MCP Server Directory

Sitelas com.sitelas/sitelas

Build a real website from a chat — then run it: read messages, check traffic, publish changes.

Run AI-generated code safely. gVisor-isolated Python/JS sandboxes for any MCP client. Pay per run.

WebhookTest.net net.webhooktest/webhook-tester

Anonymous webhook capture, inspection, waiting, and response configuration for AI agents.

BYOK, fully local AI agent that tests your app/API and writes a real Playwright spec on success.

Generate OpenAPI 3.1 specs, endpoint docs, TypeScript SDKs, and test suites from code

Umlout io.github.dmkorj/umlout

Build Umlout projects: objects with types and fields, relations, and boards that draw them.

Streamkap com.streamkap/tools

Streamkap CLI & MCP server - manage CDC pipelines, sources, destinations, and transforms

ScoreIA Open Chamber ai.scoreia/bench

Test your AI agent over MCP in the Open Chamber: a timed public trial with signed cards.

Pay-per-call developer utilities and npm supply-chain security tools for coding agents, over x402.

MCP server giving AI agents eyes on OpenImageDebugger buffers in live gdb/lldb sessions

wavefunction-search io.github.jdhart81/wavefunction-search

Post a goal before you know who can do it; agents sense open work and verified results build trails.

MCPFax Vehicle Diagnostics com.mcpscores/vehicle-fault-codes

A fault code, a VIN, or a recall — answered from public NHTSA and standards data.

AI-friendly, safety-first TestLink MCP server

constitution-lint dev.agentopskit/constitution-lint

Static linter for CLAUDE.md-style agent constitution files: 10 operational-guardrail checks.

Durable, build-scoped reverse-engineering evidence memory and query tools for AI agents.

UpToCode io.github.DDYRich72/uptocode

Evidence-backed architecture-quality analysis for Python agent applications.

emailmd dev.emailmd/emailmd

Render markdown into email-safe HTML, lint drafts for deliverability problems, and preview emails.

LiveVariant io.github.livevariant/livevariant

Build, inspect and read adaptive A/B tests. Config travels in the URL; no account or API key needed.

TextToQuant Backtesting and Quant Research com.texttoquant/texttoquant

Backtest plain-English trading strategies on real market data: graded results, honesty flags.

Structured Windows state for AI agents: processes, windows, UI trees. No screenshots.

MCP server for Sigma Computing. Provision dashboards, build models, and automate cloud analytics.

KnownFix io.github.b-hash88/knownfix

Developer fixes, free skills, browser tools and scoped technical services over MCP.

F1-grade MCP certification. 52 tests, 9 tiers (49 scored + T9 Receipt validation). Ecosystem: #2759

Local, read-only structural code navigation and bounded dependency analysis for source repositories.