"Creating a Weather Forecast System" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
Search Fragments — two tools for the queries an agent can't place, both built to decline rather than guess. resolve_fragment takes a half-remembered, cross-source query ("a musician who became famous for stopping performing") and returns a grounded answer, ranked web sources to confirm by eye, or an explicit no-resolution. verify_claim takes a specific factual assertion and returns supported, partially_supported, insufficient_evidence, or unsupported, with cited evidence and a stated_limits field that is always present. There is no confidence score — insufficient_evidence fires freely, and unsupported requires a source that explicitly contradicts, never mere absence of confirmation. Every verdict is decide-by-eye: "supported" means current web sources confirm it, not that the claim is true. Calibrated against 18 known claims before release. Free, no signup. Streamable HTTP (MCP 2025-11-25). Read-only.
Search 250,000+ reported Pakistani judgments by keyword, citation or legal question, and trace which later cases follow or cite them Pakistan Case Law gives Claude direct access to more than 250,000 reported judgments of the Federal Constitutional Court, Supreme Court of Pakistan, the Federal Shariat Court, the High Courts and tribunals, from 1970 to the present, with new judgments added daily. Instead of answering from memory and risking hallucinated citations, Claude searches the real corpus and cites what it finds. Every result carries its law-report citation (PLD, SCMR, CLC, YLR, MLD, PCrLJ, PLC, PTD and others) and a link to the full judgment, so each answer can be checked against the source.
Read-only discovery and bounded access to a finite market briefing with evidence boundaries.
Engram is a persistent, long-term memory layer for AI agents and assistants. Claude, ChatGPT, Grok, Cursor and any MCP client share one memory, stored as plain markdown notes: your knowledge base, second brain and AI context in one place. No extraction step: the memory is the note itself, so you can read exactly what your AI remembers and fix it. Edit your memory in Obsidian (real-time sync), the web app, or on your phone. Hybrid keyword + semantic search (RAG over your notes) finds exact strings like error messages, config keys and IDs. Remote MCP server over Streamable HTTP with OAuth 2.1; notes encrypted at rest. Https://engram.page https://youtu.be/rwnPeZ-8Lqo?is=NI-N7BduydGAiZlF https://github.com/engram-app/Engram
Search over 1.85 million captioned images using text, a reference image, or both. Upload a JPEG, PNG, or WebP image as base64, or provide a public HTTPS image URL. Find similar images from a Lightdrift asset ID and retrieve hosted file URLs, source licenses, and attribution. Connect with OAuth or an API key. Searches cost $0.005 ($5 per 1,000); image details are free. Setup: https://docs.lightdrift.ai/guides/images-mcp
Real-time Google Flights fares for agents. Three things people do with this server. Scan for deals: one call takes a date range and a list of destination airports, expands every combination server side, and returns each fare with Google's own low, typical or high verdict. Put live search in your app: flat JSON with a bookable link on every result, and round trips priced as paired legs. Run a 24/7 AI travel agent: add the server, sign in with Google, and schedule it. No ads, no sponsored content. You bring your own RapidAPI key, so every search is billed to your plan and never to anyone else's. Add https://flights.flightpowers.com/mcp , click Sign in, sign in with Google, and paste your RapidAPI key once on the page that opens. Scripts and clients without a sign-in button send the key as x-rapidapi-key on the same URL.
Honest SEO, AEO and GEO auditing. Audits a page, crawls a site, and checks whether GPTBot, ClaudeBot and Google-Extended can reach your URL — by fetching it as each crawler. OAuth on crawlwise.site; Pro+ API key optional.
A fast, secure, and LLM-friendly Model Context Protocol (MCP) server that scrapes job listings from major platforms (LinkedIn, Indeed, Google) and converts them into structured Markdown format.
A second opinion before your agent acts on one model's unearned confidence. One question goes to 3-4 different AI models that answer independently, then a chair returns a single verdict with a confidence score, the consensus and the dissent that held. A grounded tier buys evidence first (honeypot simulation, OFAC sanctions screen, page content, SEC profile, web results) and itemises what it spent. Pay-per-call with x402 in USDC on Base: no account, no API key, one free call a day.
Search domain availability and pricing, and check if a domain can transfer in, from chat.
Collective memory and evidence-backed trust for AI agents. Search reusable knowledge with search_memories, then inspect_memory to review provenance, reported outcomes and limitations before applying it. Discover public agents and inspect Trust Passports. Public reads require no account or credentials. This Streamable HTTP connector exposes public discovery and existing Candy sandbox tools; Candy participation uses a temporary bearer token and grants no canonical reputation or verified identity. Persistent Agent contributions use a separate authenticated connection described at https://remnant.dedale-bi.com/connect. Remote MCP: https://remnant.dedale-bi.com/mcp. Documentation: https://remnant.dedale-bi.com/connect. Examples: https://github.com/Dedale-Project/remnant-connect. Evidence and cryptographic integrity do not guarantee truth or safety. Bootstrap memories are operator-published, not independently validated.
Check that a package, module or DOI exists before an agent installs, imports or cites it.
Web scraping for agents. Point it at a URL and it returns the page as clean markdown, JavaScript-rendered pages included. Point it at a site and it maps the URLs or crawls the section you need in the background, a few pages at a time so results fit in the conversation. Search the web and read full pages, extract fields with a JSON schema you define (validated, never invented), read a store's catalogue or a blog's posts from the platform's own feed, and check whether a page has changed. Failed requests cost nothing. The free plan includes 1,500 credits a month.
Never let your agent repeat a bug or linger on a known issue. Search 385+ failure lessons to skip known errors instantly.
Supericons lets AI coding agents search, recommend, and retrieve SVG icons from a semantic registry of 20,000+ free icons.
Search and compare 26,000+ UK electronics products across multiple retailers including AO. Get real-time prices, stock availability, and price comparison across retailers in a single search. Covers laptops, phones, tablets, headphones, TVs, monitors, cameras, gaming, and more.
Hosted LinkedIn MCP server that connects your own LinkedIn account to Claude, ChatGPT, Cursor, n8n and any MCP client. 33 tools: people and Sales Navigator search, profiles, companies, jobs, inbox, posts, invites, email and phone finding. Free 7-day trial, no card (connecting your own LinkedIn account needs a paid plan). Starter $19/month, Pro $49/month, Max $199/month. $10 top-ups.
Find what slows your website down. Run a free check in Claude Code, Cursor or ChatGPT. No account needed to try it. Save your result with a free Nimo account, then check again after your fixes. No card needed. Learn more: https://heynimo.com/for/coding-assistants
A connector providing AI assistants searchable access to climate-aligned contract clauses, glossary terms, and practical guides from The Chancery Lane Project's curated knowledge graph.
Check how much real depth Armasourcing's vetted Filipino virtual assistant pool has for a specific role, skills and timezone, and understand how hiring and engagement work. Returns aggregate pool statistics only, no candidate names, no profiles, and no pricing, and ends in a free discovery call booking.
