Start Debugging

Tag: mcp

30 posts · Page 2 of 3

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.

2026-05-25 mcp claude-code ai-agents

How to Reduce the Number of MCP Tools Claude Loads to Avoid the Tool-Use Limit

Five MCP servers can burn 55k tokens and wreck tool-selection accuracy before Claude does any work. How to fix it in Claude Code 2.1.x with ENABLE_TOOL_SEARCH and alwaysLoad, on the raw API with the tool search tool and defer_loading, and on the MCP connector with mcp_toolset. Anchored to claude-opus-4-7, claude-sonnet-4-6, and the 20251119 tool search variants.

2026-05-23 errors mcp llm

Fix: Extra Inputs Are Not Permitted on a Tool Call With a Structured Argument

Your agent's tool call fails with Pydantic's 'Extra inputs are not permitted'. The model added a field your structured argument forbids. Turn on strict tool use so the grammar blocks it, relax the validator, or recover in the loop.

2026-05-22 mcp claude-code ai-agents

Fix: `ECONNREFUSED` When a Local MCP Server Starts Before the Client Is Ready

ECONNREFUSED from an MCP client means nothing was listening on that host:port yet. Fix the startup race, the localhost IPv4/IPv6 trap, and wrong-port mistakes for HTTP MCP servers.

2026-05-19 mcp claude-code ai-agents

Fix: Claude Code Reports `MCP server disconnected` Inside WSL

Why Claude Code shows 'MCP server disconnected' or 'Connection closed' for a working MCP server when launched from WSL2. Covers stdio spawning across the Windows/Linux boundary, npx and node ENOENT, mirrored networking for HTTP servers, VMMem reaping, and how to diagnose the right one with claude --debug.

2026-05-17 mcp ai-agents dotnet

dotnet new mcpserver Now Ships in the .NET 11 Preview 4 SDK

.NET 11 Preview 4 bundles the mcpserver project template directly into the SDK. No separate Microsoft.McpServer.ProjectTemplates install, no preview feed dance. Pick stdio or HTTP transport, opt into Native AOT, and dotnet new mcpserver -o MyServer is the whole setup.

2026-05-16 errors claude-code anthropic-sdk

Fix: Tool Call Arguments Did Not Match Schema in Anthropic Tool Use

Why your Claude tool call fails schema validation, in both flavours: the API rejecting your tool definition at request time, and Claude returning a tool_use block your runner cannot accept. Concrete fixes for each, with strict mode, oneOf/anyOf, additionalProperties, and the retry loop pattern.

2026-05-15 mcp claude-code ai-agents

Fix: MCP Server stdio Hang When Launched From Claude Code

Why your Model Context Protocol server gets stuck in 'connecting' from Claude Code 2.x and never registers any tools. Covers stdout pollution, the npx install prompt, MCP_TIMEOUT, buffered output, and WSL pitfalls, with verifiable repros.

2026-05-14 claude-code mcp ai-agents

How to Add Retrieval-Augmented Generation to a Claude Code Session

A 2026 walkthrough for wiring RAG into Claude Code 2.1.x: when agentic grep stops scaling, how to attach a hybrid BM25 + dense vector MCP server, how to wrap a retrieval CLI in a custom skill, and how Anthropic's contextual embeddings technique pushes recall above 92%. Anchored to claude-sonnet-4-6, claude-opus-4-7, and Claude Context 0.x.

2026-05-08 claude-code ai-agents agent-skills

How to Write a Claude Code Subagent That Runs Browser Tests

Build a project-scoped Claude Code subagent that drives Playwright in a real browser, scoped to its own MCP server so the main session never sees the 25 browser_* tools. Covers the .claude/agents/browser-tester.md frontmatter, mcpServers inline definition, allowed tool list, isolation: worktree, the Playwright Test Agents init flow, and the Sonnet-vs-Haiku model choice.