"Automated App for Improvement, Auditing, Feature Management, and Planning" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
Connect AI agents to your AI visibility and SEO data: competitors, citations, GSC, GA4, Bing.
The free 9-part video course, Explore The Coin Daily Research, walks through setup and the full workflow — charts, comparisons, news and using the tools in ChatGPT or Claude: https://www.youtube.com/playlist?list=PLKY7CRxbV8Fc Ask your assistant for a chart and it arrives in the conversation — scrub Bitcoin's week, set an A-to-B range, and see the move in numbers. Pull funding, open interest, liquidations and order-book depth. Catch hourly regime shifts. Compare whole sectors, like DeFi against AI tokens. Follow source-linked news and ticker video coverage, or read the latest published Market Update with its chapters. Every figure is grounded in The Coin Daily's own research pipeline: widgets render exactly what was read, missing readings stay visible gaps, and nothing is invented. Editorial market commentary — not investment advice. No trading, wallets or payments, ever. Sign in with OAuth.
Spend USDC in the real world: prepaid cards, gift cards, push-to-card, and bank payouts.
Pay-per-use APIs for agents: web research, data lookups, and metered endpoints billed to credits.
Operated by SpendPreflight: sanctions screening and allow/hold/block preflight for x402 payments.
Check any x402 endpoint before your AI agent pays it: trust grade, verdict, and hijack checks.
# Glama connector Description (paste into Admin → Listing → Description) MeshArc turns any website into clean markdown your assistant can read, and keeps a record of what changed on it. Read one page or 500. Map every URL a site declares in its sitemaps without fetching a page. Crawl a whole site, or one section with path globs like /blog/*. Or make it a watched project on a schedule and ask "what changed?" to get the pages added, modified and removed, with field-level diffs. Each page climbs a fetch ladder (plain request, real browser, then stealth and residential exits) only as far as it needs. A page the site refuses comes back marked as blocked and costs nothing, and so does a 404. Browser steps (click "Load more" until it is gone, type, select), structured extraction with a JSON schema, and reading PDF, Word and spreadsheet files are built in. Add it by URL (https://mcp.mesharc.dev/mcp): sign in to mesharc.dev and approve, with nothing to install. The connection is read-only unless you allow changes. Or run it locally with pip install "mesharc[mcp]". The free plan includes 1,000 credits with no card, and a plain fetch costs 1 credit. --- # Long overview (for a README-style page; see the note in chat) # MeshArc MCP Server Turn any website into clean markdown your assistant can read, and keep a record of what changed on it. MeshArc gives Claude, Cursor and any MCP client 15 tools to read pages, map and crawl sites, watch a site over time and ask what changed, all in plain English. Add it by URL, with nothing to install. ## What can you do with this server? - **Read any page as clean markdown.** Pass one URL or up to 500. Navigation, cookie banners and boilerplate are stripped. PDF, Word and spreadsheet links are read as text. - **Get past walled sites.** Each page climbs a fetch ladder: a plain request first, then a real browser, then stealth and residential exits only when the page needs them. You pay for the rung that worked. A page the site refuses comes back marked as blocked, and costs nothing. - **Map a site before you fetch it.** Every URL a site declares in its sitemaps, with its sections, without fetching a single page. - **Crawl a whole site or one section.** Use path globs such as `/blog/*`, with a page limit and a depth. You get an index of every page plus readable excerpts, sized to fit a chat turn. - **Watch a site over time.** Make it a project, put it on a schedule, and ask "what changed?". You get pages added, modified and removed, and field-level changes. Removals are held back when a run reached too little of the site, so a blocked crawl never reports a site as gone. - **Run browser steps.** Click "Load more" until it disappears, type into a search box, pick an option, then read the page. - **Extract structured fields.** Give a JSON schema and get the same fields from every page. ## How do I use the MeshArc MCP Server? 1. Add `https://mcp.mesharc.dev/mcp` to your MCP client as a remote server. 2. Sign in to mesharc.dev when the client opens the browser, and approve the connection. Choose read-only, or tick write access to let the assistant fetch pages and change projects. 3. Ask in your own words. The assistant picks the tool, fills in the arguments and reads the answer. ## What you need - An MCP client that speaks remote MCP (Claude.ai, Claude Desktop, Claude Code, Cursor, VS Code, Windsurf…), or Python 3.10+ to run the server locally. - A MeshArc account. The free plan gives 1,000 credits once, with no card. ## Quick start **Hosted (recommended).** Nothing to install, and no key to copy: you sign in and approve once. Claude.ai: Settings → Connectors → Add custom connector → `https://mcp.mesharc.dev/mcp` Claude Code: ```bash claude mcp add --transport http mesharc https://mcp.mesharc.dev/mcp ``` Cursor, Windsurf and other clients (`mcp.json`): ```json { "mcpServers": { "mesharc": { "url": "https://mcp.mesharc.dev/mcp" } } } ``` **Local (stdio), with your own API key.** Make a key under Settings → API keys on mesharc.dev. ```bash pip install "mesharc[mcp]" claude mcp add mesharc -e MESHARC_API_KEY=mesharc_... -- mesharc-mcp ``` Claude Desktop or Cursor: ```json { "mcpServers": { "mesharc": { "command": "mesharc-mcp", "env": { "MESHARC_API_KEY": "mesharc_..." } } } } ``` | Variable | Meaning | |---|---| | `MESHARC_API_KEY` | Your API key (local mode only; the hosted server never reads one). | ## Example prompts These conversations were run against real sites; the results are the real ones. - "Get Linear's pricing page and list every tier and price." The assistant used `scrape_urls`: 1 credit and 4 seconds for the four tiers. - "How many pages does the FastAPI docs site have, and which are about security?" The assistant used `map_site`: 151 URLs declared, 9 under /tutorial/security/, with no page fetched. - "Set up a project for hotspotseo.com that only scrapes the blog, weekly." The assistant used `get_project`, `map_site` and `create_project`. It found the blog under /blogs/, not /blog/, and the first run read only blog pages. - "Make it daily instead, and skip the tag and author pages." The assistant used `update_project`; the include setting stayed as it was. - "Re-check the home page and page 2 now. What changed?" The assistant used `start_run` with the two URLs, then `get_changes`. - "Read this arXiv paper (a PDF) and summarise the method." The assistant used `scrape_urls`: 6,036 words of text for 2 credits. - "Which of these pages mention GDPR?" The assistant used `list_pages` with a search, on the stored crawl, at no credit cost. ## Tools **Read the web** | Tool | What it does | Credits | |---|---|---| | `scrape_urls` | Content of 1 to 500 known URLs. `full=true` reads one URL with every format: raw html, head and extracted fields, images, and browser steps run first. | per page | | `map_site` | Every URL a site declares in its sitemaps, with its sections, without fetching a page. | 1 per sitemap file | | `crawl_site` | Crawl a site or a section once, with page limit, depth and path globs. You get an index plus excerpts. | per page | **Watch a site over time** | Tool | What it does | Credits | |---|---|---| | `list_projects` | The workspace's projects, with status and last run. | none | | `get_project` | One project's settings and state. With no id, every setting an assistant can set, with its meaning and default. | none | | `create_project` | A watched project from a URL, or from a `crawl_site` crawl with nothing fetched again. | none | | `update_project` | Change the name, schedule or settings. Only the keys you give change. | none | | `delete_project` | Delete a project and its history once its name is repeated back. Needs an admin API key, so it works locally only. | none | | `start_run` | Crawl a project now, or only the pages listed. You can wait for it to finish. | per page | | `list_runs` | A project's runs, newest first. | none | | `list_pages` | A run's pages, or with `q` a search of them: words, a quoted phrase, or a CSS selector. | none | | `get_page` | One stored page in full, with its versions across runs. | none | | `get_changes` | Pages added, modified and removed since the run before, with field changes. | none | **Long jobs** | Tool | What it does | Credits | |---|---|---| | `get_job` | Follow a crawl, run or batch that came back as a job, and get its result. | none | | `cancel_job` | Stop a crawl, run or batch that is still going. Pages already read stay. | none | Every tool has an output schema. Read-only tools are marked read-only, and the three that overwrite, stop or delete are marked destructive. ## Errors and failure paths - **Blocked is not missing.** A page the site refuses is reported as `blocked` (or `captcha`, `timeout`, `missing` for a 404 or 410), never as an empty page, and none of them is charged. - **Read-only connections:** any tool that fetches or changes something answers `code: read_only`, with how to reconnect with write access. - **Long work:** a crawl, run or batch that outlasts the connection's time limit comes back as a job. `get_job` picks it up, and calling the original tool again returns the same job rather than starting a second one. - **Out of credits:** `402`. A run that uses up the budget stops and keeps what it read. - **A run already going:** `start_run` answers `409`; `list_runs` shows it and `cancel_job` stops it. - **Plan limits:** `create_project` answers `plan_limit` when the plan's project count is full; values above a plan's caps are lowered to them. - **Settings:** an unknown config key is refused by name, never silently dropped. - **Size:** a many-page answer is an index plus excerpts inside 60,000 characters; any one page comes back whole (each body up to 12,000 characters) on request. ## Pricing, free tier and limits - **Free:** 1,000 credits once, with no card. 2 projects, 500 pages per run, and 7-day retention. - **Paid plans:** Starter $29/mo (100,000 credits), Growth $99/mo (500,000 credits, stealth tier), Scale $349/mo (2,500,000 credits), and Enterprise. - **A credit:** a plain fetch costs 1, a fetch with a site's session 2, a real Chrome 4, a residential address 16, a solved widget 22. - **Free of charge:** a refused page, a 404 or 410, a cached page, change detection, sitemaps, search, and listing and reading what is stored. - The MCP server itself costs nothing extra. A tool call is an ordinary request through your account, with the same credits, limits and rate. ## Tool selection - You have the URLs → `scrape_urls`. You need to find them → `map_site` (cheap, declared URLs only) or `crawl_site` (follows links). - One page with clicks, structured fields or every format → `scrape_urls` with `full=true`. - You want to know what changes over time → `create_project`, then `start_run` and `get_changes`. - You want to read what was already crawled, at no cost → `list_pages`, `get_page`, `get_changes`. ## How it compares | | Firecrawl | MeshArc | |---|---|---| | Blocked or error response billed | Yes | No | | 404 billed | Yes | No | | Cheaper repeat reads of protected sites | No | Yes, session reuse at 2 credits | | Website change monitoring | Yes (Monitor) | Yes, with sitemap sections and held-back removals | | Web search API | Yes | No | | Autonomous agent / browser interaction | Yes | Browser steps only | | Open source | Yes | No | Checked against public documentation and pricing pages. If you need web search or an autonomous research agent, Firecrawl is the stronger fit. ## FAQ **Does the assistant see my API key?** No. Hosted, you approve the app and MeshArc issues it a key of its own, which you can see and revoke under Settings → API keys. Run locally, the key stays in the server's environment on your machine. **Can it read pages behind a login?** No. It reads what a visitor can see. A login wall comes back as blocked, at no cost. **Does it respect robots.txt?** Yes, by default (`respect_robots`). **Can it change my projects?** Only with write access. Deleting a project also needs an admin API key, which a connected app never holds. **Which clients work?** Any client that speaks remote MCP over streamable HTTP, or any client that runs a stdio server (`mesharc-mcp`). ## Links - Website: https://mesharc.dev - MCP page and setup per client: https://mesharc.dev/mcp - Documentation: https://mesharc.dev/docs - Python SDK and MCP server: https://github.com/mesharc-org/mesharc-python · https://pypi.org/project/mesharc/ - Node SDK: https://github.com/mesharc-org/mesharc-node - Privacy: https://mesharc.dev/legal/privacy - Support: hello@mesharc.dev ## License The SDK and MCP server are MIT licensed.
Search, filter, count and sum Australian government open data, with every version kept.
Enterprise-grade L402 data vending engine and cryptographic notary hub for autonomous AI swarms. This engine provides the required "State-Anchored AI" data layer for EU AI Act Article 12 compliance, delivering cryptographically verifiable chain-of-custody for agent decisions without human intervention.
Credit card payoff, mortgages, refinancing, 401(k), rent vs buy. Every rule and default is cited.
Go MCP server for GitLab: 2 dynamic tools reach 1000+ REST/GraphQL actions. Free/CE, no paid tier.
Generate and validate Factur-X, CII & UBL invoices. Free demo; EUR 3 evaluation, no subscription.
Bring saved project decisions, preferences and goals into your next AI task. Configure keeps user-chosen context in a persistent, searchable profile with OAuth, explicit saves and user-provided imports.
Uzbek football news from gol24.uz: transfers, quotes, results, club and player news.
Traffic Parrot simulates APIs and messaging. Request or withdraw a trial, read docs, send feedback.
Plan, compare, price, generate, and recover AI video from compatible MCP clients.
teas.co.uk is an independent UK shop with more than 600 teas, coffees and hot chocolates from 60 brands. This connector searches the live catalogue in plain words, such as a strong breakfast tea or something caffeine free for bedtime, with filters for type, caffeine, milk, time of day, strength, pack size, price per cup and organic, Fairtrade or vegan labels, and shows live prices and stock. Open any product for tasting notes, a brewing guide and recipe ideas, or compare up to four side by side. Build a basket and get a secure checkout link: payment always happens on teas.co.uk, never in the chat, and the connector cannot place an order. Customers who link their teas.co.uk account (OAuth) can see orders and courier tracking, buy again, manage repeat deliveries, check reward points and start a return. teas.co.uk delivers to the UK, the Channel Islands, the Isle of Man and many European countries; prices are in pounds including VAT.
Get date-specific quotes and book private UK airport and cruise-port transfers through your AI assistant. Compare vehicle options, validate flights, retrieve bookings, amend details and cancel with customer confirmation. No registration required to start, subject to service limits; optional API-key and OAuth access for registered integrations. Transfer fares are payable separately and cancellation conditions apply. Live demo and connection instructions: https://ai.airport-pickups-london.com/ Technical documentation: https://mcp.airport-pickups-london.com/docs
Paid web research, fact-check, page summary and page extraction tools for AI agents. Pay per call in USDC with x402 (Base or Solana). A failed call is not charged.
Read-only discovery for 425 Malaysian public datasets with freshness, licence, and provenance.
