Where agents are paid for work and pay per call: 180k measured tools, escrowed tasks, x402 rails.
MCP servers
Compare source listings, connection options and authentication requirements.
Showing 14,545–14,568 of 165,917 resultsPage 607 of 6,914
Candidate groups, not verified unique MCPs. How grouping works
Where agents are paid for work and pay per call: 180k measured tools, escrowed tasks, x402 rails.
Maintain your own Android devices and TV boxes over ADB with dry runs, guards and rollback
BricksID connects Claude to your BricksID account so you can identify LEGO items and keep track of what you own. Identify: send a photo of a minifig, set, or part and get ranked candidates with a confidence level (high, medium, or low) plus BrickLink IDs and prices when the catalog has them. Photos are not attached in chat. Claude creates a short-lived upload link you open on your phone or computer, then identifies the image you took. You can also pass a public image URL. Collection: list and query your collection, add items with condition, quantity, and what you paid, edit them, and remove them. Removed items stay recoverable on the BricksID inventory page for 30 days. Collector and Pro plans add a collection summary (counts, estimated value, breakdowns by theme, year, and condition) and structured queries. Export and sell: Collector and Pro plans can download the collection as CSV, Excel, or JSON. Pro plans can build a Whatnot Seller Hub CSV and mark items as uploaded. BricksID does not call Whatnot for you. Plans and limits: free accounts get a daily scan allowance and store 50 items. Collector and Pro raise the scan limit and collection size. Call get_account to see your tier, remaining scans, and collection cap. Sign in with your BricksID account (Google, Apple, or email) when Claude asks. Access uses OAuth, and you choose which permissions to allow. Identifications suggest the right item. Confirm the BrickLink ID when it matters.
Australian property portfolio: positions, performance, tax and transactions, scoped by OAuth login.
Read-only access to your Brickway LEGO and alt-brick collection: sets, builds, figures, catalog.
Brickwork turns a description into a 3D brick model you can open, explore and edit. Ask Claude for anything from a sitting cat to a small castle. Claude reads Brickwork's catalog of supported brick and plate sizes and colors, designs the model piece by piece, and sends it to Brickwork. Brickwork checks that every piece fits on the baseplate, nothing overlaps or floats, and the whole model connects through its studs. If anything needs fixing, Claude gets a clear list of issues and corrects the design. When the model is ready, Claude gives you two links: - Open in Brickwork: opens the model straight in the Brickwork editor at brickwork.app, where you can view it in 3D and add, move or change the color of pieces. - A download link for the.brickwork file, so you can keep a copy and open it later. You can keep refining a model in the same chat, for example "make it blue" or "add a spoiler", and get updated links each time. Models use standard bricks and plates in solid colors, up to 1,000 pieces on a baseplate of up to 96 by 96 studs. You don't need a Brickwork account to create or open a model. Links expire after one hour, and generated files are deleted within a day.
Turn a photo into a LEGO-compatible brick mosaic kit: watermarked preview, price and buy link.
Visual Desktop Bridge - Give any AI full control over Windows to automate apps and inputs.
Build financial models as code. Cloud execution, GSheets MCP, version control, collaboration.
Base on-chain address labels (eth-labels 104k category tags), tx explainer, clusters, CCTP USDC.
Base on-chain address labels (eth-labels 104k category tags), tx explainer, clusters, CCTP USDC.
Hospedagem no Brasil que o agente opera: cria banco, publica, lê log e diz o custo.
BridgeApp brings your team's tasks, chats, documents, and AI agents into one workspace. This connector lets Claude read and act on that workspace with your own account's permissions. What Claude can do: - Tasks: find tasks by search or BQL filters, read a task with its comments, subtasks, blockers, relations, and plan page, create tasks, update fields and status, and comment. - Chats and threads: read channels, direct chats, and threads to the end, including agent transcripts and attachments; search messages; send a message to a channel or a direct chat. - Pages: list and read workspace and project pages, create pages, and attach them to tasks. - Projects: list projects with their statuses, task types, milestones, versions, and participants; read and update project and workspace briefs; create projects and channels. - Agents: manage routines and their schedules, run a routine, and maintain the workspace's agent rules and skills. - Links: turn a BridgeApp link into the object it points to, and build links and mentions back. You sign in with your BridgeApp account over OAuth and pick one workspace per connection. Claude never sees more than that account can see. Write actions that change or remove existing data are marked as destructive, so Claude asks before running them. For skills that teach Claude the BridgeApp workflows, add the BridgeApp plugin from the Claude directory.
Plan annual leave around public holidays: bridge days and long weekends for 200+ countries.
BridgeNode — x402 pay-per-request AI inference. OpenAI-compatible API + MCP, Solana USDC, gas-free.
BridgeNode — x402 pay-per-request AI inference. OpenAI-compatible API + MCP, Solana USDC, gas-free.
Is a website ready for AI shopping agents? Readiness score (0-100) + agent shopping simulation.
Save and adapt recipes, plan household dinners for review, and manage shared grocery lists.
brief bar is an open, versioned standard for digital product briefs: the rules a brief must pass before a team can quote on it, with their weights, a gate and an acceptance threshold. This connector gives Claude the bar itself. Claude reads the live rules, gets the service judge's own prompt, judges your brief with its own model, and sends the verdicts back. brief bar's open-source code checks every verdict (each rule exactly once, quotes copied verbatim from the brief) and computes the score, the gate and the decision with the same engine the hosted service uses. It also offers a brief template built from the rules, a gate-first improvement prompt, and fast deterministic checks (contact details that break anonymity, a stated budget and timeline, unfilled placeholders, missing sections). Free, no account, no API key. welance runs no language model for this connector: your client's model does the judging, so the result is advisory and labelled as client-judged. Write briefs in any language. Open source: https://github.com/welance/perfect-brief. Rules: https://briefs.welance.com/rules.html.
Briefcase Ledger is AI-native accounting software for UK businesses and their accountants. It codes every bill and receipt line by line, explains each decision, learns from corrections and publishes on its own when it is confident. You can ask for a profit and loss, balance sheet or aged debtors, see what needs review and why, and publish transactions, raise invoices, post journals and run month-end schedules. It also works for Xero and QuickBooks books through Briefcase Connect. Claude acts as you, on the clients you choose, with your permissions. It asks before every change, previews anything that posts to the books, and records every change in Settings → AI assistants. It never moves money.
Git-backed team knowledge compiled into token-budgeted context bundles for coding agents
Brieff holds the story behind your client and team work. Bring that context into your AI assistant and use it alongside the other tools in your workflow. Connect past conversations, meeting notes, Actions, Goals and Check-in responses to the work you're doing now. Ask questions, explore ideas and prepare your next steps with the relevant Brieff context close at hand. Run better meetings with a clear view of what's changed and what needs attention. Keep work moving between meetings by creating and updating Actions, refining agendas and updating Client notes or Internal Workspace Meeting notes from your conversation. Connect your Brieff account to get started. Your existing permissions apply, and your firm must have AI connections enabled.
Send real paper letters from AI chat: print, envelope, postage, delivery. Pay per letter.
What this catalog covers
- Source listings
- 167,897
- Candidate groups
- 168,273
- Setup-eligible endpoints
- 30,743
Sources observed 2026-10-24–2026-11-12. Listings can overlap across sources. Groups are identity candidates; setup eligibility is not a successful connection test.
SourcesMCP data from Glama connectorsMCP data from Glama source codeOfficial MCP RegistryClaude connector directoryAPI Tracker · publisher documentationSlack MCP directory
Default browsing excludes 2,356 specialized utility groups across the catalog. They remain available through keyword search and direct links. This editorial filter does not change the indexed totals or establish publisher quality.
Categories currently cover records matched to our reviewed catalog; other listings remain Uncategorized. Source-only projects have no generated connection option. Browse reviewed official MCPs →
- Glama connectors
API result set; pagination may cap at approximately 1,000 connectors. Not exhaustive.
- Glama source code
Complete chronological source-code catalog response; includes source-reported author classifications, not publisher attestations or ready-to-use endpoints.
- Official MCP Registry
Complete paginated registry response; registry membership is not publisher verification.
- Claude connector directory
Complete public Claude directory MCP components. Source tiers, tools, icons and sign-in hints are declarations, not publisher or runtime verification.
- API Tracker · publisher documentation
Reviewed publisher and third-party remote, local and setup-only MCP listings. Publisher status is retained per exact connection. Discoverability does not establish connection readiness.
- Slack MCP directory
Reviewed additions discovered through the public Slack Marketplace MCP category. Complete discovery inventory is retained separately; membership does not prove external-client compatibility.
Listings are grouped by exact public endpoints, exact package sets, or explicit reviewed identity bindings. Shared names or repositories alone do not merge implementations. Official includes publisher evidence and accepted source author classifications. It does not mean independently verified, runtime-tested or security-certified.