Model Context Protocol (MCP) Server Directory

Open-source Hazmat, released on GitHub around August 17, 2026, wraps Claude Code, Codex, OpenCode, and Cursor Agent in a dedicated OS account so coding agents run with least privilege: only the declared project directory is shared and a per-session firewall rule caps network access. This briefing walks the macOS containment flow, the ~5.5% TLA+ formal specification, the demo that proves private keys stay unreadable, and the ROI of OS-account sandboxing versus breach risk.

Zeplyn's Schwab integration (Aug 12, 2026) showed agentic account opening cuts NIGO by 80% — but regulated account opening needs compliance rails, not just automation. This workflow builds account-open, a LangGraph pipeline that drafts the entire account-opening workflow, runs KYC/AML and eligibility checks, routes every uncertain field to a human approval gate, and writes an immutable audit trail before submission. It is the assisted-automation pattern for regulated finance.

On August 12, 2026, SKALE Labs launched Agent Pit — a paper-trading prediction-market sandbox built on its zero-gas blockchain and modeled on Polymarket's structure, so builders can train and validate AI agents before deploying them to live markets. This briefing covers why prediction markets are the natural proving ground for agent strategy, how paper trading prevents the live-money failure loop, and the validation discipline — benchmark, sandbox, then go live with caps.

On August 14, 2026, Chainlink unveiled Chainlink for Agents — an infrastructure platform that gives autonomous AI agents verified data, protected execution, and cross-chain settlement via CCIP. The platform answers the three problems every agent economy hits: agents cannot trust scraped web data, cannot pay for services autonomously, and cannot move value across blockchains. This briefing covers the agent-data trust problem, the CCIP settlement layer, and what protected computation means for agent safety.

SKALE's Agent Pit (Aug 12, 2026) established paper trading as the training ground for prediction-market agents. This MCP server — polymarket-mcp — gives agents the same discipline as a tool surface: read markets, order books, and positions in paper mode by default, then graduate to live orders only behind an explicit mode flag with position caps. Built with FastMCP in TypeScript with inputSchema JSON, mcpServers config, and an API-key security guide.

On August 14, 2026, Octane launched an AI operating system built for convenience-store operators — an AI workforce that goes beyond dashboards to complete work across store operations, with the goal of making stores self-operating. This briefing covers what an AI workforce actually does in a c-store, why retail is the perfect agent proving ground, and the deployment discipline — start with back-office autonomy, keep humans for exceptions.

On August 13, 2026, DISCO launched Advanced Research for general availability: an agentic AI application for eDiscovery and fact investigation that adds autonomous multi-step reasoning and provides detailed visibility into its decision-making. For a profession built on defensibility, explainability is the feature that matters. This briefing covers what agentic research changes in eDiscovery, why the reasoning trail is the compliance surface, and how legal teams should validate agent findings.

Chainlink for Agents (Aug 14, 2026) made CCIP cross-chain settlement a first-class agent capability — which means every agent transfer is now a governance decision. This workflow builds settle-bot, a LangGraph pipeline that sits between an agent and its money: it verifies the transfer against verified price feeds, checks per-transaction caps and policy, routes value movement through a human approval gate, and writes an immutable audit record before and after settlement.

On August 12, 2026, Ahrefs launched Letaido, an agent-powered marketing workspace built to handle the recurring research, reporting, and monitoring tasks that marketing teams and agencies still do by hand every week. This briefing covers what an agent workspace is, why recurring work is the right first target for marketing agents, and the trust pattern — agents own the routine, humans own the decisions.

Chainlink for Agents (Aug 14, 2026) made verified data feeds and CCIP cross-chain settlement first-class resources for autonomous AI agents. This MCP server — chainlink-mcp — exposes those resources as governed tools: read price feeds, check token balances, inspect cross-chain transfer status, and submit CCIP transfers behind an explicit approval gate. Built with FastMCP in TypeScript with full inputSchema JSON definitions, an mcpServers config, and an OAuth 2.0 / API-key security guide.

DeepSeek's V4-Pro hit general availability on August 16, 2026 at 16:00 UTC, bringing adaptive reasoning profiles (low / standard / maximum) that route compute to task complexity, native OpenAI Responses API support, one-click Codex setup, and a tiered peak/off-peak pricing model where off-peak is exactly half of peak. This briefing covers the compute-routing economics, benchmark positioning against V4 Flash, and when each reasoning profile is the right call.

At Inspire 2026, Alteryx unveiled Agent Studio plus an MCP Server that lets business analysts convert existing data workflows and business logic into autonomous agents without IT involvement. Agents deploy to Slack, Microsoft Teams, and external AI models through the MCP Server. This briefing covers the IT-bottleneck elimination, what analyst-built agents mean for governance, and the unit economics of moving pipeline work to agent-driven automation.