cd /news/ai-products/anthropic-announces-claude-marketpla… · home › topics › ai-products › article
[ARTICLE · art-139911] src=cryptobriefing.com ↗ pub= topic=ai-products verified=true sentiment=↑ positive

Anthropic announces Claude Marketplace as hub for plugins and connectors

Anthropic launched a developer submission portal on September 25, 2026, giving builders on Claude's Pro, Max, Team, and Enterprise plans a formal path to list tools in the Claude Marketplace, which the company announced on September 23, 2026 and which already lists over 2,000 plugins and connectors. Developers can submit either a single remote MCP connector or a full GitHub-hosted plugin bundle, both routed through automated validation, safety scans, and review status tracking, with post-approval usage analytics. The portal replaces a largely manual submission process and centers on the Model Context Protocol, Anthropic's open standard for connecting AI applications to external tools and data sources.

by read3 min views1 publishedSep 25, 2026
Anthropic announces Claude Marketplace as hub for plugins and connectors
Image: Cryptobriefing (auto-discovered)

Anthropic's new developer portal gives builders a structured path to list tools in the Claude Marketplace, complete with safety scans and usage analytics

Two days after launching a marketplace stocked with over 2,000 plugins and connectors, Anthropic followed up with the infrastructure developers actually need to add to it. A new submission portal, live as of September 25, 2026, gives builders on Claude’s paid plans a formal, trackable way to get their tools into the Claude directory.

What the portal actually does #

Builders on Claude’s Pro, Max, Team, and Enterprise plans can submit through two distinct paths. The first is a single remote MCP connector, useful for developers who want to expose one specific tool or data source. The second is a full plugin bundle hosted on GitHub, suited for more comprehensive integrations that package multiple components together.

Both routes run through the same set of guardrails. Submissions go through automated validation, safety scans, and review status tracking before anything reaches the Claude directory. Once a plugin clears approval, developers get access to post-launch usage analytics, so they can see how often their connector is actually being used rather than guessing in the dark.

The Model Context Protocol, or MCP, sits at the center of all of this. Anthropic designed MCP as an open standard for connecting AI applications to external tools and data sources securely. Instead of every integration requiring custom plumbing, MCP provides a shared interface that works consistently across the ecosystem.

Context: the Claude Marketplace and what came before #

The portal’s arrival makes more sense when you consider what came two days earlier. On September 23, 2026, Anthropic announced the Claude Marketplace, a centralized hub for plugins, connectors, agents, and partner services. By the time the developer portal launched, that marketplace was already listing over 2,000 available tools.

AI, tech, and the markets they move—in one daily briefing.

Daily. Free. Join 34,000+ readers across crypto, finance, and policy.

The marketplace already includes connections to platforms like Google Drive and Atlassian products. Before this portal existed, developers had to navigate a largely manual submission process, with limited visibility into where their submission stood or why it might have stalled. Automated validation means faster turnaround on clear-cut submissions. Review status tracking means developers are not emailing into a void. Safety scans mean Anthropic gets a scalable quality control mechanism instead of reviewing everything by hand.

What developers and organizations should watch #

For developers, the immediate practical implication is straightforward: if you have been waiting for a cleaner path to get a Claude integration in front of users, that path now exists. The GitHub-hosted bundle option in particular gives developers something familiar to work with, since most teams already manage their code there. The safety scan requirement is worth reading carefully before submitting. Anthropic has not published a detailed rubric for what gets flagged, and the automated nature of the process means edge cases will inevitably surface. Developers building connectors that touch sensitive data or require elevated permissions should expect that the review process will look hardest at exactly those integrations.

Disclosure: This article was edited by Diego Almada Lopez. For more information on how we create and review content, see our

Editorial Policy.

── more in #ai-products 4 stories · sorted by recency
── more on @anthropic 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/anthropic-announces-…] indexed:0 read:3min 2026-09-25 · —