"Loop" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
An AI answering line for US businesses, paid per answered call; Odile Formats for video and photos.
Free fantasy sports AI: ESPN, Sleeper and Fantrax league data for Claude and ChatGPT. Read-only.
Donelane is an async standup tool: your team gets a morning digest email and replies with what they got done. This MCP server puts your agents in that same loop. Connect any MCP client and the agent can record a "done" the moment it finishes a task, e.g. "Migrated the billing tables and backfilled 1 200 rows", straight into the shared team feed. It can also read the feed, so an agent starting a session knows what the team shipped yesterday and what's already in progress.
AgenticBooks is agent-native financial infrastructure. An agent can open an account, connect a user's payment and banking sources, and read back clean, reconciled accounting books over MCP. No human in the loop and free to start.
Human-in-the-loop for AI agents over MCP: durable approvals with a hosted review page & audit trail
MCP-native AI SRE. Exposes your production OpenTelemetry problems, traces, and logs over the Model Context Protocol, plus an AI remediation loop that opens a reviewed GitHub fix PR and verifies in production (reopening on regression). Tools include list_problems, get_problem, query_traces, detect_anomalies, and request_problem_remediation. Human-in-the-loop by default — the merge button stays yours.
Open-source AI presentation builder from Builder.io: every app action — generating a deck from a prompt, editing and reordering slides, applying brand styles, sharing — is exposed as an MCP tool, plus an ask-agent meta-tool that hands complex requests to the app's own agent loop. Streamable HTTP with OAuth 2.1 dynamic client registration; MIT-licensed and self-hostable.
Hosted remote MCP server for AI-driven stealth browser automation. Connect any MCP client (Cursor/Cline natively, Claude Desktop via mcp-remote) — no install, no Docker, no Playwright. Drives a real Chromium with residential proxies, automatic CAPTCHA solving, persistent profiles, and a live viewer URL for human-in-the-loop. Three tools: humanbrowser_run, humanbrowser_stream, humanbrowser_viewer_url. Same hb_live_* Bearer token works for both MCP and the A2A 1.0 endpoint.
Create and publish events on SocialLoop — manage tickets, guest lists, promo codes, affiliates, and the full production OS — from any AI assistant. No API keys.
US property register: 92M parcels, deeds, violations, CMBS filings, county sales, market series.
AI code review for GitHub PRs with an MCP autofix loop for Claude Code and Cursor
- mdreviewOAuth via extensionio.github.ranawaqas-ai
Human-in-the-loop document review: an agent pushes a draft, a person comments, the agent revises.
Loom for agents: AI agents record narrated product demos, plus transcripts, summaries, and search.
Marketing MCP: your AI agent runs your organic growth loop — you approve before it ships.
- e2a-mcpOAuthdev.e2a.mcp
Authenticated email gateway for AI agents. Each agent gets its own deliverable email address with SPF/DKIM-verified inbound and optional human-in-the-loop approval on outbound. 18 tools covering send, receive, reply with threading preserved, and HITL approval queue.
Minimal chat-first app with durable threads, actions, and the app-agent loop
Deterministic AI code review, with an audit record. Governance inside the agent loop.
A collaborative place for user requests: collect feedback, plan work, keep users in the loop.
AI-native Kanban board — connect Claude to claim, work and move your tasks over MCP.
- LoopsOAuth unavailableio.github.loops-so
Manage Loops contacts, mailing lists, campaigns, and transactional email from your Loops account.
