{"id":"mcp-server-spec-driven-development","name":"Spec-Driven Development MCP Server","homepage":"https://github.com/formulahendry/mcp-server-spec-driven-development","repo_url":"https://github.com/formulahendry/mcp-server-spec-driven-development","category":"developer-tools","subcategories":["workflow","code-generation","documentation"],"tags":["spec-driven","requirements","design","code-generation","typescript","workflow","EARS"],"what_it_does":"Provides structured MCP prompts that guide AI agents through a three-stage spec-driven development workflow: generating EARS-format requirements, deriving design documents, and producing implementation code from those specs.","use_cases":["Enforcing a requirements-first discipline when using AI for greenfield feature development","Generating traceable specs/requirements.md and specs/design.md artifacts before writing code","Teams wanting to reduce 'vibe coding' and maintain documentation that outlives a single AI session"],"not_for":["Rapid prototyping or exploratory coding where upfront specs add friction","Existing codebases that do not benefit from EARS-formatted requirements","Workflows where the LLM client does not support MCP prompt invocation"],"best_when":"You are starting a new feature or project and want the AI to produce auditable requirements and design artifacts before touching implementation code.","avoid_when":"You need fast iteration or your team does not have a culture of maintaining spec documents; the structured overhead will slow you down.","alternatives":["mcp-shrimp-task-manager","aider","github-copilot-workspace"],"af_score":75.5,"security_score":80.0,"reliability_score":null,"package_type":"mcp_server","discovery_source":["github","npm"],"priority":"low","status":"evaluated","version_evaluated":"latest","last_evaluated":"2026-03-01T09:50:05.906053+00:00","performance":{"latency_p50_ms":null,"latency_p99_ms":null,"uptime_sla_percent":null,"rate_limits":null,"data_source":"llm_estimated","measured_on":null}}