Buffer’s MCP server puts social workflows in your agent stack
Buffer has added an MCP server plus native connections for Claude, Cursor, and Raycast, putting social publishing and channel data closer to the agent interfaces developers already use. Replit Agent is making a parallel move, with a broad third-party catalog spanning tools including Gmail, LinkedIn, Shopify, Slack, and Adobe Commerce. Cursor leads outbound clicks this week, which makes these integrations more consequential: coding-agent adoption is increasingly a route into adjacent operating workflows. Check whether Buffer’s API and MCP permissions expose the posting and approval controls your team needs before connecting an agent to production channels.
See what changed on Buffer'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.
|
8/36 · Guided Assistant
Revdoku repositions around email-enabled cloud buckets for AI agents — Revdoku has substantially rewritten its product positioning from general AI-agent file storage toward email-enabled cloud buckets.
Source: the tool's own site — detected 2026-09-24 by agentic.ai's daily recrawl.
|
|
10/36 · Guided Assistant
Buffer adds MCP support and native integrations for Claude, Cursor, and Raycast — Buffer’s updated site highlights expanded developer and agent integrations, including an MCP server, Zapier MCP configuration, native connections for Claude, Cursor, and Raycast, and broader API access for posts, ideas, channels, and analy…
Source: the tool's own site — detected 2026-09-24 by agentic.ai's daily recrawl.
|
|
13/36 · Adaptive Collaborator
Conversica rebrands as “The Conversation Company” and introduces Ignite… — Conversica has substantially revamped its homepage around a new “Conversation Company” positioning and introduced Ignite, described as a revenue activation engine for automotive groups.
Source: the tool's own site — detected 2026-09-24 by agentic.ai's daily recrawl.
|
|
10/36 · Guided Assistant
Cresta unveils an AI agent platform for automating, augmenting, and analyzing… — Cresta has substantially overhauled its product positioning around AI Agents for customer conversations.
Source: the tool's own site — detected 2026-09-24 by agentic.ai's daily recrawl.
|
|
12/36 · Guided Assistant
Replit expands Agent with a broad catalog of third-party integrations — Replit’s updated Agent pages add a large integration catalog spanning services such as ActiveCampaign, Adobe Commerce, Ahrefs, Gmail, LinkedIn, Shopify, Slack, and many others.
Source: the tool's own site — detected 2026-09-24 by agentic.ai's daily recrawl.
|
|
14/36 · Adaptive Collaborator
SentinelOne positions Purple AI as an agentic security analyst… — SentinelOne’s updated Purple AI page presents it as an agentic security analyst capable of running investigations, surfacing evidence, answering questions without queries, performing auto-triage, generating investigation notebooks, and gui…
Source: the tool's own site — detected 2026-09-24 by agentic.ai's daily recrawl.
|
What's new in the directory
|
7/36 · Guided Assistant
RankMeRabbit is a cloud-based SEO review tool that combines site structure with Google Search Console data. It identifies internal-linking, on-page, technical, schema, and image issues, then prepares recommendations for human review before changes are published.
Source: published listing, rubric-scored on ingest.
|
|
11/36 · Guided Assistant
Candor is a personal-finance workspace that connects read-only financial records to supported AI agents such as Claude, ChatGPT, Grok Bot, and Muse. It helps your agent review accounts, identify issues that need a decision, and retain approved plans across future conversations.
Source: published listing, rubric-scored on ingest.
|
|
19/36 · Domain Specialist
Atlarix is a desktop AI coding agent for engineering teams on macOS, Windows, and Linux. It can inspect repositories, edit code, run tests and terminals, and use your Chrome for app testing, while holding code changes for your approval.
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 iLook actually works
iLook is a single-purpose photo analyzer, not an agent. You give it one authorized adult face photo, and it returns a written readout of visible features such as face shape, symmetry, a subjective face score, and Golden Ratio context. It also adds appearance and style feedback. That’s analysis, not action planning: it doesn’t carry out tasks, make decisions over time, or operate on its own. The only state it keeps is a private history of past results, and even that stays there until you delete it. So control stays with the user at every step - upload a photo, read the output, decide what to do next. With a 6/36 score, it looks much closer to a basic evaluator than an autonomous tool.
See iLook's full scorecard →
One tool worth testing
Atlarix — Atlarix is a desktop coding agent for engineering teams that need repository inspection, code edits, terminal and test execution, and browser-based app testing across macOS, Windows, and Linux. Its newly published listing describes a useful control point: code changes are held for approval rather than applied without review. Evaluate Atlarix against Cursor in a 30-minute pilot on one existing bug fix, comparing repository context, test execution, and the quality of the approval-ready diff.
Our pick: Clay
The use case: sales & marketing.
Tops our independent /36 — strongest on action and autonomy, ahead of 11x Alice. Pricing: Actions + data credits (two meters).
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 →
|