plith
Server Details
AI agent infrastructure: dedup, cost prediction, validation, governance, failure intelligence.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-06-18
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 4 tools
Each tool targets a distinct lifecycle stage: planning, execution, job status, and workflow listing. The only mild overlap is between rigor_status and rigor_workflows, both monitoring-oriented, but descriptions clearly delineate single-workflow retrieval versus org-wide listing.
All tools share a predictable rigor_ prefix, but the suffixes mix verbs and nouns (execute/plan vs status/workflows), so the pattern isn't uniformly verb_noun. Still readable and predictable in practice.
Four tools is on the thin side for a workflow orchestration platform, but each maps to a necessary step (preview, run, poll, list). Nothing appears redundant or padded.
The surface covers plan → execute → poll → list, but lacks obvious lifecycle operations such as cancel/abort a running workflow or explicitly delete/archive prior runs. Agents could work around some of this, but cancellation and cleanup are notable dead ends.
Available Tools
4 toolsrigor_executeAInspect
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.
Inputs: mode, context, agent_id, delivery, +9 more.
rigor_planARead-onlyIdempotentInspect
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.
Inputs: task_description (required), context, agent_id, language, +4 more.
rigor_statusARead-onlyIdempotentInspect
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.
Inputs: workflow_id (required).
rigor_workflowsARead-onlyIdempotentInspect
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.
Inputs: q, limit, cursor, status, +5 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
AI agent infrastructure for discovery, authorization, execution, identity, and signed receipts.
Infrastructure for AI agents from different companies and people to work together.
AI agent cost control: true cost per outcome, budgets, spend limits, anomalies, audit evidence.
Agent-native security, trust, reliability, data and procurement tools for AI workflows.
Related MCP Servers
- AlicenseAqualityBmaintenanceEnables autonomous AI agents to proactively poll event queues, evaluate document compliance, retrieve grounded knowledge via semantic RAG, enforce human-in-the-loop approval gates, and track multi-model cost budgets.10MIT
- AlicenseAqualityBmaintenanceGovernance layer for AI agent spending: enforces budgets, per-merchant limits and human approval before issuing single-use virtual cards (Lithic, PayPal), with a tamper-evident audit log.5307 npmApache 2.0
- AlicenseAqualityDmaintenanceCompliance and guardrails infrastructure for AI agents, enabling safe operations within regulatory boundaries like GDPR and EU AI Act.621 PyPIMIT

ComputeGauge MCPofficial
AlicenseNot gradedqualityDmaintenanceProvides cost intelligence and a reputation scoring system to help AI agents optimize spending through smart model selection and local-to-cloud routing. It enables real-time cost tracking and rewards agents for making efficient, high-credibility decisions across various LLM providers.Apache 2.0
Glama MCP Gateway
Add one secure layer between your agents and this server.