MCP servers

Figma has limited access to its MCP (Model Context Protocol) server to a whitelist of approved clients, with Pi reportedly left off the list. Developers integrating Figma with AI tools through MCP now need to check whether their client is supported, and the exclusion of Pi has prompted discussion about how openly Figma will keep its AI integrations available.

OpenAI has streamlined the process for setting up custom MCP (Model Context Protocol) servers within ChatGPT, reducing the configuration steps required to connect external tools and data sources. Developers discussing the change note it lowers the barrier for building custom integrations, though some point out that connecting remote servers still requires careful handling of permissions and security.

The Model Context Protocol project's servers repository, written in TypeScript, is gaining traction among developers. It hosts reference server implementations for MCP, an open standard for connecting AI applications to external data sources and tools. Interest appears tied to the broader boom in AI tooling and agent integrations.

A developer has released mcp-footprint, an open-source Node.js command-line tool that analyses how large tool definitions are in a captured Model Context Protocol catalog. It compares MCP tool definitions from saved tools/list responses, letting developers see which servers define unusually heavy or bloated tools. The project is being shared in software and development communities as MCP tooling adoption grows.

A developer reports building 35 MCP servers in two weeks, along with a Google Sheets add-on and a complete x402 payment stack. All of it works: servers are deployed, paywalls respond, and APIs return correct data. Revenue so far is zero, highlighting the gap between technical shipping and actual market demand.

Major AI platforms reportedly use the same verification step before listing an MCP (Model Context Protocol) server: confirming ownership of its domain. A security-focused team says it now runs checks on every MCP server it grades and reviewed 20 popular ones, raising questions about whether domain verification alone is enough to catch malicious or insecure servers in the fast-growing agent ecosystem.

Developers are commenting on the overwhelming pace of open-source AI releases, with new agent frameworks, MCP servers and machine learning tools appearing every week. Discussion centres on which fast-growing projects are worth attention and how hard it has become for engineers and hobbyists to stay current in the field.

A developer who runs AgentoolRank, one of the directories used for listing MCP servers and AI agent tools, has published a comparison table of where to list such tools, covering free versus paid options along with pricing and review times. The disclosure of their own stake in one of the listed directories is drawing attention to the transparency of the comparison.

A developer argues that most MCP servers are tested minimally — one client connected, a few tools called by hand, then shipped. The piece proposes soak-testing MCP servers before AI agents begin relying on them at scale, stressing the gap between casual manual checks and the continuous, unpredictable load real agent traffic creates. The discussion touches on testing practices, open-source tooling and engineering habits in the fast-moving AI ecosystem.

Flexport has launched an MCP Server that allows AI agents to book freight directly through its logistics platform. The move positions the freight forwarder at the front of efforts to automate supply chain booking with agentic AI, and was reported by FreightWaves. It could let corporate systems and AI assistants handle shipping arrangements without human brokers.

Figma has limited access to its Model Context Protocol server to a whitelist of approved clients, excluding Pi. The move, announced by a Figma employee, restricts which AI-powered development tools can connect to Figma's API for design data. Developers are debating whether the tighter controls protect the platform or close off an open ecosystem for AI tooling.

NorthCinder is an open-source MCP server that lets users compare products across stores of their choosing. According to its README, the tool requires a signed, single-use buyer approval tied to one exact offer before any checkout can proceed. The project is being shared in information security circles and discussed as an example of adding safety controls to AI agent purchasing.

A developer has published a guide for building a Model Context Protocol (MCP) server that serves documented basketball player data through a typed Sportmicro API integration, written in TypeScript. The tutorial walks through exposing the player insights endpoint so MCP clients can query structured basketball statistics. It is drawing attention from developers interested in connecting sports data to AI tooling.