ai-architect-mcp-spec — Claude Code MCP server: overview and setup
Validates PRDs and specs against code graphs and requirements before code generation begins. It catches hallucinated APIs and unlinked acceptance criteria early.
Open on GitHubWhat ai-architect-mcp-spec does
AI coding agents frequently hallucinate missing functions or invent performance targets during spec generation. This MCP server prevents those errors before any code gets written. It validates referenced symbols against a codebase graph and confirms that every acceptance criterion traces to a documented requirement. The verification rules run deterministically without calling a language model in the checking loop.
The project bundles 17 MCP tools across 20 pipeline stages. It operates as a stateless reducer where the server yields actions for the host environment to run. A panel of reasoning agents evaluates critical claims, logging outcomes to a local SQLite database for Bayesian reliability calibration. Consensus is monitored closely: an identical verdict across five or more claims triggers a suspicious distribution flag.
Local execution requires Node.js 20.x or 22.x and TypeScript 7.0+. The full generation workflow currently runs only in Claude Code, though other stdio hosts can execute the deterministic validator. Performance claims never receive an automatic pass without empirical benchmarks, forcing a status of SPEC-COMPLETE or NEEDS-RUNTIME.
What it helps with
- verify PRD symbols against the codebase graph
- trace acceptance criteria back to functional requirements
- block unmeasured latency and throughput claims
- calibrate judge agent reliability with Bayesian posteriors
Example prompts for the agent
- Verify this PRD draft against the codebase graph
- Run the step-by-step PRD generation pipeline with acceptance criteria checks
- Check if the judge panel consensus on these requirements looks suspicious
How to install ai-architect-mcp-spec
Install
The MCP registry has no launch command for it: see the repository README
Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about ai-architect-mcp-spec
How to install ai-architect-mcp-spec in Claude Code?
Running the server requires Node.js 20.x or 22.x alongside TypeScript 7.0+. You configure it locally as a stdio MCP process within Claude Code or another supported host.
What does ai-architect-mcp-spec do?
It exposes 17 MCP tools to create and verify software requirement documents step by step. The tools check symbol existence against your codebase graph and confirm acceptance criteria tie back to requirements.
Which hosts support the full specification pipeline?
Claude Code is currently the only packaged host able to execute the complete 20-step orchestration pipeline. Other environments like Codex, Cursor, and Zed run the deterministic verification checks.
