Servers by llmlatency

Scanned where there is a package or repository to read, and every release diffed against the tool surface we already hold. Every figure on a card is counted from this marketplace's own rows.

Browse stacks Start publishing

Filters

Verified publishers only Has a free tier No local install needed Answers through mcprush Tools listed Only what I saved 0 Already in one of my lists

Pricing model

Free1

Category

AI & Agents1

Memory & Knowledge0 Developer Tools & Repos0 API Development0 Databases0 Data Science & ML0 Analytics & Monitoring0 Cloud & DevOps0 Security & Testing0 Authentication & Identity0 Web, Search & Scraping0 Browser Automation0 Search0 Files & Storage0 Productivity & Workflow0 Communication & Collaboration0 Email0 Learning & Documentation0 Research0 Content Management0 Design & Media0 Finance & Commerce0 Payments & Billing0 E-commerce0 Sales & CRM0 Marketing, SEO & Social0 Gaming & Entertainment0 Lifestyle & Local0 Other0

Runtime

Remote (hosted)1

Auth

No auth1

Works with

Claude Code1

Claude Desktop1

ChatGPT1

Cursor1

VS Code1

Codex CLI1

Gemini CLI1

Grok Build1

Microsoft Copilot1

Perplexity1

DeepSeek Harness1

Zed1

Devin Desktop1

Windsurf (legacy)1

OpenAI Agents SDK1

HTTP / API1

Minimum rating any

1 MCP server

Scanned where there is a package or repository to read — the grade is on each server's page

AI & AgentsWorks with DeepSeek HarnessBy llmlatency

LLM Latency Tracker

llmlatency·AI & Agents

Measured latency, time to first token and uptime for ~45 AI inference APIs, by region.

2 tools

Free

Compare

tick one more

Side-by-side

mcprush

Find MCP servers and skills for your AI apps. Publish your own tools and reach people who need them.

For customers

MCP Servers
Agent skills
Stacks
Pricing
Trust & scanning

For publishers

Publish a tool
Publisher fees
MCP hosting
Why us?
Developer Guide

Developers

MCP endpoint
CLI reference
Gateway API
Top 50 MCP
Affiliate program

Company

Blog
About
For Investors
Careers
Contact