ai.plith/rigor

None of its 4 tools are described as changing anything. For 4 the reading was uncertain, so no mark is shown.

• rigor_planon 1 other server

  “Before executing a complex task, get a structured workflow plan with per-step cost estimates.”

  Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes

  5 inputs, 1 required

  • task_descriptionstringrequired“Natural language description of the task, at most 4,000 characters.”
  • task_typestring“Optional hint to bypass automatic classification.”
  • preferencesobject“Optional workflow preferences.”
  • prior_workflow_idstring“Optional: the workflow_id (wr_…) of a finished workflow in your workspace to build on.”
  • context_fieldsarray“Optional, with prior_workflow_id: the fields to carry over.”
• rigor_executeon 1 other server

  “Execute a structured workflow end-to-end.”

  Publisher declares: read-only no · destructive no · idempotent no · open-world yes

  7 inputs, 1 required

  • task_descriptionstringrequired“Natural language description of the task, at most 4,000 characters.”
  • task_typestring“Optional hint to bypass automatic classification.”
  • deliveryobject“Delivery method.”
  • preferencesobject“Optional workflow preferences.”
  • contextobject“Additional context for the workflow.”
  • prior_workflow_idstring“Optional: the workflow_id (wr_…) of a finished workflow in your workspace to build on.”
  • context_fieldsarray“Optional, with prior_workflow_id: the fields to carry over.”
• rigor_statuson 1 other server

  “Check the status of a running or completed Rigor workflow.”

  Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

  1 input, 1 required

  • workflow_idstringrequired“The workflow ID returned by rigor_execute (format: wr_xxx).”
• rigor_workflowson 1 other server

  “List and search Rigor workflows for your organization, with filtering and pagination.”

  Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

  9 inputs

  • statusstring“Filter by status (comma-separated).”
  • task_typestring“Filter by classified task type”
  • qstring“Search the workflow title and task description.”
  • folder_idstring“Filter by folder ID.”
  • created_afterstring“ISO timestamp — only workflows created after this time”
  • created_beforestring“ISO timestamp — only workflows created before this time”
  • counts_toward_limitstring“Filter to workflows counting toward the concurrent limit”
  • limitnumber“Page size (default 20, max 100)”
  • cursorstring“Pagination cursor (created_at timestamp from previous page)”

Each quoted sentence is the first sentence of the publisher’s own description. The kind of tool and the “changes data” mark are our AI model’s reading of that description, not something we tested: two differently worded runs had to agree, otherwise no label is shown, and nobody has checked them by hand. A tool without the “changes data” mark is described as only reading, searching or calculating, or the two runs did not agree. No tool was called. Read the publisher’s full description before relying on it. “Publisher declares” lists the hints the server itself sends with the tool (MCP annotations: read-only, destructive, idempotent, open-world); they are the publisher's claims, not checked by us. Inputs are the parameters in the tool's own input schema: name, declared type, whether it is required, and the first sentence of its description. Read 2026-10-26.

The registry verifies a package once, when it is published, and does not re-check it. A difference below is about the listing, not a judgement of the publisher.