Mipiti MCP Server

Overview Schema Source Related Servers Discussions Admin

Regenerate Controls

regenerate_controls

Propose rebuilding a threat model's controls from current COs, keeping unchanged control data and soft-deleting changed controls; optionally scope to specific CO IDs.

Instructions

Propose a regeneration of the model's controls. Starts nothing.

A regeneration re-authors controls from the current COs; its publish creates the next model version. Controls whose descriptions survive unchanged KEEP their implementation status, evidence, notes, assertions, and Jira / compliance mappings. Controls whose descriptions change or disappear are soft-deleted (still queryable via get_controls(include_deleted=True)). When co_ids is given, only those COs' controls are regenerated — all other controls are left as-is.

This tool records the regeneration as the model's PROPOSED build and returns at once with status: "proposed" and proposal (mode, objective_ids, objective_count, estimated_credits, and the model_version and set_revision a start must name). A proposal merges with any already proposed for the model, the broader one winning. Show the user what it would build and cost; once they agree, call start_control_build with those values and confirm_estimate=True. A build someone started holds the model, so this is refused (409 generation_active) until it finishes, or is resumed and finishes, or is discarded.

To rebuild everything, omit co_ids. To fix only stale/orphaned CO mappings without re-authoring control text, prefer remap_control (mechanical, no LLM).

Input Schema

TableJSON Schema

Name	Required	Description	Default
`mode`	No	"batch" (default) or "per_co" (most thorough — one LLM call per CO).	batch
`co_ids`	No	Optional comma-separated CO IDs to regenerate (e.g. "CO1,CO5"). Omit to regenerate all controls.
`model_id`	Yes	ID of the threat model.
`batch_size`	No	COs per batch in batch mode (default 15). Smaller = more accurate and more granular progress, but more LLM calls.
`server_version`	Yes

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedv0.66.0Aug 5, 2026

changedInput schema / properties / batch_size / description

Previous value: -"COs per batch in batch mode (default: 15). Smaller\n= more accurate + granular progress, more LLM calls."New value: +"COs per batch in batch mode (default 15). Smaller =\nmore accurate and more granular progress, but more LLM calls."

changedInput schema / properties / co_ids / description

Previous value: -"Optional comma-separated CO IDs to regenerate (e.g.\n\"CO1,CO5\"). When omitted, regenerates all controls."New value: +"Optional comma-separated CO IDs to regenerate (e.g.\n\"CO1,CO5\"). Omit to regenerate all controls."

changedInput schema / properties / mode / description

Previous value: -"\"batch\" (default) or \"per_co\" (most thorough, one LLM\ncall per CO)."New value: +"\"batch\" (default) or \"per_co\" (most thorough — one LLM call\nper CO)."

First observedv0.57.0Jul 8, 2026

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 burden and does so: it discloses what survives (status, evidence, notes, assertions, mappings), what is destroyed (changed/removed controls soft-deleted, still queryable via get_controls(include_deleted=True)), merge semantics (broader proposal wins), and the immediate return shape (status "proposed" plus proposal fields). This is unusually complete behavioral disclosure for a mutation-adjacent tool.

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?

Front-loads the crucial distinction ("Starts nothing") and each subsequent sentence carries distinct information: retention rules, scoping, return payload, and the conflict path. It runs long across several paragraphs, but the density is high and little is redundant.

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 proposal tool with an output schema, annotations absent, and 5 parameters, the description covers purpose, side effects, scoping, return contract, and the handoff to start_control_build. Nothing an agent needs to invoke it correctly is missing.

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 80%, so the schema already documents mode, co_ids, and batch_size. The description adds real meaning beyond it: co_ids scoping ("only those COs' controls are regenerated — all other controls are left as-is") and the omit-co_ids default ("To rebuild everything, omit co_ids"). batch_size and the batch/per_co tradeoff are left to the schema.

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?

States a specific verb+resource ("Propose a regeneration of the model's controls") and immediately disambiguates from the actual build with "Starts nothing." It distinguishes itself from siblings like start_control_build and remap_control explicitly, so an agent can route 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 Guidelines5/5

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

Names the follow-up action and condition ("once they agree, call start_control_build with those values and confirm_estimate=True"), names an alternative for a narrower case ("prefer remap_control (mechanical, no LLM)"), and states the blocking condition (409 generation_active). Nothing is left to inference.

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

Deploy Server