet). Drive test implementation from it, then call submit_functional_test_assertions with TEST_EXISTS + TEST_ATTESTED assertions so CI verifies each test; read the resulting pass/fail state via get_functional_coverage. control_id does not apply to this kind and is ignored.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
kindNo"security" (default) or "functional" — which scan brief.security
model_idYesID of the threat model.
control_idNoSecurity kind only — optional single control to scope the prompt to. Empty (default) returns prompts for all not-yet-implemented controls. Ignored when kind="functional".
server_versionYes

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.68.2
    • changedInput schema / properties / control_id / description
      Previous value: -"Optional single control to scope the prompt to. Empty (default) returns prompts for all not-yet-implemented controls."New value: +"Security kind only — optional single control to scope\nthe prompt to. Empty (default) returns prompts for all\nnot-yet-implemented controls. Ignored when kind=\"functional\"."
    • addedInput schema / properties / kind
      Added value: +{
+  "default": "security",
+  "description": "\"security\" (default) or \"functional\" — which scan brief.",
+  "type": "string"
+}
  2. Changed1 schema field changedv0.66.0
    • changedInput schema / properties / control_id / description
      Previous value: -"Optional specific control ID."New value: +"Optional single control to scope the prompt to. Empty (default) returns prompts for all not-yet-implemented controls."
  3. Addedv0.62.2
  4. Removedv0.62.0
  5. First observedv0.57.0

TDQS

A4.8/5.0
Behavior5/5

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

With no annotations provided, the description carries the full transparency burden and does so well: it explicitly states 'Read-only; no side effects.' It also reveals behavioral details such as only NOT_IMPLEMENTED controls being included, the default behavior of kind, and control_id being ignored for functional. This goes well beyond the schema.

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 longer but well-organized by mode, with the core statement and read-only guarantee front-loaded. Most sentences earn their place because they explain mode-specific behavior and workflow. Some phrasing is dense and could be tightened, but the structure is effective.

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?

Given that an output schema exists and the tool is read-only, the description covers everything needed to select and call it correctly: both modes, default behavior, parameter applicability, and downstream tools. The only minor omission is server_version semantics, but the required parameter is visible in the schema and the overall operational context is complete.

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 75%, so the schema already describes kind, model_id, and control_id reasonably. The description adds meaningful context for kind and control_id, including mode-specific behavior and downstream workflow impact. However, server_version remains undocumented in both the schema and description, preventing a 5.

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 returns guidance prompts/scan briefs for scanning a codebase, with a simple verb+resource framing. It further distinguishes the two kinds of scan briefs (security and functional), so an agent can tell what this tool is for without confusion from its many siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

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

Explicit usage guidance is provided for both modes: use the security kind for gap-discovery and then submit_findings/submit_assertions; use the functional kind to drive test implementation and then submit_functional_test_assertions and read get_functional_coverage. It also clearly states that control_id is ignored for functional, preventing misapplication.

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