Claude MarketplacesSubmit
lazymac2x avatar

Ai Eval

lazymac2x/ai-eval-api

A lightweight evaluation server running on Cloudflare Workers that exposes MCP over both REST and JSON-RPC 2.0. The implementation uses streamable HTTP transport, making it accessible from any MCP client that supports remote connections. You'd reach for this when you need to integrate AI evaluation capabilities into your workflow without managing infrastructure, since it's already deployed and accessible at api.lazy-mac.com/ai-eval. The dual protocol support means you can call it from traditional HTTP clients or connect it directly through MCP. Documentation is minimal, so expect to explore the available tools and prompts through your MCP client's discovery features.

tools
3
transport
HTTP
last updated
May 16, 2026
View on GitHub

Install

From registry metadata
$ npx add-mcp https://api.lazy-mac.com/ai-eval/mcp --name ai-eval

Run in your terminal. add-mcp asks which agents to add it to (Claude Code, Codex, Cursor and more). Add -g to install it for every project.

Review the command, arguments and environment values before installing. MCP servers run with your local permissions.

Other ways

Claude Code

$ claude mcp add --transport http ai-eval https://api.lazy-mac.com/ai-eval/mcp

Run in your terminal. Add --scope user to make it available in every project.

Tools

Verified live · 3 tools

Verified live against the running server on Nov 6, 2026.

score_responseScore an AI response against a prompt using heuristic metrics (length, relevance, structure, completeness)3 params

Score an AI response against a prompt using heuristic metrics (length, relevance, structure, completeness)

Parameters* required
criteriaarray
Optional keywords that should appear in response
prompt*string
The original prompt/question
response*string
The AI response to evaluate
compare_responsesCompare and rank multiple AI responses to the same prompt2 params

Compare and rank multiple AI responses to the same prompt

Parameters* required
prompt*string
responses*array
text_metricsGet text quality metrics: word count, sentence count, estimated tokens, readability grade1 params

Get text quality metrics: word count, sentence count, estimated tokens, readability grade

Parameters* required
text*string

Sponsors

Promote your product hereReach 125k+ visitors monthlyPromote your product hereReach 125k+ visitors monthlyAgent CaffeineSponsoredClose your lid, come back to finished workSnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthlyWaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthlyknobsSponsoredSee your site on any phone, any day, in any language

Readme

ai-eval-api

Cloudflare Workers MCP server: ai-eval. REST + MCP (JSON-RPC 2.0). Live: api.lazy-mac.com/ai-eval

Details

Repository
github.com/lazymac2x/ai-eval-api
Category
Cloud & Infrastructure
Transport
HTTP
Registry
MCP registry, active
Tools verified
Nov 6, 2026

More from lazymac2x

Related Cloud & Infrastructure MCP servers

View all
1lazymac2x avatarAi Token Counterlazymac2x/ai-token-counter-apiCloudflare Workers MCP server: ai-token-counter0stars
2lazymac2x avatarApi Mock Serverlazymac2x/api-mock-server-apiCloudflare Workers MCP server: api-mock-server0stars
3lazymac2x avatarApi Perf Analyzerlazymac2x/api-perf-analyzer-apiCloudflare Workers MCP server: api-perf-analyzer0stars
4lazymac2x avatarCron Collision Detectorlazymac2x/cron-collision-detector-apiCloudflare Workers MCP server: cron-collision-detector0stars
5lazymac2x avatarSmart Data Extractorlazymac2x/smart-data-extractor-workersmart-data-extractor MCP server on Cloudflare Workers · REST + MCP JSON-RPC · free tier0stars
6pipeworx-io avatarStudio Ghiblipipeworx-io/mcp-studio-ghibliStudio Ghibli MCP — fan API. Auth: none. Docs: https://ghibliapi.vercel.app0stars