Model Context Protocol (MCP) Server Directory

The BenchLM August 2026 leaderboard is the deployment guide for agent builders: Claude Mythos 5 tops the composite at 83.2, Qwen3.8 Max leads open weights at 79.9, and MiniMax M3 sits at 68.8. This MCP server — benchlm-mcp — exposes that leaderboard to agents as governed tools: query model scores by benchmark, compare two models, and pick the cheapest model that clears a quality threshold. Built with FastMCP in TypeScript with inputSchema JSON, mcpServers config, and an API-key security guide.

AI agent startups raised roughly $1.8 billion across a dozen or more deals in July 2026, with average valuations up about 40% quarter over quarter. The leaders: Harvey AI's $200M Series C at a $2.1B valuation, Assort Health's $120M Series C at $1.2B, and Rime's $24M Series A for voice models — with Lovable, Glean, and Hebbia close behind. Almost all of the money funds agents that work for businesses. This briefing covers what the wave is funding, the voice-agent thesis, and what the pattern says about where the market is heading.

At I/O 2026, Google shipped agentic shopping features that complete purchases and place real phone calls to stores — including calling around to check inventory — marking the first time a major platform's consumer agent dials a real business and speaks to a real person. This briefing covers what the feature actually does, why crossing the calling line matters more than the feature itself, the honest limits (it is one narrow errand, not general personal calling), and the AI-to-AI future it opens.

The BenchLM August 2026 leaderboard shows open weights closing on the frontier: Claude Mythos 5 leads the composite at 83.2, Qwen3.8 Max leads the open-weight ranking at 79.9, and MiniMax M3 — a 428B-total, 23B-active native multimodal MoE released in June 2026 — sits at 68.8, roughly a 17% gap to the top. This briefing covers what the leaderboard actually says, why MiniMax M3 matters for open-weight builders, and the deployment math behind the numbers.

Hazmat (open-source, ~Aug 17 2026) runs AI coding agents in a dedicated least-privilege OS account so they cannot read SSH keys or cloud credentials, backed by a TLA+ formal spec, per-session macOS backups, and a session-scoped firewall. This dispatch builds agentcell, a LangGraph workflow that plans a session with declared paths, generates a per-session sandbox policy, preflights a backup, spawns any harness (Claude Code, Codex, OpenCode, Cursor) inside the account, and terminates on the first escape attempt.

Inspired by the MCP 2026-07-28 specification (released July 28, 2026, stewarded by AAIF under the Linux Foundation), this dispatch builds stateless-mcp, a Python FastMCP server on the new stateless core: initialize and Mcp-Session-Id are gone, Mcp-Method/Mcp-Name headers drive routing, results carry ttlMs/cacheScope cache hints, MRTR (SEP-2322) handles elicitation, and the Tasks extension (SEP-2663) powers poll-based tasks/get.

The MCP spec 2026-07-28, released July 28, 2026 by the Agentic AI Initiative under the Linux Foundation, is the fifth spec release and the one that made MCP serverless: the stateless core removes the initialize/initialized handshake and Mcp-Session-Id, moves method routing into Mcp-Method and Mcp-Name HTTP headers, and adds per-request _meta plus ttlMs/cacheScope caching. It also brings MRTR (SEP-2322), a Tasks extension (SEP-2663), and auth hardening via RFC 9207 and RFC 8707, alongside a deprecation policy for roots, sampling, and logging. Adoption has scaled to roughly 400M+ monthly SDK downloads, about 4x this year, near 250M per week.

Inspired by Cloudflare's August 5, 2026 Identity-Aware AI Gateway launch — which ties every outbound AI request to a verified Access identity via cf.user_id — plus the August 14, 2026 Cloudflare One MCP traffic detection wave (is_mcp selector, MCP Portal classification), this dispatch builds cloudflare-one-gateway-mcp, a FastMCP TypeScript server that registers agent identities, attaches identity headers, queries per-identity usage, sets model policies, and inspects detected MCP traffic.

The Agent Plugins 1.0 spec, published August 6, 2026, packages agent skills and MCP servers into a single portable plugin: a plugin.json manifest, a skills/ folder, and an mcp.json, designed to run across VS Code, Cursor, GitHub Copilot, ChatGPT, Codex, and Kiro. Vercel drafted the spec with input from Amazon, Cursor, Microsoft, and OpenAI, and Google joined on August 6 as a core maintainer under the Linux Foundation AAIF. GitHub shipped support on August 12 in VS Code, Copilot CLI, and the Copilot SDK, with managed-settings.json controlling enabledPlugins and strictKnownMarketplaces.

Cloudflare's Agents Week in August 2026 shipped 20+ launches that give AI agents the two things they need to be trusted with real work: money and identity. Cloudflare Wallets and cloudflare.pay (handle reservation on August 4, 2026, full banking later) let agents buy within human-set limits via the x402 machine-to-machine payment protocol, while the Identity-Aware AI Gateway went GA on August 5, 2026 to attach verified identity to every outbound AI request. DeepSeek V4 Flash/Pro 0813 also landed on Workers AI on August 15, 2026 with a 1,048,576-token context window.

OpenAI shipped cross-model delegation in Codex Multi Agents v2 (Aug 15, 2026): GPT-5.6 Sol orchestrates while delegating narrow tasks to cheaper GPT-5.6 Luna pure subagents that cannot spawn more agents, with guidance (Provencher) capping fan-out at 6-8 subagents. This dispatch builds modelrouter, a LangGraph workflow implementing capability-tier routing: an orchestrator decomposes a job, routes each task to the cheapest capable tier, enforces a max subagent count, and uses a quality gate to re-escalate failed tasks to a higher tier.

Cloudflare Agents Week (Aug 4-15, 2026) launched Cloudflare Wallets and cloudflare.pay on the x402 protocol so agents can hold verifiable identity and purchase within human-set limits, plus an Identity-Aware AI Gateway (Aug 5, 2026) attaching verified identity to every outbound AI request. This dispatch builds machpay, a LangGraph payment workflow where an agent requests a purchase, the workflow validates the request against a human-set spend ceiling, checks wallet balance, settles via x402 in a single idempotent request, and logs every spend line to an audit ledger with identity attribution.