Spec Score Mcp
Before you hand Claude a spec to build from, run it through this scoring server. It rates your spec on four axes (completeness, clarity, constraints, specificity) and returns a balance score with a radar chart visualization. The verdict tells you if you're ready to ship or which axis needs work. Three tools: spec_score for analysis, spec_visualize for SVG charts, spec_compare for side-by-side diffs. The insight here is that balance matters more than high scores on individual axes. A spec that's 0.95 on goals but 0.20 on constraints will make Claude improvise features you never asked for. Catch lopsided specs before they become lopsided code.
- GitHub stars
- 2
- tools
- 3
- transport
- STDIO
- last updated
- Feb 28, 2026
Tools
3 toolsPublic tool metadata for what this MCP can expose to an agent.
spec_scoreScores a spec on 4 axes, returns balance score and verdict.
Scores a spec on 4 axes, returns balance score and verdict.
No parameter schema in public metadata yet.
spec_visualizeGenerates an SVG radar chart from scores.
Generates an SVG radar chart from scores.
No parameter schema in public metadata yet.
spec_compareSide-by-side comparison of two scored specs.
Side-by-side comparison of two scored specs.
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageReadme
Spec Score MCP
Score your specs before Claude builds from them.
A balanced spec produces balanced code. An unbalanced spec produces creative fiction.
The problem
When your spec is detailed on some axes but vague on others, Claude doesn't ask for clarification — it fills in the blanks. The result compiles, the tests pass, but it's not what you meant.
This tool catches that before you start building. It scores your spec on 4 axes, tells you which one is weakest, and gives you a concrete tip to fix it.
4 axes
| Axis | Question it answers |
|---|---|
| completeness | Can Claude understand the full scope of what to build? |
| clarity | Is there only one way to interpret this spec? |
| constraints | Does Claude know what NOT to build? |
| specificity | Are there concrete, testable details? |
Each axis scores 0.0 to 1.0. The balance score measures how evenly the 4 axes are covered.
Details
- Repository
- github.com/openpoem/spec-score-mcp
- Category
- AI & LLM Tools
- Package
spec-score-mcp- Transport
- STDIO
- Registry
- MCP registry, active
Related AI & LLM Tools MCP servers
View all
Bolor Brain Mcpphotoxpedia/bolor-brain-mcpCognitive architecture MCP server with memory, learning, and contextual understanding2stars
Hindsight MCPrbfinch/hindsight-mcpMCP server for AI-assisted coding with development history: git, tests, Copilot.2stars
Resemble AIresemble-ai/resemble-mcpResemble AI: deepfake, AI-text, and site agent detection, Detect Agents, intelligence, watermarks.2stars
Power Automate Mcp Serversapientsai/power-automate-mcp-serverInspect, operate, and author Microsoft Power Automate cloud flows from an agent context.2stars
Knowmintsou0327/knowmintAI agent knowledge marketplace. Discover, purchase, and retrieve human expertise via x402 on Solana.2stars
Create Starterstarter-series/create-starterScaffold Starter Series projects and check release, deployment, security, and agent instructions.2stars