"Using Cursor to Handle Documentation During a Commit" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
Location tools for Claude and other MCP clients, strongest in the US and Great Britain. Geocode whole lists with a confidence score per row, filter by distance, get road distances and drive-time areas, and plan multi-driver routes with Google Maps links. Check flood zones, crime and live warnings, find nearby places and UK registers (NHS, CQC, food hygiene), and keep shareable maps. Reads and writes Google Sheets. Free: sign in with Google.
fivebar’s MCP server lets Claude, ChatGPT, Cursor and other MCP clients read your cookieless, privacy-friendly web analytics and explain what changed, where traffic and signups came from, and which pages are slow. It can also install and verify the tracking tag from your coding agent, and connects with OAuth, read-only by default, with no API key needed.
Create and manage online surveys and analyze responses from Claude, ChatGPT, Cursor and other MCP clients. Connect your QUESTIONSTAR account via OAuth. Supports survey design, response collection, statistical analysis and reporting. Hosted in Germany. Free plan: all survey features, one active survey, up to 50 responses per survey. Interface: English, German and Russian; surveys in any language. Docs: https://questionstar.com/help/integrations/mcp-ai/
MappaIQ is the first open marketplace for commercial real estate listings with an MCP connector, letting brokers and buyers search live CRE listings from Claude or ChatGPT. Brokers drop in a spreadsheet and get a live, shareable map with parcel data — free to start at mappaiq.com.
Query your databases and build dashboards, Streamlit apps and reports your team logs in to.
Reliable datasets from the unreliable web Tell Jsonify the data you need in plain words. Jason, its AI data engineer, picks the sources, builds the pipeline and checks every row. The dataset then arrives on schedule from websites and mobile apps, with the source page behind every value. When a site changes and a run breaks, Jason repairs the pipeline. You pay per row, and the first 100 rows a month are free. Collect web data, manage pipelines, query datasets, and explore dashboards with Jsonify. Connect using OAuth. Website: https://jsonify.com/?ref=glama Documentation: https://www.jsonify.com/docs/ Authentication: https://factory.jsonify.com/auth.md
Turn your data into map images of countries, states, counties and ZIP codes with Ultimaps MCP server. Each map comes with a link to Ultimaps Studio, where you can keep editing it, export it, or publish an interactive version. No account needed: 30 maps per hour, PNG up to 1600px, with Ultimaps attribution.
Connect your ads, shop, analytics, social, CRM and finance platforms once, then let Claude, ChatGPT, Cursor or any MCP client read, join and explain your numbers. Public statistics from the World Bank, IMF, Eurostat, OECD, WHO and SEC filings come as context, searchable and chartable from the same tools. Read-only by design, every number carries its source.
Option analytics over the SYNTH sample or a permitted chain: Greeks, positioning, payoffs, plots.
Email Engagement Report turns a raw email event export into a per-recipient engagement report.
Publish complete HTML artifacts and return a public share URL.
Anthropic's SDK went from 34% to 97% of the OpenAI SDK's weekly npm downloads in 46 weeks. It.
The gap between Arena's #1 and #10 models fell from 148 points in Feb 2024 to 18. #10 now wins.
OpenAI's headline model fell from $30 to $2 per million input tokens since Jun 2023: 93% in.
The Vercel AI SDK fell from 31 to 23 weekly downloads per 100 downloads of the OpenAI,.
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.
14 labs launched 50 named AI models from 6 Jul 2026 to 27 Sept 2026. Alibaba's Qwen team led.
Of 13 model launches from 23 Sept 2026 to 3 Oct 2026, 9 opened an API on day one, 7 of them.
The best open model trails the best closed model by 42 Arena points. In a blind vote it would.
