Faiz Writes

Faiz Writes

Notes on MCP servers, OpenClaw, AI security, agent workflows, and the practical details that show up while building software.

Read latest Browse archive

Featured note

MCP servers that do one thing well

Tool boundaries, traceable actions, and why boring interfaces make better agents.

Audit trail

Permission checked
Tool call logged
Result inspected

OpenClaw

Repeatable local builds April notes

Practical notes from software systems, agent tooling, and deployment work.

May 10, 2026 · MCP servers

MCP servers that do one thing well

Narrow tools, boring data, and enough trace evidence for a human to replay what happened after an agent run.

Read article

April 18, 2026 · OpenClaw

OpenClaw notes from a repeatable build

What started as a local setup became a checklist for making agentic workflows easier to reproduce.

Read article

March 27, 2026 · AI security

AI security starts with boring boundaries

Most safety work in small tools is permission design, logging, and refusing to blur trust zones.

Read article

Archive

Recent notes, experiments, and debugging writeups.

May 15, 2026 Hello, world. First post May 10, 2026 MCP servers that do one thing well MCP servers April 18, 2026 OpenClaw notes from a repeatable build OpenClaw March 27, 2026 AI security starts with boring boundaries AI security February 21, 2026 A practical audit trail for AI tools Agents January 16, 2026 Shipping static previews on Cloudflare Pages Deployment December 8, 2025 Local agents, remote services, and where I draw the line Workflow