Reply.io's 70-tool MCP makes sales-agent access a check
Reply.io’s new MCP server gives compatible agents access to 70 tools for searching contacts, managing sequences, analyzing performance, and executing outbound actions. That shifts the evaluation from drafting help to permission design: Claude, ChatGPT, Codex, and Cursor can now sit closer to the sales workflow itself. TestFit is making a similar connection available for site planning through a $100/month-or-more MCP add-on, while Canva AI 2.0 pulls context from Slack, Gmail, Google Drive, and Notion into creation. Before connecting an assistant, map the actions it can take and the approval points it cannot bypass.
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.
|
11/36 · Guided Assistant
Reply.io launches MCP server for running sales workflows from AI assistants — Reply.io has added Reply MCP, a standard JSON-RPC 2.0 MCP server with 70 tools that lets Claude, ChatGPT, Codex, Cursor, and other compatible agents search contacts, manage sequences, analyze performance, and execute outbound actions.
Source: the tool's own site — detected 2026-09-16 by agentic.ai's daily recrawl.
|
|
8/36 · Guided Assistant
Canva unveils Canva AI 2.0 with conversational creation, connected tools… — Canva’s updated AI 2.0 experience is positioned as a conversational creative partner that can turn ideas into editable designs, use context from connected tools such as Slack, Gmail, Google Drive and Notion, perform web research, personali…
Source: the tool's own site — detected 2026-09-16 by agentic.ai's daily recrawl.
|
|
13/36 · Guided Assistant
Upsolve AI repositions around Agent Studio for context-verified data… — Upsolve AI’s website now presents Agent Studio for data teams, with agents that combine warehouse structure, semantic models, institutional context, verified answers, lineage, and usage signals.
Source: the tool's own site — detected 2026-09-16 by agentic.ai's daily recrawl.
|
|
9/36 · Guided Assistant
Lilt repositions around multilingual agentic AI and AI model evaluation — Lilt’s homepage now presents the company as an agentic AI platform for enterprises, public-sector organizations, and AI developers, adding messaging around agent and model evaluation, multilingual AI infrastructure, and AI transformation w…
Source: the tool's own site — detected 2026-09-16 by agentic.ai's daily recrawl.
|
|
11/36 · Guided Assistant
Aivah repositions around AI employees for business — Aivah has substantially repositioned its product and website around AI employees for sales, support, and customer onboarding, replacing broader messaging about AI agents, workspace tools, and model choice.
Source: the tool's own site — detected 2026-09-16 by agentic.ai's daily recrawl.
|
|
8/36 · Guided Assistant
TestFit adds MCP connectivity for AI assistants with a $100/month add-on — TestFit’s updated pricing and product pages introduce an MCP Connection add-on priced at $100/month or more, allowing users to connect TestFit to assistants such as Claude and ChatGPT and direct site-planning work through natural-language…
Source: the tool's own site — detected 2026-09-16 by agentic.ai's daily recrawl.
|
Score activity
|
18/36 · Adaptive Collaborator
Score now 18/36 (15→18). The rubric moved on documented capability evidence; press alone does not move the score.
Trigger: submission.
|
From Agentic-News.ai
Agentic-AI industry signal we're tracking — launches, releases, and research from across the ecosystem. The directory rubric hasn't scored these yet; awareness now, evaluation next pass.
|
F5, Inc.
product launch
F5 announced the availability of Workforce AI Security within its F5 AI Security Platform. The agentless offering provides visibility and policy control over employee AI use and actions taken by agents on users' behalf. For those tracking agentic AI products, this signals a growing market for guardrails around assistants that call tools, manipulate data, and access enterprise systems. The product's value will depend on whether policy controls can stop risky actions without blocking useful automation.
Via Agentic-News.ai — Market Screener. Read: https://www.marketscreener.com/news/f5-inc-announces-availability-of-f5-workforce-ai-security-within-f5-ai-security-platform-ce785bd9d181f326
|
|
Casepoint
product launch
Casepoint launched Casepoint IQ, a platform-wide AI framework combining autonomous agents, generative assistants, predictive coding and MCP. The launch brings newer agent capabilities together with Casepoint's existing tools for e-discovery, legal holds, FOIA and investigations. For those tracking agentic AI products, this signals a push to make agents part of established legal workflows rather than standalone chat tools. The key question is which actions Casepoint IQ can complete without human intervention and how much oversight customers retain.
Via Agentic-News.ai — LawSites. Read: https://www.lawnext.com/2026/09/casepoint-launches-casepoint-iq-an-ai-framework-spanning-its-full-platform-from-new-autonomous-agents-and-assistive-ai-to-legacy-predictive-coding.html
|
|
RavenDB
product launch
RavenDB launched Quill, a context layer intended to prepare SQL databases for production AI agents without moving the system of record. The company says the product avoids a custom architecture while giving agents access to enterprise data. For those tracking agentic AI products, this targets one of the biggest barriers to deployment: connecting agents to existing systems safely. The important detail is how Quill handles permissions, context and agent actions across legacy SQL environments.
Via Agentic-News.ai — dzone.com. Read: https://dzone.com/articles/ravendb-launches-quill-to-bring-production-ai-agen
|
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.
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.
GitHub Copilot helps you write, review, and adapt code directly in GitHub, your IDE, and the terminal. It supports everything from inline suggestions to agentic coding workflows with broader model choices and enterprise controls.
- 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.
- OpenHands · 18/36 · Adaptive Collaborator · L2
OpenHands (formerly OpenDevin) is a fully autonomous open-source AI coding agent. MIT-licensed core, plans + executes Python actions via CodeAct, uses browser + terminal + files. ~72% on SWE-bench Verified with Sonnet 4.5 via the OpenHands Software Agent SDK (arXiv:2511.03690).
What operators are searching for this week
A week's demand signal — what operators are typing into the directory's search. Suggestion-chip defaults + off-topic / greetings filtered.
- "best coding agent"
- "Free video generator"
- "AI agent to triage and reply to my email inbox"
- "best coding agent for a large existing codebase"
- "tools to automate customer support ticket triage"
Learn: Action Capability: can it actually DO things (run code, send, edit files), or only suggest?
Action Capability is the gap between a tool that talks about work and one that can do the work. A chatbot can draft an email, outline a script, or tell you what command to run. An agent with action capability can send the email, execute the command, edit the file, or call the API itself. That difference is what separates a real agent from a wrapper around a model.
Check for direct tool execution. Look for a live action log, permission prompts before each side effect, and a clear list of actions the system can take without copying output into another app. If it only produces text for a human to paste somewhere else, action capability is low.
How our 9-dimension rubric works →
One tool worth testing
Upsolve AI — Test Upsolve AI if your data team needs agents that can answer questions against warehouse structure, semantic models, and institutional context. Its new Agent Studio positioning emphasizes context-verified answers, lineage, and usage signals rather than generic data chat, making it worth a focused evaluation now. Compare it with your current analytics assistant on a 30-minute pilot: ask it to answer three recurring business questions, then inspect the supporting context and lineage behind each response.
Our pick: Claude Code
The use case: coding agents.
Tops our independent /36 — the tiebreaker over Cursor: Continuity 3 vs 1. Pricing: Per-seat (usage per member, NOT pooled).
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 →
|