Enables AI agents to retrieve live public data from 70+ platforms — profiles, posts, comments, transcripts, products, prices, reviews, listings, jobs, ads and search results — plus website crawls and live browser sessions through 650+ endpoints in one response format. Includes free cost previews, per-call credit caps, safe retries, refunded failures and scheduled monitoring.
MCP servers
Compare source listings, connection options and authentication requirements.
Showing 5,425–5,448 of 165,839 resultsPage 227 of 6,910
Candidate groups, not verified unique MCPs. How grouping works
A unified MCP layer that serves organization toolkits as MCP endpoints with per-tool permissions, an async approval queue, and full audit logging.
Enables AI agents to fetch real-time quotes, token information, and trade transaction data from Monorail's aggregation of 11 exchanges and 7000+ tokens.
Pay per MCP tool call in USDC on Base. Non-custodial settlement, no admin keys, 30 bps fee.
MCP server that exposes Moolre's API as 24 tools for AI agents, enabling account management, transfers, payments, SMS, and WhatsApp operations.
Provides AI agents with live access to a global directory of consumer and business banks, including community-rated scores across categories like customer service, fees, digital experience, and crypto friendliness, enabling grounded answers to banking questions.
Enables AI assistants to capture bookmarks, sticky notes, todos, notes, and web archives, and to search and organize personal knowledge and memory across cloud-synced clients.
Official European law, expanding globally: 20M+ documents, 35+ jurisdictions, verifiable citations.
Enables agents to research and analyze public short-form video content on Instagram Reels, TikTok, and YouTube Shorts for trend spotting, creator research, competitive briefs, and content ideation.
Enables interaction with Moorcheh AI services including namespace management, document embedding, vector search, and AI-powered answers through the Model Context Protocol.
Git and GitHub operations — repo status, diffs, branches, stashes, PRs, issues, and Actions from MCP.
A TypeScript wrapper for the Moralis REST API that enables interaction with blockchain data through the Model Context Protocol (MCP).
Enables AI clients to query and manage multiple Minecraft servers through MineAuth's HTTP API using one shared service token, covering server and plugin status, online players, tickets, claims, balances, and rail network routing, plus plugin install/update operations. It also exposes a generic MineAuth passthrough so new addon endpoints work without modifying the server.
Enables interaction with the Morphik multi-modal database system for document ingestion, retrieval, querying, and management. Supports text and file ingestion, semantic search with LLM-powered completions, and file system navigation with security controls.
Provides AI-ready access to Indian government statistics through MCP, enabling natural language queries for economic, demographic, and social indicators.
Enables LLM agents to interact with the MOSTLY AI Platform for generating synthetic data, including training generators, managing data connectors, executing queries, and generating synthetic datasets with OAuth 2.1 authentication.
This MCP gives you full control over your translation projects from start to finish. You can log in anytime to see what stage your project is in — whether it’s being translated, reviewed, or completed. You don’t have to guess or follow up via email.
This MCP gives you full control over your translation projects from start to finish. You can log in anytime to see what stage your project is in — whether it’s being translated, reviewed, or completed.
Motherboard is the service knowledge platform for field service teams that maintain complex equipment and robotic fleets. This connector gives Claude read-only access to your company's Motherboard workspace, so you can ask questions about your own operation and get answers grounded in your records. With it, Claude can look up and search service tickets, equipment, parts and assemblies; follow relationships such as which parts go into an assembly and how many; read your company's SOPs and the exact pages of service manuals and source documents, including their page images; and search service knowledge across all of them. Every answer can cite the exact record, SOP or document page it came from, with a link back to Motherboard. The connector is strictly read-only: it cannot create, change or delete anything, take actions, or post messages. Claude sees only what you are allowed to see in Motherboard, because every request runs under your own account and role. To connect, enter your company's Motherboard workspace name (the first part of your Motherboard web address) and sign in with your Motherboard account. You can disconnect at any time from Settings > Connected agents in Motherboard. Requires a Motherboard account provided by your company.
Enables AI tools to search and retrieve automotive brand data, logos, and color palettes from the Motomarks car logo API, and generate authenticated CDN image URLs for embedding.
Create and manage voice AI agents using natural language from Claude Desktop or Cursor. Enables agent creation, listing, updating, deletion, and viewing call logs.
Enables inspecting, creating and modifying MakeHuman characters inside Blender — phenotypes, rigs, assets, skins, faces, expressions and saved presets — through 34 named tools served by a companion Blender bridge add-on that dispatches a closed command vocabulary instead of executing code. It also exposes read-only introspection, catalogue and documentation lookups that always answer, even when Blender is unreachable.
MCP server that allows AI agents to discover and pay for thousands of APIs (x402 on Solana/Base) using a single key, with automatic payment handling and a federated catalog of machine-payable endpoints.
Enables financial research on US-listed equities by answering natural language questions with structured data from fundamentals, prices, earnings, and insider activity.
What this catalog covers
- Source listings
- 167,775
- Candidate groups
- 168,195
- Setup-eligible endpoints
- 30,727
Sources observed 2026-10-24–2026-11-04. 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
Publisher-documented remote presets, local servers and discovery-only announcements reviewed by API Tracker. 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.