Read-only on-chain intelligence for AI agents on Base: balances, tokens, gas, tx status.
MCP servers
Compare source listings, connection options and authentication requirements.
Showing 13,513–13,536 of 165,917 resultsPage 564 of 6,914
Candidate groups, not verified unique MCPs. How grouping works
Read-only on-chain intelligence for AI agents on Base: balances, tokens, gas, tx status.
MCP server for Base L2 DeFi operations with 9 monetized endpoints
Free onboarding tool providing authentic live transaction analysis on Base mainnet.
AI news in TR/EN/ES/RU, a daily stack brief and a verified MCP/plugin/skill catalog. Read-only.
Base token checks for agents: simulated buy and sell, taxes, honeypots. Pay per call in USDC (x402).
Decode any Base tx: plain English, strict JSON, risk flags, no LLM. 50 free/day per IP, then $0.02.
Zero-slippage swaps on Base (8453) via Uniswap v4 Hook 0xd72CD1d46bA05479583fbB561B558f133BA98088.
Base MCP connects Claude to your Base account so you can work with your store data directly in the conversation. Once connected via OAuth 2.1 (with your login and consent through Base’s screen), Claude can check account details, look up orders, review product listings, and check inventory levels, and can also take actions on your behalf, such as updating order statuses, adding orders, or updating inventory stock levels. Read-only and write operations are separate tools, and Claude acts only within the permissions you approve on the consent screen.
Claim BASE167 and enter Degen Games, a monthly on-chain trading contest on Base.
Encoding MCP — Base64 / Base64URL / Base32 / Hex.
Encode/decode base64 and URL-safe base64. x402 micropayment.
Fee-ranked agent origin on Base. MCP discover + local sign. Non-custodial. Fee Arena.
Fee-ranked agent origin on Base. MCP discover + local sign. Non-custodial. Fee Arena.
USDC-gated Base JSON-RPC: free 10 req/min, $0.50 per 10k. Failover, cache, /mcp, ledger.
Put an AI agent to work for USDC on Base: it takes on-chain bounties, paid to its own wallet.
Basecamp puts every to-do, decision, and update for a project in one place. Now Claude can work there too. Turn meeting notes into to-dos with owners and due dates. Start a project, post the Friday update to the message board, move the card that shipped, put the deadline on the schedule, or answer this week's check-in. When something needs a follow-up, leave a comment that @mentions the right person. Need to catch up first? Ask what happened on a project this week, what's overdue, or what was decided, and see what's actually done and what's left before you ship. No status meeting required. You stay in control. Claude sees and does only what you can in Basecamp, nothing more. Choose read-only, require approval before Claude posts or changes anything, and disconnect anytime.
Basecoat UI 1.0 components (shadcn/ui look in plain HTML + Tailwind) with usage docs and setup.
Offline Basecoat UI MCP: templates, macro layouts, theming contract, and static validation.
Basedash is an AI-native BI platform. This connector lets Claude query governed company data, list available sources, and create, edit, list, or retrieve dashboards and charts — with the same workspace permissions as the Basedash app. Connect once with browser OAuth (no API keys). Claude can: • Ask plain-English questions of live databases, warehouses, and SaaS sources • Discover which data sources the signed-in user can access • Create or edit dashboards and charts from natural-language instructions • List and open existing dashboards and charts, including durable Basedash URLs and chart screenshots when available Every tool call enforces Basedash access controls. If an account cannot see a source, dashboard, or chart in Basedash, the connector will not expose it. Dashboard/chart reads use mcp:dashboards:read; creates/edits use mcp:chat:ask and mcp:dashboards:write. Requires a Basedash account and at least one connected data source. Setup: https://www.basedash.com/docs/features/mcp-server
Find public creator tools, work and conversation. Read-only; no wallet, posting or payment.
Basee is a cloud back-office suite for Japanese service businesses that brings estimates, invoices, expenses, attendance, paid leave, payroll and projects into one place. This connector lets you use your own Basee account from Claude in natural language. What you can do - Check your profile, today's attendance, your paid-leave balance, your expenses, expense categories and projects - Clock in, clock out, and record time away from work (recorded immediately, only when you ask) - Request leave and register out-of-pocket expenses, optionally with a receipt file - Review the requests waiting for your approval, then approve, reject or relay them to another approver - Search customers, estimates and invoices, and create estimate and invoice drafts How you stay in control - Every write except clocking takes two steps: Claude first shows exactly what will be registered, and Basee commits it only after you explicitly agree. - Estimates and invoices are created as drafts only. Nothing is issued, sent or emailed from Claude. - The connector acts only within your own role and permissions in Basee, and only in the organization you choose on the consent screen. You can review and revoke connections at any time in Basee. Requirements - A Basee account. An administrator of your organization must turn on AI assistant connections in Basee (Settings > Integrations). - The Basee screens and data are in Japanese.
Explore Baseline equity research directly in Claude. Screen companies by qualitative scores for business quality, pricing power, management and risk, then read the research rationale behind each score. Discover scored fields and sectors, combine screening conditions, and create or manage personal watchlists. A Baseline account is required. Connect securely through OAuth using your normal Baseline login. Research reflects its recorded update date and is not a live market-price feed.
Building data: address, use, size, height, age, roof, solar panels and registered businesses.
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.