Start Debugging

Tag: mcp

79 posts · Page 6 of 8

2026-06-16 cursor ai-agents mcp

How to Gate Which Cursor SDK Tool Calls Run Automatically With Auto-Review and permissions.json

By default a local Cursor SDK agent runs every tool call without asking. Set local.autoReview to route Shell, MCP, and Fetch calls through the classifier, then steer it with the autoRun block in permissions.json. With code, the three-step evaluation order, and why none of it is a security boundary.

2026-06-15 cursor ai-agents typescript

How to Persist Cursor SDK Agent State Across Restarts (SQLite vs JSONL vs a Custom LocalAgentStore)

The Cursor SDK already persists agent state to disk so Agent.resume() can pick a conversation back up after a crash. This walks the SqliteLocalAgentStore default, the JsonlLocalAgentStore you can commit to git, and how to implement the LocalAgentStore interface for Postgres, Redis, or an in-memory CI store.

2026-06-14 cursor ai-agents mcp

How to Expose Your Own Functions to a Cursor SDK Agent With local.customTools (Instead of a Separate MCP Server)

Pass local.customTools to a Cursor SDK agent and the model calls your in-process functions through the built-in custom-user-tools MCP server. No stdio handshake, no separate process, no transport bugs. Local agents only: cloud agents throw ConfigurationError.

2026-06-07 github-copilot copilot-sdk ai-agents

GitHub Copilot SDK Hits GA: Embed Copilot's Agent Runtime in Your Own C# Apps

At Build 2026 GitHub shipped Copilot SDK 1.0 GA with a first-class .NET package. You can now drive the same planning, tool-calling, and multi-turn agent runtime from C# code, BYOK included.

2026-06-05 comparison ai-agents microsoft-agent-framework

Microsoft Agent Framework vs LangChain vs LlamaIndex in 2026

All three hit 1.0. Pick Microsoft Agent Framework if you live in Azure and .NET, LangChain/LangGraph for vendor-neutral graph orchestration, LlamaIndex for retrieval-grounded agents.

2026-06-04 comparison mcp llm

MCP vs OpenAPI Plugins vs Custom Tool Calling for AI Agents: Which Should You Pick in 2026?

Use custom tool calling for one app you own end to end, MCP for any integration you want reused across Claude Code, Cursor, and ChatGPT, and OpenAPI plugins only as a bridge when you already have a spec. MCP is the cross-client standard in 2026; plugins are legacy.

2026-06-01 errors mcp claude-code

Fix: MCP Servers Stopped Working After a Claude Desktop Update on Windows

After an MSIX update, Claude Desktop on Windows reads claude_desktop_config.json from a virtualized path while Edit Config opens the old %APPDATA% one. Edit the file under AppData\Local\Packages\Claude_pzs8sxrjxfjjc and restart.

2026-05-31 errors mcp claude-code

Fix: GitHub MCP server tool calls fail silently when the PAT isn't passed

GitHub MCP tools show up but every call returns empty or 'Bad credentials'? The token is unset. Put the PAT in the env block, verify with curl, done.

2026-05-28 dart flutter mcp

The Dart and Flutter MCP server: one command to give Claude Code your running Flutter app

Dart 3.12 ships dart mcp-server, the official MCP bridge into the Dart and Flutter toolchain. Register it once in Claude Code, Cursor, or Codex CLI and your agent gets hot reload, pub.dev search, and live widget introspection without copy-pasting a DTD URI.

2026-05-28 mcp claude-code ai-agents

Fix: HTTP MCP Server URL Won't Connect in Claude Desktop (stdio vs HTTP Transport)

Claude Desktop's claude_desktop_config.json only validates stdio servers. Drop a 'url' field in and it silently strips the entry, crashes on startup, or boots with zero tools. Use a custom connector for remote URLs and mcp-remote as a stdio bridge for local HTTP servers.