MCP

Figma has restricted access to its MCP (Model Context Protocol) interface to a whitelist of approved clients, with Pi among those excluded. The change means third-party AI tools not on Figma's approved list can no longer connect directly to Figma through MCP. Commenters are debating whether the move reflects security and stability concerns or an effort to tighten control over which AI assistants can integrate with Figma's design platform.

Earendil has published a blog post titled 'You Said No MCP', which is drawing strong discussion on Hacker News. The piece appears to address the Model Context Protocol, the emerging standard for connecting AI assistants to external tools and data, and the company's position on adopting it. Readers are debating the arguments in the comments.

A new open-source project called context-mode, written in TypeScript and hosted on GitHub, targets context window optimization for AI coding agents. It claims to sandbox tool output for a 98% reduction in token usage, persist session memory, and enforce routing across 17 platforms using MCP and hooks. Developers are taking notice as context management becomes a growing pain point for agent workflows.

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.

A new tool has been released that lets AI assistants scrape business data from Google Maps using the Model Context Protocol. The tool, showcased on Hacker News under the 'Show HN' format, connects Google Maps listings directly to language models so they can pull places, reviews and contact details on request. Early attention is coming from developers interested in automation and data-extraction workflows built around MCP.

A new blog post from networking company Earendil, titled 'You Said No MCP,' has drawn heavy attention on Hacker News, gathering over 500 points and nearly 300 comments. The piece appears to address decisions around adopting or rejecting the Model Context Protocol, an emerging standard for connecting AI systems to tools and data, prompting lively argument among developers about when saying no to MCP makes sense.

Stablecoin issuer Tether has released beta command-line interface and MCP wallet tools that let users manage Tether holdings locally and keep custody of their own keys. The move is aimed at users who prefer self-custody over leaving assets on exchanges or custodial platforms, and the tools are available in beta while feedback is gathered from the crypto community.

Earendil has published a new post explaining why its Pi.dev product does not support MCP, the Model Context Protocol that has become a common standard for connecting AI assistants to external tools. The piece defends the decision to skip the protocol, and the argument is drawing attention and debate among developers following the discussion.

Google's Agent Payments Protocol (AP2), introduced for AI-agent-driven purchases, is drawing renewed debate in developer circles. Commenters argue AP2 standardizes how AI agents authorize and initiate payments, but does not solve settlement — the clearing of funds between parties. That still depends on existing financial rails or crypto. The discussion suggests agent commerce will need both layers working together before autonomous purchasing goes mainstream.

Montgomery County Public Schools in Maryland are raising concerns about proposed changes to a federal internet funding program that could cost the district roughly $1.5 million. Officials say the loss would affect efforts to keep students connected, and district leaders are watching the federal policy debate closely as they plan budgets.

TikTok has opened its advertising network of nearly 400,000 apps to US advertisers, saying that advertiser usage of its MCP tools rose more than 200% since launch. The rollout also includes Buy Direct checkout and updates to its Smart+ campaign automation. The company has not given start dates for most of the new tools, so advertisers are watching to see when full access arrives.

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.

The National Stock Exchange of India's MCP initiative has drawn attention from developers who work with NSE market data. The Model Context Protocol is designed to standardize how large language models and AI tools connect to external data sources, and applying it to NSE data would let AI systems access standardized Indian stock market information. Observers familiar with the exchange's data see practical potential in the move.

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.

Commentary circulating in developer and crypto circles argues that NVIDIA's attestation capabilities change how compute work can be verified. The piece, tagged around AI, MCP and blockchain, frames 'compute settlement against proof' as a new question for anyone building systems that must trust remote hardware. Readers appear to be debating whether hardware-level attestation can replace economic or cryptographic proofs of computation.

Tuskira has released an open source AI agent runtime gateway designed to let teams observe, govern and switch between large language models and MCP tools without rewiring their agents. The announcement, distributed via Business Wire, targets enterprises building AI agents that need model flexibility, oversight and control. Details on adoption and community response are limited so far, as the launch is newly announced.

WireMCP, a Model Context Protocol server, gives large language models the ability to analyze live network traffic. Built on Wireshark's tshark tool, it captures and processes network data so AI assistants can inspect packets and assist with network diagnostics and security analysis in real time.

A new open-source tool called Google Maps Scraper MCP has been released, allowing developers to extract location and business data from Google Maps through the Model Context Protocol. The launch is being shared and discussed in developer communities, where users are weighing its usefulness for AI-driven workflows against questions around scraping legality and terms of service.

GPTZero, an AI-detection tool created by a former student of writing teacher John McPhee, has grown into a business valued at around $30 million. Its founder says the company does not want to act as a 'policeman of the Internet', positioning the tool as a service for detecting AI-generated text rather than an enforcer of online rules. The story highlights how quickly demand for AI-detection has grown in education and publishing.

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.

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.

Mario Zechner, creator of the pi.dev coding assistant, spent over a year publicly refusing to support Anthropic's Model Context Protocol, calling the stance a matter of philosophy rather than an unfinished feature. The pi.dev homepage once declared outright that Pi does not support MCP. That position has now changed, with MCP support added despite the earlier dismissals.

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.

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.

Earendil's Pi, an AI coding assistant, previously declined to support the Model Context Protocol on its own website but is now integrating it into its core. The shift has prompted discussion of what MCP is and how the assistant's position on the open protocol changed, drawing interest from developers following AI tooling standards.

McPartlin and Brant led the Newton girls tennis team at a regional tournament, according to the Newton Daily News. The pair turned in the top performances for Newton as the team competed against other schools in the regional event. Further details on individual results and the team's final placement were not included in the report.

Cloudflare has introduced paid access to MCP tools, meaning AI agents using the Model Context Protocol can now be charged for the services and data they call. The move raises the question of who controls and authorises an agent's spending when tools cost money. Discussion is focused on billing, budgets and oversight for autonomous agents.

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.