Immutable event logging and audit trail for agent transactions
MCP servers
Compare source listings, connection options and authentication requirements.
Showing 27,457–27,480 of 165,917 resultsPage 1145 of 6,914
Candidate groups, not verified unique MCPs. How grouping works
Hiveflow is a visual AI agent orchestrator: you design workflows on a drag-and-drop canvas, connect them to your tools and data, and let them run on a schedule, from a trigger, or on demand. This connector brings your Hiveflow workspace into Claude, so you can inspect and operate it in conversation instead of switching to the dashboard. What you can do with it: • Flows — list your workflows with their execution state, inspect a flow's nodes and edges, create new flows, run one on demand, and activate or pause it. • Kanban boards — list boards, read columns and cards, create cards, move them between columns, and add comments. • Workers — see which agents are connected to a board, whether they are paused, and when they last checked in. Moving a card into a watched column is how you hand work to them. • Organizations and workspaces — list the organizations and workspaces you belong to, and scope any operation to a specific one. • Live API reference — a docs tool that returns the current Hiveflow API reference, so Claude works from up-to-date definitions rather than assumptions. Everything runs with your own Hiveflow account through OAuth: the connector sees exactly what you see, respects your organization roles and permissions, and every action is attributed to you. Tools that only read are marked read-only; tools that change your account — running a flow, pausing one, moving a card — are marked as such, so Claude asks before acting. Free to connect with any Hiveflow account.
Agent spawning, lifecycle management, and population control for AI economies
Agent admission queue with capacity control and priority tiers
Trust & settlement for AI agents: DID, ZK reputation, audit, USDC/USDCx/USAD/ALEO. First DID free.
Shared research, saved evidence, independent reviews and open tasks for AI agents.
Governance framework, dispute resolution, and arbitration for agents
Read and author HiveLearn courses, events, quizzes, certificates, resources, leaderboards, tracks.
Read and author HiveLearn courses, events, quizzes, certificates, resources, leaderboards, tracks.
Collective intelligence, memory storage, and knowledge marketplace
Hive is one connected workspace for social growth — not a cheaper version of a single tool. DM automations come first. Comment-to-DM, keyword replies, story-mention replies, welcome messages and follow-up sequences across Instagram, Messenger, WhatsApp and TikTok, built on a visual flow canvas with conditions, delays, randomised variants and data collection. Contacts are unlimited on every plan — you are never charged per person you talk to. A full link-in-bio page, with links, blocks, themes and click tracking, for the profiles that only allow one URL. Real team workflows: a shared inbox, roles and permissions, approval workflows, delegation, and a separate workspace per client or brand. Publishing as a pillar, not a footnote. Write once and schedule to every network at once, with per-network validation, best-time slots, a visual queue and bulk scheduling. Analytics across every account in one view — reach, engagement, followers, clicks, campaigns and attribution side by side, plus saved reports, competitor tracking and social listening. Twelve networks: Instagram, Facebook (with Messenger), WhatsApp, TikTok, YouTube, LinkedIn, Threads, Pinterest, Snapchat, Bluesky, Mastodon and Telegram. Through this connector Claude gets 47 tools over all of it. Reads and drafting run immediately; anything that reaches a real audience does not. Scheduling, rescheduling or cancelling a post, replying publicly to a comment, sending a direct message and setting an automation live each return an approval link the account holder confirms inside Hive. There is no immediate-publish tool, and every write permission is unticked by default.
Real-time health monitoring and heartbeat tracking for agent services
Connect Claude to the Shared Inboxes you manage in Hiver in Gmail. Use Claude to find specific conversations faster, get up to speed on issues, and take actions like creating drafts, adding tags or internal notes, updating CRM records, or creating tasks in your project management tool. Admins can use Claude to analyze support metrics and trends, including conversation volume, response times, SLA attainment, CSAT, and workload. You can compare metrics across different periods, spot patterns, and understand what needs attention. Try asking Claude * Show me the recent conversations from Acme Corp that were assigned to me and summarize the open issues and next steps. * Pull up the latest conversation from John Doe, apply the “Escalated” tag, and create a shared draft offering a discount. * Which conversations breached SLA this week? Group them by issue and tell me where we’re seeing the biggest delays. * How did Support perform this month compared with last month? Highlight changes in volume, response times, SLA attainment, and CSAT. * Where is the team carrying the heaviest workload right now, and how is that affecting response times? Claude can only access the Shared Inboxes you’re part of. It can only perform actions supported by this connector and allowed by your existing role and permissions in Hiver.
Connect your Shared Inboxes in Hiver Omni to Claude to quickly find the conversations you need, understand the context behind customer issues, and take actions like drafting responses, adding tags and internal notes, updating a CRM record, or creating a task in your project management tool. Admins can use Claude to analyze support metrics and trends, including conversation volume, response times, SLA attainment, CSAT, and workload. You can combine metrics in the same question to investigate patterns, compare periods, and understand what needs attention. Try asking Claude * Show me unresolved conversations tagged “Billing” and summarize what’s blocking each one. * Pull up the latest conversation from @acme.com, summarize the outstanding issues, and create a shared draft addressing the most recent request. * What login issues did customers report this week? Summarize the common problems. * Which days had the longest first response times this month, and what was conversation volume like on those days * What are customers with low CSAT scores most commonly unhappy about this quarter? Claude can only access the Shared Inboxes you’re part of. It can only perform actions supported by this connector and allowed by your existing role and permissions in Hiver.
Marketplace MCP server for live venture-capital raises and agent-mediated dealflow.
KYA identity verification, trust scoring, and performance bonds for AI agents
Shared project wiki for AI agents: read and write pages, next actions, and activity logs over MCP.
Find and check free.si names (600,000+ indexed), and look up DNS and WHOIS for any domain.
Hjarni is a knowledge base your AI can actually use. Write notes in Markdown. Organize them in folders and tags. Claude reads them directly through a built-in MCP server. No plugins. No pasting the same context into every conversation. Claude starts every conversation from zero. Connect Hjarni once and it stops asking. Ask questions across all your notes. Have Claude write new notes, update old ones, and tag them the way you want. Set instructions per folder to control how Claude writes, formats, and tags. Share a folder with your team so everyone's AI works from the same knowledge base. Search across everything in one call.
Hong Kong Companies Registry (香港公司註冊處) open data via data.gov.hk (keyless): search companies by…
hk-elegislation — Hong Kong Ordinances, subsidiary legislation and instruments, bilingually…
Exact Hong Kong IPO costs: entry fee, margin interest, break-even price, scenarios, sell fees
Hong Kong horse racing: race cards, AI win chances, odds, results, form and stats.
Hong Kong equities MCP. Keyless.
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.