A new protocol-level defense against tool poisoning in the Model Context Protocol (MCP) has been proposed, using signed tool manifests to detect unauthorized changes to tool descriptions between appro…
The Linux Foundation working group released the Agentic Resource Discovery (ARD) specification, a draft discovery layer that allows domains to advertise agent capabilities via a manifest at /.well-kno…
Developer mrzk released Charted, a zero-dependency Python charting library that outputs SVG, and later built an MCP server to let AI agents render charts inline. The library was designed to avoid the …
Lightpanda released a native agent that achieves 0.830 accuracy on GAIA and 0.697 on AssistantBench, cutting task completion time to 86 seconds on GAIA by eliminating MCP serialization overhead. The i…
Spronta released Crawlie, a free open-source SEO audit tool that crawls websites for broken links, redirects, missing metadata, and over 40 SEO and generative-engine optimization checks. The tool incl…
A new technique called tool search reduces token usage in AI agents by loading only tool names upfront instead of full schemas, cutting context from 60k tokens to 2-3k. The method uses a dedicated sea…
Google's Apigee now converts any REST API into a governed MCP tool with token-aware rate limiting, addressing security risks from over 8,000 exposed MCP instances reported in February 2026. The move a…
Sanity added a give_feedback MCP tool to its server, enabling AI agents to report bugs, confusing outputs, and missing capabilities directly. Over 20,000 agents have made three million tool calls sinc…
Cursor's June 2026 SDK update introduces custom tools, nested subagents, auto-review safety gates, and custom persistence stores, transforming the IDE assistant into a deployable agent runtime for CI/…
Go's runtime is well-suited for production AI agents, which are long-running, concurrent, I/O-bound processes. The language's goroutines, channels, and single-binary deployment enable teams to build a…
A developer automated database backups across a fleet of servers using the remote-agents MCP server, which connects each host to an encrypted relay room. The setup includes a Postgres primary, two str…
Amazon Quick, an AI assistant, gained the ability to control IFTTT automations through a custom proxy built by a developer. The proxy bridges the gap between Quick's stdio-based MCP transport and IFTT…
A new open-source CLI tool, mcp-customs, scans MCP servers for security risks before installation, running fully offline with no telemetry. It checks for issues like shell injection, path traversal, a…
James Miller (via OpenClaw) proposes a badge system for measuring AI agent success in production, focusing on transparency, safety, sandboxing, and efficiency. The system uses wrapper functions, injec…
A developer identified a new class of security failure in agentic AI systems using the Model Context Protocol (MCP), where authority delegation between components can execute unauthorized actions with…
DriftGuard offers a CI gate that catches silent MCP contract drift before merge. The tool scans mcp.json files, compares tool schemas, and blocks pull requests when endpoints are missing or changed. A…
DataGrout launched Data, a suite of deterministic JSON manipulation tools for AI agents, exposed as MCP tools. The tools allow agents to filter, sort, aggregate, merge, flatten, and map JSON payloads …
Elastic has launched Agent Builder, a persistent memory layer for AI agents built on Elasticsearch, achieving a recall of 0.89 on a QA evaluation. The system uses three memory types from cognitive sci…
A developer built AgentMemo, a free REST API that gives AI agents persistent, semantic memory. The API allows agents to store, retrieve, and forget memories based on meaning rather than keywords, and …
A developer describes the evolution from prompt engineering to context engineering and finally to building a 'harness'—a persistent structure of files, memory, and tool access that enables AI models t…