Skip to main content
Glama
Mipiti

Mipiti MCP Server

by Mipiti
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

Get Controls

get_controls

Read a model's controls or a single control, filter by status, CO, or component, and page results to inspect published, orphaned, deleted, or verification details.

Instructions

A model's controls, or one control. Read-only.

Without control_id: {controls, total, returned}, the published set, filtered by status, co_id and component_id and paged by offset / limit. Orphaned controls (every mapped CO tombstoned) are left out unless include_orphaned=True, soft-deleted ones unless include_deleted=True. summary_only=True returns only id, description, status, verification_status, assertion_count, co_ids, assumption_groups and attestation_dependency. An empty list on a new model means its proposed build was never started (get_control_generation_status); while a build holds the model the list is the last published set, with a building marker.

With control_id: that control, with an orphaned flag; version reads it as of a model version (0 = latest).

An objective id on a control is an ATTACHMENT, not credit: only a member of a required mitigation group earns any, and a control that is defense-in-depth everywhere can be implemented and verified without moving an objective. Read get_mitigation_groups before evidence work.

status is the operator's (not_implemented / implemented / verified); verification_status is the EVIDENCE: verified (both tiers pass and the assertions cover the whole description), partially_verified (a tier failed, clauses are unproven, or an attestation EXPIRED — get_sufficiency says which; the fix is more assertions or a narrower description, never a recompute), pending, unverified (none submitted). A for-all clause is credited only by a sound type bound with covers; get_control_work_order lists what each clause needs. status="implemented" finds what still needs evidence. Only this model's own controls are listed; inherited ones are counted by assess_model.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
co_idNo
limitNo
offsetNo
statusNo
versionNo
model_idYes
control_idNo
component_idNo
summary_onlyNo
server_versionYes
include_deletedNo
include_orphanedNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed11 schema fields changedv0.84.0
    • removedInput schema / properties / co_id / description
      Removed value: -"List-mode filter — control objective ID."
    • removedInput schema / properties / component_id / description
      Removed value: -"List-mode filter — component ID (e.g., \"CMP1\")."
    • removedInput schema / properties / control_id / description
      Removed value: -"If set, detail mode — return this one control's full\nrecord directly (e.g. ``CTL-12``). If omitted, list mode."
    • removedInput schema / properties / include_deleted / description
      Removed value: -"List mode — include soft-deleted controls\n(default False)."
    • removedInput schema / properties / include_orphaned / description
      Removed value: -"List mode — include controls mapped only to\ntombstoned COs (default False)."
    • removedInput schema / properties / limit / description
      Removed value: -"List mode — max controls to return (0 = all)."
    • removedInput schema / properties / model_id / description
      Removed value: -"ID of the threat model."
    • removedInput schema / properties / offset / description
      Removed value: -"List mode — skip the first N controls (pagination)."
    • removedInput schema / properties / status / description
      Removed value: -"List-mode filter — \"implemented\", \"not_implemented\", or\n\"verified\"."
    • removedInput schema / properties / summary_only / description
      Removed value: -"List mode — if True, returns only id, description,\nstatus, assertion_count, and assumed_by per control (much\nsmaller response)."
    • removedInput schema / properties / version / description
      Removed value: -"Detail mode only — model version to read the control\nfrom. 0 (default) uses the latest. Ignored in list mode."
  2. Changed1 schema field changedv0.71.1
    • changedInput schema / properties / control_id / description
      Previous value: -"If set, detail mode �� return this one control's full\nrecord directly (e.g. ``CTL-12``). If omitted, list mode."New value: +"If set, detail mode — return this one control's full\nrecord directly (e.g. ``CTL-12``). If omitted, list mode."
  3. Changed1 schema field changedv0.71.0
    • changedInput schema / properties / control_id / description
      Previous value: -"If set, detail mode — return this one control's full\nrecord directly (e.g. ``CTL-12``). If omitted, list mode."New value: +"If set, detail mode �� return this one control's full\nrecord directly (e.g. ``CTL-12``). If omitted, list mode."
  4. Changed10 schema fields changedv0.68.2
    • changedInput schema / properties / co_id / description
      Previous value: -"Filter by control objective ID."New value: +"List-mode filter — control objective ID."
    • changedInput schema / properties / component_id / description
      Previous value: -"Filter by component ID (e.g., \"CMP1\")."New value: +"List-mode filter — component ID (e.g., \"CMP1\")."
    • changedInput schema / properties / control_id / description
      Previous value: -"Optional specific control id for detail mode."New value: +"If set, detail mode — return this one control's full\nrecord directly (e.g. ``CTL-12``). If omitted, list mode."
    • changedInput schema / properties / include_deleted / description
      Previous value: -"Include soft-deleted controls (default False)."New value: +"List mode — include soft-deleted controls\n(default False)."
    • changedInput schema / properties / include_orphaned / description
      Previous value: -"Include controls mapped only to tombstoned COs\n(default False)."New value: +"List mode — include controls mapped only to\ntombstoned COs (default False)."
    • changedInput schema / properties / limit / description
      Previous value: -"Max controls to return (0 = all)."New value: +"List mode — max controls to return (0 = all)."
    • changedInput schema / properties / offset / description
      Previous value: -"Skip the first N controls (pagination)."New value: +"List mode — skip the first N controls (pagination)."
    • changedInput schema / properties / status / description
      Previous value: -"Filter by \"implemented\", \"not_implemented\", or \"verified\"."New value: +"List-mode filter — \"implemented\", \"not_implemented\", or\n\"verified\"."
    • changedInput schema / properties / summary_only / description
      Previous value: -"If True, returns only id, description, status,\nassertion_count, and assumed_by per control (much smaller\nresponse)."New value: +"List mode — if True, returns only id, description,\nstatus, assertion_count, and assumed_by per control (much\nsmaller response)."
    • addedInput schema / properties / version
      Added value: +{
+  "default": 0,
+  "description": "Detail mode only — model version to read the control\nfrom. 0 (default) uses the latest. Ignored in list mode.",
+  "type": "integer"
+}
  5. Changed7 schema fields changedv0.66.0
    • changedInput schema / properties / control_id / description
      Previous value: -"Optional specific control for detail mode."New value: +"Optional specific control id for detail mode."
    • changedInput schema / properties / include_deleted / description
      Previous value: -"Include soft-deleted controls."New value: +"Include soft-deleted controls (default False)."
    • changedInput schema / properties / include_orphaned / description
      Previous value: -"Include controls mapped only to tombstoned\nCOs (default False)."New value: +"Include controls mapped only to tombstoned COs\n(default False)."
    • changedInput schema / properties / limit / description
      Previous value: -"Max to return (0=all)."New value: +"Max controls to return (0 = all)."
    • changedInput schema / properties / offset / description
      Previous value: -"Skip first N (for pagination)."New value: +"Skip the first N controls (pagination)."
    • changedInput schema / properties / status / description
      Previous value: -"Filter by \"implemented\", \"not_implemented\", \"verified\"."New value: +"Filter by \"implemented\", \"not_implemented\", or \"verified\"."
    • changedInput schema / properties / summary_only / description
      Previous value: -"If True, returns only id, description, status,\nassertion_count, and assumed_by per control (much smaller response)."New value: +"If True, returns only id, description, status,\nassertion_count, and assumed_by per control (much smaller\nresponse)."
  6. Addedv0.62.2
  7. Removedv0.62.1
  8. First observedv0.57.0

TDQS

A4.5/5.0
Behavior4/5

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

With no annotations, the description carries the full disclosure burden and largely meets it: read-only nature, default exclusion of orphaned/soft-deleted rows via include_orphaned/include_deleted, the summary_only projection, the 'building' marker while a build holds the model, and version=0 meaning latest. It omits any permission/auth or rate-limit context, which keeps it short of a 5.

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 purpose is front-loaded and the 'Without control_id / With control_id' split gives useful structure. The later paragraphs on objective attachment, mitigation groups, and clause crediting are dense and somewhat tangential to invoking this reader, so it runs longer than strictly needed.

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?

For a 12-parameter domain-specific tool the coverage is strong: return shapes are sketched, filter semantics are defined, and follow-up tools are named for the edge cases it flags. An output schema exists, so the return-value detail is redundant but not harmful.

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

Parameters5/5

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

Schema description coverage is 0%, so the description must compensate, and it does: control_id as the mode switch, status with its enum values, co_id/component_id/offset/limit as filters and paging, include_orphaned/include_deleted defaults, summary_only, and version semantics (0 = latest). Only the self-evident required ids (model_id, server_version) go unmentioned.

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 opening sentence states a specific resource and scope ('A model's controls, or one control') and immediately flags the operation as read-only. It cleanly separates the two modes (list without control_id, single entity with control_id), so an agent can distinguish it from neighbors like get_control_work_order or list_assertions.

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 gives real operational routing: read get_mitigation_groups before evidence work, consult get_control_generation_status when the list is empty, and use status="implemented" to find what still needs evidence. It does not, however, explicitly say when to prefer this over sibling readers such as get_control_work_order or get_sufficiency.

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