MCP server for AI coding agents — persistent engineering memory, knowledge compounding, and spec-driven development workflows. Part of TRW Framework.
Agent
Read-only red-team adapter for the standard TRW audit protocol. Use when an independent pass after or alongside trw-auditor should challenge generous verdicts, Potemkin gates, unreachable safety logic, or unsupported exclusions.
Agent
Spec-vs-code auditor with bidirectional traceability verification. Use when you need to verify a PRD has been implemented as specified — every FR traced to source and tests, every NFR checked, wiring confirmed end-to-end. Runs a read-only 7-phase audit with wave pauses. Not for code-style review (use trw-reviewer) or…
Agent
Implement production code and its tests within assigned boundaries. Use when a PRD-backed feature, focused fix, or coverage gap requires behavior tracing, integration, project-native validation, and evidence. Honors existing contracts and shared-workspace ownership.
Agent
Client-neutral coordination lead. Use when work has independent streams, explicit integration boundaries, or enough risk to benefit from delegated research, implementation, testing, and review. Adapts to available harness capabilities and falls back to safe sequential coordination. Does not write production code.
Agent
PRD authoring and grooming specialist. Use when a PRD must be created, grounded in repository evidence, reviewed for testable requirements, or advanced to a full, valid, risk-scaled approved result. Not for implementation.
Agent
Read-only PRD quality review. Use when sprint readiness needs an independent, evidence-linked assessment after drafting or grooming. Returns category-aware blocking findings, actionable remediation conditions, and a READY, NEEDS WORK, or BLOCK verdict; it does not edit the PRD.
Agent
Evidence-grounded requirements author. Use when a feature description, research finding, or existing PRD needs singular functional and non-functional requirements with requirement-appropriate verification. Uses EARS or Given/When/Then only when those forms improve clarity.
Agent
Read-only investigation of code, external evidence, and competing approaches. Use when an implementation decision depends on facts, tradeoffs, root-cause analysis, or current primary sources. Returns scoped findings with citations, uncertainty, and recommended next steps.
Agent
Read-only review of changed code and tests for correctness, security, performance, maintainability, integration, and requirement compliance. Use when pre-delivery or pre-merge findings must be prioritized, evidence-linked, and actionable.
Agent
Test specialist for coordinated helper workflows. Use when a sprint task needs comprehensive tests written — verifies PRD acceptance criteria, follows the project-configured coverage gate, parametrizes edge cases, writes unit and integration tests. Not for production-code implementation (use trw-implementer) or ad-hoc…
Agent
Read-only requirement traceability verification. Use when source and test links must be checked before delivery. Reports verified, missing, stale, ambiguous, and orphan links; applies a configured gate only when the project or requirement defines one.
Agent
You are TRW's codebase exploration specialist. You have read-only access to tools for search and analysis.