Search server records by name, category and declared transport. Update timestamps describe registry freshness, not tested functionality. Consult each publisher for current connection details and requirements.
Search and filter the complete saved snapshot
Snapshot 2026-11-06T19:40:01.441438+00:00 · 57,752 saved records · page 169 of 482. Latest-version cursor traversal completed; registry-deleted records are excluded from search. Availability and safety are not independently verified.
robots.txt tester (RFC 9309), AI crawler access (GPTBot, ClaudeBot...) and sitemap check.
NYSE, Federal Reserve, TARGET2 and UK business days, holidays and T+N settlement dates.
SPF, DKIM, DMARC, MTA-STS and domain-expiry checks for any domain, with SPF lookup counts.
Mubboo Flights: all-in-one travel comparison and tickets platform. MCP tools for flight search.
Webhook alerts for EVM wallets, contract admin changes, Safe queues and custom events.
Wallet trust scores for AI agents. Stellar, XRPL, EVM 81+ chains. OFAC sanctions. x402 payments.
Search and read Protoperfect Labs research, documentation and glossary. Read-only.
AI character videos from one line: returns a link the user taps. First video free, no account.
Compare AI perspectives with configurable Modes, estimate deliberations, and retrieve run receipts.
Inspect Kairon VMs, network policy and VM-edge flows from an agent. Read-only by default.
Authorized security scans, evidence, fix prompts and retests for AI-built web apps.
Accountability partner in your agent: one yearly aim, one main step a day, a timer your agent runs.
Free, account-free agent messaging with signed sessions, AEAD, and replay protection.
Deterministic social-caption API: hooks, bodies, CTAs + hashtags as JSON. No LLM in the loop.
Smart-contract risk reports for AI agents on 20 EVM chains, paid per call via x402 ($0.02 USDC).
Apple developer docs, Human Interface Guidelines and 1,700 WWDC sessions with code for AI assistants
Self-hosted MCP gateway and LLM proxy: OAuth 2.1, model aliases, Grok subscription as an API.
VMware/Omnissa Horizon VDI ops: pools, sessions, machines, images — 27 MCP tools.
x402 web/data toolkit: tools, US$5 lead pack, free flapjax_check, paid Nostr relay
Psychological risk assessments (GBU Psyche) via Safe Mind: surveys, departments, analytics.
Read-only XRP Ledger token-risk, issuer-authenticity and wallet-security checks.
SEO and GEO audit: check if a site can be read and cited by Google, ChatGPT, Perplexity and Claude.
Checks agent-written Python against your repo: duplicate helpers, error handling, security.
VMware NSX security: DFW policies and exclusions, groups, tags, Traceflow, IDPS — 22 MCP tools.
VMware NSX networking management with 33 MCP tools: segments, gateways, NAT, routing, IPAM.
Search institutional series-b venture capital firms, partner profiles, and valuation.
Search institutional series-a venture capital firms, partner profiles, and valuation.
Search institutional seed venture capital firms, partner profiles, and valuation benchmarks on.
Search institutional pre-seed venture capital firms, partner profiles, and valuation.
claude-opus-4-6-high leads Arena coding at 1535. Anthropic has held #1 for 280 days, but Z.ai.
Arena rates 399 text models from 52 labs, up from 10 models in May 2023. Yet only 5 labs hold.
Anthropic holds 8 of the Arena top 20, Google 7 and OpenAI 0. In Apr 2025 OpenAI held 9 and.
On 11 Sept 2026, Claude's best model rates 40 points above OpenAI's and 16 above Gemini's..
qwen3.8-max trails claude-fable-5.1-max by 27 points. Over the past year the gap has stayed.
The gap between Arena's #1 and #10 models fell from 148 points in Feb 2024 to 18. #10 now wins.
14 models are statistically tied for #1 in Arena math, spanning 49 points. 4 are Flash models.
Anthropic has 7 of the top 10 creative writing models and Google 3. Meta's muse-spark-1.2.
claude-opus-4-5-20251101-high-32k is #49 overall but #14 in coding. gpt-5.6-terra-xhigh is #52.
Anthropic's SDK went from 34% to 97% of the OpenAI SDK's weekly npm downloads in 46 weeks. It.
The Vercel AI SDK fell from 31 to 23 weekly downloads per 100 downloads of the OpenAI,.
The MCP SDK had 52.3M npm downloads in the week of 24 Aug, 1.3× the OpenAI SDK and more than.
LangChain's share of weekly npm framework downloads fell from 32% to 19% in 46 weeks, while.
On npm, Ollama's client fell from 27 to 6.6 downloads per 1,000 cloud lab SDK downloads in 46.
86% of surveyed Claude users say AI makes them faster and 82% say it widens what they can do..
ChatGPT reports 900M weekly users (Feb 2026). Gemini reports 950M monthly (Jul 2026), 2.4× its.
OpenAI's models hold 17.9% of all 12.3M Arena votes and none of the top 20 seats. Anthropic's.
54.8% of Americans aged 18–64 used generative AI outside work in Q2 2026, up from 36.0% in Q3.
14 labs launched 50 named AI models from 6 Jul 2026 to 27 Sept 2026. Alibaba's Qwen team led.
Of 51 named model launches since 6 Jul 2026, 22 stated their weights: 18 closed, 4 open. All.
OpenAI was the #1 lab on Arena for 95% of 2024. On 25 Sept 2026 it ranks 8th among labs, and.
Since Jan 2024, Google's models have been #1 on Arena for 227 of 1003 days, third among labs.
Audio and speech made 11 of 59 named model launches since 6 Jul 2026, from 6 labs. In the.
Between 31 Aug–6 Sep and 25 Sep–1 Oct, anthropic's PyPI downloads grew 25% and openai's 14%,.
Of 13 model launches from 23 Sept 2026 to 3 Oct 2026, 9 opened an API on day one, 7 of them.
Since Jan 2025, Arena's #1 spot has changed hands 16 times. Half of the finished reigns lasted.
Anthropic builds 14 of the Arena's top 50 models and OpenAI builds 5. But 44% of US adults use.
The best open model trails the best closed model by 42 Arena points. In a blind vote it would.
OpenAI's headline model fell from $30 to $2 per million input tokens since Jun 2023: 93% in.
23.8% of US firms used AI in the latest two-week survey, up from 17.3% 10 months earlier..
66% of developers use AI coding assistants, but only 48% trust AI output they can validate, a.
Among US employees who use AI, 63% say it makes them faster but only 46% say it raises.
Qwen3.8-Max rates within 30 Arena points of Claude Opus 5.5 for 3.3× less per output token..
Google holds #1 in 6 of 8 Arena categories; Anthropic in 2. OpenAI has no category in the top.
Google leads the Arena again; Anthropic trails by 22 points and OpenAI by 62. Query full.
Open weights briefly beat every proprietary model in early 2025 (deepseek-r1); today the best.
61% of Americans aged 18–29 use ChatGPT; Claude reaches 6% of all adults. Query full empirical.
The top 10% of pre-seed AI startups command 3.4x higher valuations ($28.0M vs $8.2M) than.
Validate emails (MX, disposable, role, typo) and phone numbers, singly or in batches, for AI agents.
MCP server for the Zabbix API — daily brief, problems, hosts, items
Proxy-rotated web scraping and cross-platform intelligence for AI agents.
Policy decision point for agent payments — allow, ask, or veto before signing
Query empirical frontier LLM release velocity, inference token deflation, and enterprise AI spend.
Evaluate startup distribution moat defensibility (Tier 1-5) and pre-seed valuation dispersion.
Search and retrieve time-series data across 38 empirical AI adoption and venture research charts.
Search 3,650+ institutional venture capital firms and 13,000+ partners by stage, sector, and HQ.
Query 38 empirical AI market charts, evaluate distribution defensibility, and search 3,650+ VCs.
Cross-platform local-network diagnostics & security-posture MCP server — 31 tools.
Tides, currents, marine forecasts and warnings for paddlers, anglers and small boats, 26 countries.
Can I camp here, and will I have signal? Land status, signal, weather and fires in Canada and the US
Send anything. Get the truth — REAL, SUSPICIOUS or LIKELY SCAM verdicts on messages and links.
SVG Lab MCP: the Design Engine for AI. App screens, icons, illustrations and charts as SVG.
Agentic MCP server for CSI ETABS v22+: model, load, analyse, design and inspect structures.
Draft, schedule and publish social posts to X, LinkedIn, Instagram, TikTok, YouTube and more
AI-to-AI: free risk previews; optional $0.50 MPP receipts; $5 Cropper federal checks.
Send contracts for e-signature, track signing, get signed PDFs and audit trails, verify any PDF.
Live tables, release times and booking odds at hard-to-book restaurants in NYC, SF, LA and Chicago.
Manage uptime monitors and incidents and search logs, metrics and traces from an AI assistant.
Check any x402 endpoint before your AI agent pays it: trust grade, verdict, and hijack checks.
Contact Verify (verify-x402). Basic $0.002, domain $0.02, sender $0.025.
Deterministic JSON hashing and EIP-712 attestations for AI agents via x402.
Owner and APN lookup across 171 verified US county parcel ArcGIS endpoints. No API key needed.
AI-native project and portfolio management platform for PMOs. OAuth + PAT.
Saved TickerTrac theses, retained changes and exact source evidence; owner-reviewed record changes.
Offline market diagnostics, news repetition, data coverage and statistical checks for AI agents.
Find vector artwork and free design generators for laser cutting, engraving and 3D printing.
Domain availability and prices from 40+ registrars, name checks, DNS setup, and a domain broker
Motorsports workspace for vehicles, setups, sessions, logs, maintenance, and race engineering.
Futures trading journal: performance, setups, prop-firm drawdown risk, tagging and screenshots.
Design a KiCad PCB from a prompt: parts, schematic checks, routing, KiCad DRC and Gerbers.
Build LumenJS apps, use the Roxyon BaaS, and deploy apps and web projects to Roxyon infrastructure.
HVAC MCP server — fault codes, model lookup and answers cited to the OEM manual page.
Make micro dramas and anime episodes from an idea, with the same characters in every shot.
Bot-first AU job board: live jobs, verified candidates apply via bots. First 100 employers free.
Verified keyboard shortcuts for Windows, macOS, Linux, ChromeOS and 45+ apps, with sources.
Verify legal citations, check case validity and quotes, and research US law with cited answers.
Check 21,000+ devices with open firmware or protocols before reverse engineering one.
Multi-model debate with named dissent, plus decision provenance queries for AI coding work.
Split songs into vocals, drums, bass, guitar and piano stems, in batches; manage songs and setlists
12 image models (Nano Banana, GPT Image, FLUX…) and 10 tools in chat. No API keys. Pay per image.
Qubic DEX aggregator: best-price quotes across QX and QSwap, order books, candles, trade plans.
Free, no-login forum, wiki and chat for AI bots: share hard-won fixes, peer validation, topic karma.
Pay-on-success win-back for RevenueCat and Stripe apps. Read-only pricing, fit and estimates.
Checks AI support agent refunds against Shopify and Stripe. Read-only pricing, fit and estimates.
Offline, keyless lookup of the US civil aircraft registry — decode N-numbers, search records.
Lightweight coordination layer for multiple AI agents working on the same codebase simultaneously.
Bulk HTTP status checker: up to 100,000 URLs per job, with redirect chains and response times.
Search and fetch ~800K Federal Reserve economic time-series from the FRED API via MCP.
Federal opportunities, awards, agencies and companies from G2X, in any AI agent.
Discord server management MCP for AI agents: chat, moderation, admin, and full server building.
Source-timestamped energy data and reviewed OilPriceAPI product facts for MCP clients.
The MCP Index makes a saved official-registry snapshot searchable. Entries are ordered by recorded registry update date. The catalog does not measure adoption, independently test servers or establish that every entry is open source.
A searchable saved snapshot of server records from the official Model Context Protocol registry. A listing is not a safety, quality, open-source-license or availability certification.
Entries are ordered by the recorded registry update timestamp, newest first. Freshness categories summarize that timestamp; they are not GitHub popularity, adoption or runtime-health measurements.
The saved snapshot date is shown with the catalog. The snapshot is built only after the official latest-version cursor traversal completes. Deleted records are excluded from search and retained historical URLs are labeled. A moving registry is not an atomic census; listings are not independently tested.
Published by Kymata Labs. Explore the related directories at indexes.kymatalabs.com.