MCP & AI Agents
Model Context Protocol, AI agent integration, and codebase context for LLMs
Your MCP Server Is Probably Not Being Called
We ran the same MCP servers and questions on two agent harnesses. Under Claude Code most tools were barely called at all. Here is the measured cause of it.
Giving AI Coding Agents Real Codebase Context
Codebase context for AI agents turns one index into 10 task-shaped MCP tools, cutting real agent-loop output tokens 31.6% on Codex. See how structured context works, try repowise.
Claude Code Context Management for Large Codebases
Claude Code large codebase work fails for a simple reason: the model can only reason over what fits in its context window. A big repo does not fit. A good…
Cursor Codebase Context: MCP Setup That Actually Helps
Cursor MCP works best when you stop treating it like a magic search box and start treating it like a source of structured codebase context. Cursor’s own docs…
What Model Context Protocol actually sends to Claude Code
See how model context protocol sends structured repo data to Claude Code, with a wire-level example and 7 tools to inspect.
Same refactor, 27× fewer tokens with Repowise MCP
See how Repowise MCP cut the same refactor to 27× fewer tokens, with transcript and tool-call traces showing the exact savings.
When an MCP tool should return raw text, not answers
A practical mcp tools design rule: return raw evidence when the model needs to inspect files, symbols, or decisions. See the boundary in Repowise.
Why we ship a graph-aware MCP server instead of file readers
Graph aware mcp cuts grep loops: resolve callers, dependents, and review impact in one hop. See the token and latency math.
Task-Shaped MCP Tools Beat Entity CRUD for Code Agents
See mcp tools design on a real regression: task-shaped tools cut re-reading and context loss, with 49% fewer calls and 27× fewer tokens.
Ten MCP Tools That Make AI Agents Actually Useful for Code
The current state of AI-assisted engineering feels like a paradox. We have Large Language Models (LLMs) with massive context windows, some spanning millions o...
Give Your AI Agent Codebase Context Without Stuffing the Prompt
The engineering community is currently caught in a 'context arms race.' As LLM providers announce increasingly massive context windows, moving from 32k to 200...
How to Set Up an MCP Server for Claude Code, Cursor, and Cline
The fundamental bottleneck in AI-assisted engineering isn't the model's reasoning capability; it’s the context window. Even with million-token windows, stuff...