Skip to main content
Glama
Mipiti

Mipiti MCP Server

by Mipiti
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

List Decisions

list_decisions

Read a threat model's append-only decision ledger, newest first, showing who decided what and whether it fell within delegation policy; call before proposing or asking for a judgment.

Instructions

List the decision ledger of a model: every judgment recorded on it (finding dismissed or remediated, risk accepted, not-applicable declared, proposal accepted / rejected / reverted, assumption accepted, behavioural model answered / confirmed, a control's delta declared, a finding of its cross-check dismissed, a seal, position, privileges or surface extent attested, escalation resolved, an inventory pair decided or an entity's tags declared), newest first, with who made it and whether it was within the workspace's delegation policy. Read-only; no side effects.

Call this BEFORE raising a proposal or asking for a judgment, so you do not propose what a person rejected or ask again for what was already decided.

The ledger is append-only. There is no tool that edits it; to undo an accepted proposal, revert or re-decide, never edit the record. Rows with outcome == "refused" are judgments a program was refused; their escalation, if any, is in list_proposals. agent is null for a person's decision.

Input Schema

NameRequiredDescriptionDefault
limitNoMaximum rows to return. 0 (default) uses the server default.
decisionNoOptional kind filter, one of ``finding_dismissed``, ``finding_remediated``, ``risk_accepted``, ``not_applicable_declared``, ``proposal_accepted``, ``proposal_rejected``, ``proposal_reverted``, ``assumption_accepted``, ``behavioural_model_answered`` (an answer, an element edit or a link declared), ``behavioural_model_confirmed``, ``behavioural_delta_declared``, ``behavioural_cross_check_dismissed`` (a person set aside a finding of a declaration's cross-check), ``behavioural_confirmation_withdrawn`` (a confirmation withdrawn by a report that the code does more than the description), ``seal_attested``, ``position_attested``, ``privileges_attested``, ``extent_attested``, ``escalation_resolved``, ``drift_intent_decided`` (whether a description-drift finding was intended or a defect of the code), ``description_revised`` (a revised description accepted), ``inventory_pair_decided`` (two inventory entries decided one entity or not), ``inventory_tag_declared`` (an entity's taxonomy tags declared). Empty (default) returns every kind.
model_idYesID of the threat model.
agent_onlyNoOnly decisions made by a program (``agent`` not null). Default False.
server_versionYes
outside_policy_onlyNoOnly decisions made outside the delegation policy in force at the time (``within_policy`` false). Default False.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.91.0
    • changedInput schema / properties / decision / description
      Previous value: -"Optional kind filter, one of ``finding_dismissed``,\n``finding_remediated``, ``risk_accepted``,\n``not_applicable_declared``, ``proposal_accepted``,\n``proposal_rejected``, ``proposal_reverted``,\n``assumption_accepted``, ``behavioural_model_answered``\n(an answer, an element edit or a link declared),\n``behavioural_model_confirmed``, ``behavioural_delta_declared``,\n``behavioural_cross_check_dismissed`` (a person set aside a\nfinding of a declaration's cross-check), ``seal_attested``,\n``position_attested``, ``privileges_attested``,\n``extent_attested``, ``escalation_resolved``,\n``drift_intent_decided`` (whether a description-drift finding was\nintended or a defect of the code), ``description_revised`` (a\nrevised description accepted). Empty (default) returns every\nkind."New value: +"Optional kind filter, one of ``finding_dismissed``,\n``finding_remediated``, ``risk_accepted``,\n``not_applicable_declared``, ``proposal_accepted``,\n``proposal_rejected``, ``proposal_reverted``,\n``assumption_accepted``, ``behavioural_model_answered``\n(an answer, an element edit or a link declared),\n``behavioural_model_confirmed``, ``behavioural_delta_declared``,\n``behavioural_cross_check_dismissed`` (a person set aside a\nfinding of a declaration's cross-check),\n``behavioural_confirmation_withdrawn`` (a confirmation withdrawn\nby a report that the code does more than the description),\n``seal_attested``, ``position_attested``, ``privileges_attested``,\n``extent_attested``, ``escalation_resolved``,\n``drift_intent_decided`` (whether a description-drift finding was\nintended or a defect of the code), ``description_revised`` (a\nrevised description accepted), ``inventory_pair_decided`` (two\ninventory entries decided one entity or not),\n``inventory_tag_declared`` (an entity's taxonomy tags declared).\nEmpty (default) returns every kind."
  2. Changed1 schema field changedv0.88.0
    • changedInput schema / properties / decision / description
      Previous value: -"Optional kind filter, one of ``finding_dismissed``,\n``finding_remediated``, ``risk_accepted``,\n``not_applicable_declared``, ``proposal_accepted``,\n``proposal_rejected``, ``proposal_reverted``,\n``assumption_accepted``, ``behavioural_model_answered``\n(an answer, an element edit or a link declared),\n``behavioural_model_confirmed``, ``behavioural_delta_declared``,\n``behavioural_cross_check_dismissed`` (a person set aside a\nfinding of a declaration's cross-check), ``seal_attested``,\n``position_attested``, ``privileges_attested``,\n``extent_attested``, ``escalation_resolved``. Empty (default)\nreturns every kind."New value: +"Optional kind filter, one of ``finding_dismissed``,\n``finding_remediated``, ``risk_accepted``,\n``not_applicable_declared``, ``proposal_accepted``,\n``proposal_rejected``, ``proposal_reverted``,\n``assumption_accepted``, ``behavioural_model_answered``\n(an answer, an element edit or a link declared),\n``behavioural_model_confirmed``, ``behavioural_delta_declared``,\n``behavioural_cross_check_dismissed`` (a person set aside a\nfinding of a declaration's cross-check), ``seal_attested``,\n``position_attested``, ``privileges_attested``,\n``extent_attested``, ``escalation_resolved``,\n``drift_intent_decided`` (whether a description-drift finding was\nintended or a defect of the code), ``description_revised`` (a\nrevised description accepted). Empty (default) returns every\nkind."
  3. Changed1 schema field changedv0.87.0
    • changedInput schema / properties / decision / description
      Previous value: -"Optional kind filter, one of ``finding_dismissed``,\n``finding_remediated``, ``risk_accepted``,\n``not_applicable_declared``, ``proposal_accepted``,\n``proposal_rejected``, ``proposal_reverted``,\n``assumption_accepted``, ``escalation_resolved``. Empty\n(default) returns every kind."New value: +"Optional kind filter, one of ``finding_dismissed``,\n``finding_remediated``, ``risk_accepted``,\n``not_applicable_declared``, ``proposal_accepted``,\n``proposal_rejected``, ``proposal_reverted``,\n``assumption_accepted``, ``behavioural_model_answered``\n(an answer, an element edit or a link declared),\n``behavioural_model_confirmed``, ``behavioural_delta_declared``,\n``behavioural_cross_check_dismissed`` (a person set aside a\nfinding of a declaration's cross-check), ``seal_attested``,\n``position_attested``, ``privileges_attested``,\n``extent_attested``, ``escalation_resolved``. Empty (default)\nreturns every kind."
  4. Changed1 schema field changedv0.83.1
    • changedInput schema / properties / decision / description
      Previous value: -"Optional kind filter, one of ``finding_dismissed``,\n``finding_remediated``, ``risk_accepted``,\n``not_applicable_declared``, ``proposal_accepted``,\n``proposal_rejected``, ``proposal_reverted``,\n``escalation_resolved``. Empty (default) returns every kind."New value: +"Optional kind filter, one of ``finding_dismissed``,\n``finding_remediated``, ``risk_accepted``,\n``not_applicable_declared``, ``proposal_accepted``,\n``proposal_rejected``, ``proposal_reverted``,\n``assumption_accepted``, ``escalation_resolved``. Empty\n(default) returns every kind."
  5. Addedv0.75.0

TDQS

A4.8/5.0
Behavior5/5

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

With no annotations present the description carries the full burden, and it does: "Read-only; no side effects", "The ledger is append-only. There is no tool that edits it." It also disambiguates record semantics the agent would otherwise misread — `outcome == "refused"` rows are refused judgments whose escalation lives elsewhere, and `agent` is null for a person's decision.

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?

Purpose and the read-only/append-only constraint are front-loaded, and the later notes on refused rows and null `agent` each earn their place. The long parenthetical enumerating every decision kind is somewhat redundant with the `decision` parameter's enum in the schema, which is the main source of bloat.

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?

An output schema exists, so return shape need not be explained; the description instead covers the things structure cannot — read-only nature, append-only immutability, correct recovery actions, and the meaning of refused/agent-null rows. For a 6-parameter list tool at 83% schema coverage, nothing an agent needs before calling 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 83%, so the baseline is 3; the description still adds value by spelling out the decision kinds that the `decision` filter accepts, stating the newest-first ordering that bears on `limit`, and explaining that rows carry who made them and whether they were within policy (i.e. what `outside_policy_only` selects). It does not restate defaults or the agent_only filter explicitly, so it is an addition rather than a full override.

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?

Opens with a specific verb+resource+ordering ("List the decision ledger of a model ... newest first") and immediately scopes what it returns (who made the decision, whether it was within delegation policy). The parenthetical enumerates the decision kinds so the agent knows exactly what class of records this covers, and it points to the sibling `list_proposals` for escalation detail, distinguishing the two.

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?

Gives explicit interventional guidance: "Call this BEFORE raising a proposal or asking for a judgment, so you do not propose what a person rejected or ask again for what was already decided." It also states the correct recovery path ("to undo an accepted proposal, revert or re-decide, never edit the record") and redirects escalation lookups to `list_proposals`, so the agent knows both when to call and where to go next.

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