Reply.io’s 70 MCP tools change your sales-stack review
Reply.io’s expanded surface is more than another sales integration: it now offers 213 REST endpoints, 70 MCP tools, a CLI, and packaged skills for clients including Claude, Cursor, and n8n. That is why its agent positioning changes the review from feature coverage to how tightly an AI assistant can operate outbound workflows. MimikFlow’s addition of MCP-compatible prospecting control, WhatsApp follow-up, and email prospecting raises the same operational question in a second tool: where will prospect data, approvals, and channel handoffs live? Run that governance check before giving an assistant access to sequences.
See what changed on Reply.io's listing →
What changed on the ground
Changes we detected on each tool's own pages — pricing, features, platform reach — via our daily crawls. Often ahead of any press coverage; each links to the scored listing.
|
14/36 · Adaptive Collaborator
Kilo Code announces acquisition by Anaconda and expands enterprise AI coding… — Kilo Code’s site now states that it has been acquired by Anaconda.
Source: the tool's own site — detected 2026-09-30 by agentic.ai's daily recrawl.
|
|
13/36 · Adaptive Collaborator
MimikFlow expands beyond LinkedIn with MCP control, WhatsApp follow-up… — MimikFlow’s updated product surface adds substantial platform capabilities: users can control prospecting through MCP-compatible assistants, run WhatsApp follow-up and reactivation workflows, and use an email prospecting channel with manag…
Source: the tool's own site — detected 2026-10-01 by agentic.ai's daily recrawl.
|
|
11/36 · Guided Assistant
Automation Anywhere acquisition reshapes Aisera around a unified AI agent… — Aisera’s homepage now prominently references its acquisition by Automation Anywhere and positions the company around a unified AI agent platform.
Source: the tool's own site — detected 2026-10-01 by agentic.ai's daily recrawl.
|
|
11/36 · Guided Assistant
Manus expands its AI agent platform with game creation, video generation… — Manus’s refreshed product site announces a broad product expansion centered on Manus 2.0, adding prompt-based game creation, AI video generation powered by Seedance 2.5, and a desktop video editor with editable timelines, audio, captions a…
Source: the tool's own site — detected 2026-10-01 by agentic.ai's daily recrawl.
|
|
9/36 · Guided Assistant
Coda rebrands as Superhuman Docs, positioning its workspace around team AI… — Coda is now Superhuman Docs, with the product repositioned as an AI-powered team workspace.
Source: the tool's own site — detected 2026-10-01 by agentic.ai's daily recrawl.
|
|
11/36 · Guided Assistant
Reply.io expands its platform with a REST API, MCP server, CLI, and agentic… — Reply.io now prominently positions its sales engagement platform for AI agents and developers, highlighting 213 REST endpoints, 70 MCP tools, a CLI, packaged skills, and integrations with clients such as Claude, Cursor, n8n, and other MCP-…
Source: the tool's own site — detected 2026-10-01 by agentic.ai's daily recrawl.
|
What's new in the directory
|
15/36 · Guided Assistant
Hourtick is a team time-tracking, task-management, and chat workspace that lets people assign work to AI agents such as Claude, GPT, Grok, and Muse. It records agent time and cost alongside human work, with timesheets, approvals, and invoicing controls built in.
Source: published listing, rubric-scored on ingest.
|
Agenticness Leaderboard
This week's most-clicked tools, re-ranked by rubric score. The score is the editorial signal; the popularity is what drew the directory's traffic here this week.
- Hyper · 22/36 · Domain Specialist · L3
Hyper is a cloud-based autonomous software engineering platform for turning product objectives into tested code in your GitHub repositories. It plans work, runs parallel agent sessions in isolated lanes, verifies results server-side, and can open pull requests or deploy supported projects.
- Sinatra · 21/36 · Domain Specialist · L3
Sinatra is an autonomous coding agent that takes work from Linear or GitHub, reads the relevant repository, writes a change, runs tests, and opens a draft pull request. Teams review the result in GitHub and can request follow-up changes in the PR thread.
Claude Code is Anthropic's agentic coding tool that lives in your terminal. It understands your entire codebase, makes multi-file edits, runs commands, manages git workflows, and uses MCP for tool integration. Built with a Unix philosophy — it reads, plans, edits, and verifies in a loop. The fastest-growing product in the coding agent category.
- Cursor · 18/36 · Adaptive Collaborator · L2
Cursor is a developer-focused AI environment that adds agents, context, and automation around your repositories. It combines an editor-like interface, a CLI, and a cloud agent API to automate code review, bug fixing, CI hygiene, and more. Designed for individual developers and engineering teams who want AI to take real actions in their code and infrastructure, not just chat.
- Cline · 18/36 · Adaptive Collaborator · L2
Cline is an AI coding assistant for VS Code that can inspect your project, edit files, run terminal commands, and use a browser while asking for permission at each step. It is aimed at developers working on real codebases who want more than code completion.
Learn: How ThunderPhone actually works
ThunderPhone is a cloud voice-agent system for phone calls. Based on the description, it can answer inbound calls and run outbound campaigns through a no-code dashboard or API. It does more than suggest responses: it can speak with callers, pull in knowledge for answers, and handle telephony tasks during the call. It also supports live supervision, which means a human can monitor or step in when needed. The platform appears to keep session context long enough to carry on a conversation, including multilingual back-and-forth, but the description doesn’t prove long-term memory across separate calls. In practice, ThunderPhone is autonomous inside the call flow, but human control returns through supervision and whatever the team sets up in the dashboard or API.
See ThunderPhone's full scorecard →
One tool worth testing
MimikFlow — MimikFlow is worth testing for teams that want an AI assistant to run multichannel prospecting and follow-up. Its updated surface adds MCP-compatible assistant control, WhatsApp reactivation workflows, and an email prospecting channel, making it a timely way to test whether one operator workflow can span more than LinkedIn. In a 30-minute pilot, compare it with Reply.io on one prospect list: assistant control, handoff quality, and the steps that still require human review.
Our pick: ChatGPT
The use case: general-purpose ai agents.
Tops our independent /36 — the tiebreaker over Hermes Agent: Reliability 2 vs 0. Pricing: Subscription + credit-metered agents.
Ranked by our 9-dimension Agenticness rubric — not by who pays us (nobody does). The full scorecard, true-cost pricing, and the reliability evidence behind every score are in the report.
Read the full report →
|