# Plith Rigor

> Plith Rigor is a freemium MCP server for productivity. Remote MCP server that plans and runs structured analysis workflows for business and code. It runs as a hosted remote server, so there is nothing to install locally.

- **Kind:** MCP server
- **Pricing:** Freemium
- **Platforms:** API, Web
- **Website:** https://plith.ai
- **Repository:** https://github.com/newsspectator/plith
- **MCP Registry name:** ai.plith/rigor
- **Categories:** productivity, developer tools
- **Listing updated:** 2026-11-14

## About

The pitch comes from a former strategy consultant: instead of one chat completion, Rigor routes a task through a sequence of established frameworks, researches it, reviews its own draft and returns a deliverable with a record of every step. Examples on the site include competitive scans, SWOT analyses, gap analyses, solution designs, code reviews and bug diagnosis, each with a quality score and cost breakdown.

The MCP server exposes discoverable tools for plan, execute, status and workflows, plus hidden ones for resume, approve, step, connections and manage. Planning a task is always free and returns a plan in under five seconds. Execution streams over SSE, and a failed review sends work back for refinement. The same functions are available through a REST endpoint.

Billing has two layers: a monthly plan for the platform and credits at $1 per 1,000 for the AI work. Typical standard-level runs listed include a competitive scan at $2.70 to $4.30 and a research brief at $1.70 to $3.40. Failed runs with no output are refunded in full. Rigor can also read a connected codebase, docs and tickets, with connections isolated per workspace.

## Features

- **Free task planning:** Plan calls cost nothing and show an estimate before you commit.
- **Structured deliverables:** Competitive scans, SWOT, gap analysis, solution designs, code reviews and bug diagnosis.
- **Quality gates:** Reviews run at checkpoints and a failed review sends work back for refinement.
- **Step-by-step control:** Interactive mode lets you approve each step and see full outputs.
- **MCP plus REST:** The same engine is reachable through an MCP server or one REST endpoint with SSE streaming.
- **Workspace-scoped connections:** Codebase, docs and ticket connections stay isolated per workspace.

## Good for

- Produce a competitive scan with sources for a planning meeting
- Run a codebase-aware code review from an editor agent
- Size a market or draft a business case with a step-by-step audit trail
- Let an agent request a planned and reviewed deliverable instead of raw model output

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http rigor https://plith.ai/api/mcp/rigor
```

### Claude Desktop (Settings → Connectors → Add custom connector)

```sh
https://plith.ai/api/mcp/rigor
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "rigor": {
      "url": "https://plith.ai/api/mcp/rigor"
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "rigor": {
      "type": "http",
      "url": "https://plith.ai/api/mcp/rigor"
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "rigor": {
      "serverUrl": "https://plith.ai/api/mcp/rigor"
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

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

## FAQ

### Is there a free tier?

New accounts get 20,000 credits on signup after email verification, worth $20, with no card required. Credits never expire.

### What does a task cost?

Credits are $1 per 1,000. Standard-level examples include $2.70 to $4.30 for a competitive scan and about $0.20 for a quick task.

### What if a workflow fails?

With no output you get a full credit refund; with partial output you pay only for completed steps.

### Does it train on my data?

The site says it does not train on your data and that data is encrypted in transit and at rest.

### Which plan adds team features?

Team supports up to 20 members and 10 workspaces; Enterprise is $399 a month for up to 50 members.

### Is Plith Rigor free?

Plith Rigor has a free plan, with paid plans for more usage or features.

### How do I add Plith Rigor to Claude Code?

Run this command in your terminal: claude mcp add --transport http rigor https://plith.ai/api/mcp/rigor

### What are the best alternatives to Plith Rigor?

The closest alternatives to Plith Rigor are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.

## Alternatives

- [REA](https://ai-powered.com/mcp/rea): REA is an open-source MCP server for developer tools.
- [Codebase Memory](https://ai-powered.com/mcp/codebase-memory): Codebase Memory is an open-source MCP server for knowledge and memory.
- [GitHub](https://ai-powered.com/mcp/github-2): GitHub is an open-source MCP server for developer tools.
- [Serena MCP: the IDE for your agent](https://ai-powered.com/mcp/serena-mcp-the-ide-for-your-agent): Serena MCP: the IDE for your agent is an open-source MCP server for developer tools.
- [XERJ](https://ai-powered.com/mcp/xerj): XERJ is an open-source MCP server for knowledge and memory.
- [Ha MCP](https://ai-powered.com/mcp/ha-mcp): Ha MCP is an open-source MCP server for productivity.
- [Ouroboros](https://ai-powered.com/mcp/ouroboros): Ouroboros is an open-source MCP server for developer tools.
- [Claude Code Ultimate Guide](https://ai-powered.com/mcp/claude-code-ultimate-guide): Claude Code Ultimate Guide is an open-source MCP server for ai models and llm tooling.

---
Source: https://ai-powered.com/mcp/plith-rigor
