Plith Rigor

ai.plithPublished by plith.aiOfficial publisherv1.0.0Updated Oct 25, 2026

Structured multi-step workflows that produce production-quality deliverables. Plan any task free.

The publisher's own server: Plith

VerifiedStreamable HTTPWeb executableProductivity & WorkflowAI & ML

Overview

AI-generated overview

Plith Rigor is a remote MCP server that plans and runs structured multi-step workflows, producing deliverables such as solution designs.

What you can do
Plan a task: classify it, pick a framework sequence and return a step-by-step plan with per-step cost estimates, without executing anything, plus whether the plan is eligible for direct execution. Execute a workflow: run the planned steps end-to-end with the appropriate LLM model per step and return a complete deliverable. Check status: poll a running or completed workflow for progress, step results and the final deliverable. List and search workflows: filter and page through your organization's workflows, with status, progress, capacity usage and available actions.
When to use it
Useful when a task is complex enough to benefit from a structured multi-step plan and a finished deliverable rather than a single answer, and when you want to preview the step sequence and cost before committing credits.
Requirements
A remote streamable HTTP endpoint; no packages, environment variables or headers are declared. No authentication is declared, though workflows are scoped to an organization. Network access to the endpoint is required.
Before you install
Execution consumes credits, so preview with the free planning step before committing. Workflows are tied to an organization and can be listed and searched, so prior work is visible to that scope. Execution runs tasks end-to-end and produces deliverables, which may involve sending task content to third-party LLM models.

Installation

In SourceWeft

  1. Open Plith Rigor in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/ai.plith%2Frigor/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "plith-rigor": {
      "type": "http",
      "url": "https://plith.ai/api/mcp/rigor"
    }
  }
}

README

This repository has no README.

Tools

4

rigor_plan

Plan a Rigor workflow

Before executing a complex task, get a structured workflow plan with per-step cost estimates. Classifies your task, selects the optimal framework sequence, and returns the full plan without executing anything. The response's allowed_modes tells you whether this plan is eligible for direct execution. Free — no credits charged.

Parameterstask_typepreferencescontext_fieldstask_descriptionrequiredprior_workflow_id

rigor_execute

Execute a Rigor workflow

Execute a structured workflow end-to-end. Call rigor_plan first (free) to preview the step sequence and cost estimate before committing credits. Classifies the task, selects the optimal tool sequence, and executes each step with the right LLM model. Returns a complete deliverable — solution designs, competitive analyses, governance documents, and more. Supports SSE streaming for real-time progress, webhook callback, or polling. For atomic work — classification, scoring, ranking, entity extraction, query parsing — set preferences.execution to 'direct' and declare preferences.output_contract to get validated JSON records from a single call, routed to the cheapest model that holds the schema.

Parameterscontextdeliverytask_typepreferencescontext_fieldstask_descriptionrequiredprior_workflow_id

rigor_status

Check workflow status

Check the status of a running or completed Rigor workflow. Returns progress, step results, and the full deliverable when complete. Use after rigor_execute with polling delivery to retrieve results.

Parametersworkflow_idrequired

rigor_workflows

List Rigor workflows

List and search Rigor workflows for your organization, with filtering and pagination. Returns status, progress, capacity usage, and available actions per workflow. Use to monitor workflow state, understand concurrent limit usage, identify stuck or completed workflows, and — via q — find prior work on a subject before commissioning it again. Pair a q hit with rigor_status to read that workflow's deliverable.

Parametersqlimitcursorstatusfolder_idtask_typecreated_aftercreated_beforecounts_toward_limit

Version history

1
  1. v1.0.0LatestOct 25, 2026

Score

75% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • License10 pts

    Declare a license in the repository or the registry entry.

Other Plith integrations

Plith

ai.plithOfficial publisher

Plith is a remote MCP server that gives an AI assistant infrastructure tools for caching repeated LLM tasks, estimating and tracking LLM costs, validating agent

Streamable HTTPWeb executable
Security & Monitoring15 toolsOct 24, 2026