Model Context Protocol (MCP) Server Directory

August 2026 marks the point where agents stop being separate products and start being native features of the tools you already run. Salesforce's Agentforce lets agents perform CRM tasks in place of human users, and Atlassian's embedded agent Robo automates complex workflows inside Jira and Confluence. This briefing covers the shift from tools-people-operate to systems-agents-do-the-work, plus adoption, extension, and disablement in compliance-sensitive workflows.

Civic-tech nonprofit Code for India launched Code for a Billion – Bharat Agentic-AI Hackathon 2026 on August 15, 2026: a 90-day virtual event building agentic-AI projects for public good across education, health, climate, governance, and financial inclusion, developed in AgentFoundry.me. This briefing covers civic and public-sector agent deployment, India-first AI adoption, and how public-impact agents will be evaluated.

The 2026 enterprise guidance for adopting external AI agents is deceptively simple: start with low-risk, repetitive tasks — report generation, test scheduling — and put least-privilege access plus anomaly monitoring in place from day one, per NCSC-style recommendations. This briefing covers an agent onboarding policy, the external-agent permission model, and continuous anomaly detection that catches drift before it becomes a breach.

SUPERAGENT AI shipped version 3.0 on August 11, 2026, positioning itself as an AI business partner for insurance agencies rather than another dialer or CRM bolt-on. The release unifies inbound and outbound calling, campaigns, quoting data capture, call intelligence, producer training, public self-sign-up, and instant phone provisioning. This briefing covers vertical-agent economics, agentic quoting, and where human-in-the-loop remains non-negotiable for insurance compliance.

Inspired by Featured's July 2026 MCP server for PR agencies, this dispatch builds pr-media-mcp, a FastMCP TypeScript server that lets agents monitor press mentions, track journalist and outlet sentiment, manage pitch outreach queues, and draft response drafts. Read tools are always available; write tools — send pitch, update contact — are gated behind OAuth 2.0 scopes plus a human approval gate, and every action lands in an append-only audit trail.

Inspired by SUPERAGENT 3.0 (August 11, 2026), the AI business partner for insurance agencies, this dispatch builds agency-ops-mcp, a FastMCP TypeScript server exposing read-only quote data, policy and CRM lookup, and compliance status to agents. Write tools for quote generation and policy updates are gated behind OAuth scopes plus a human approval gate, and every action is written to an append-only audit trail.

The 2026 agent-browser wave (Cloudflare Kitesurf) and QF-Test 11.0.1's MCP server let Claude Code and GitHub Copilot plug into automated testing. This dispatch builds web-native-tester, a LangGraph workflow that drives a lightweight headless browser runtime, orchestrates web-platform tests via an MCP server, collects results, and routes failures into a human-fix loop with retry and regression tracking.

Code for India's Code for a Billion — Bharat Agentic-AI Hackathon 2026 (Aug 15, 2026) targets education, health, climate, governance, and financial inclusion. This dispatch builds civic-serve, a LangGraph workflow that turns public-service intents into governed agent actions: intake plus eligibility check, privacy-gated data access, multilingual output, human approval for entitlement-changing actions, and an append-only audit for public-sector transparency compliance.

Microsoft's June 30, 2026 security guidance formalizes the shift from read-only assistants to read-write operators: agents that draft email, create docs, and update calendars through MCP. The impact profile moves from biasing an output to triggering an action. This briefing covers read-write boundary design, least-privilege scopes, and approval gates enforced outside the model.

In 2026, tool names and descriptions became the agent's instruction context: a poisoned description is a system prompt written by the attacker. MCP tool poisoning abuses the protocol's discovery model, where every connected server contributes tokens to the agent's brain. Verification, description allowlists, and treating metadata as untrusted are the working defenses.

Two July 2026 incidents — claude.ai's Memory Heist and Noma Security's GitLost — proved agents with fetch and send capabilities are exfiltration devices. Both attacks share one spine: indirect prompt injection converted into data theft. Egress allowlists and fetch sandboxing are now the baseline controls for agentic systems.

DeepSeek's August 2026 release open-sourced the agent harness — tools, memory, orchestration, and eval loop — completing the commoditization of the agent stack. With Agent = Model + Harness and both halves open, differentiation moves to evals, data, and integrations. The make-vs-buy math has changed.