json
30 articles about json in AI news
AgentShare MCP Registry: Discover and List MCP Servers via agent.json and
AgentShare MCP Registry provides a curated, machine-readable directory via agent.json for Claude Code users. Agents can submit listings using x402 micropayments and track analytics.
Build a Bulletproof Claude Code JSONL Parser
Learn 3 battle-tested patterns for parsing Claude Code's JSONL session files under ~/.claude/projects/, including tolerant whitelists, versioned derived data, and toWellFormed() string normalization.
MCP Becomes USB for AI: 3 Primitives, JSON-RPC 2.0, 50+ Servers
Anthropic's MCP standardizes AI tool connections via JSON-RPC 2.0 with three primitives. Over 50 community servers exist, making it the USB for AI.
How Structured JSON Inputs Eliminated Hallucinations in a Fine-Tuned 7B Code Model
A developer fine-tuned a 7B code model on consumer hardware to generate Laravel PHP files. Hallucinations persisted until prompts were replaced with structured JSON specs, which eliminated ambiguous gap-filling errors and reduced debugging time dramatically.
How to Build Interactive Apps with Claude Code Using JSON as a Bridge
A developer built a music maker where Claude generates beats via JSON, showing how to create collaborative AI tools without complex APIs.
Stop Clicking 'Approve': A .claude/settings.json Template for 80% Fewer
A practical guide to configuring Claude Code's permissions file to auto-approve routine development commands, speeding up your workflow without sacrificing safety.
Build a Persistent, Multi-Surface Claude Code Agent: Inside claude-crew
claude-crew shows how to run Claude Code headless (`-p --input-format stream-json`) as a persistent agent with a Gateway, PreToolUse approvals, and OS-level sandboxing for production-grade autonomy.
Agent Plugins 1.0.0: The Portable Plugin Standard That Makes MCP Servers
Agent Plugins 1.0.0 standardizes MCP server packaging into portable plugins. Claude Code users can create a plugin.json manifest to share tools across ChatGPT, Cursor, Copilot, and more.
Integration Testing Your MCP Server: The Pattern That Caught 3 Hidden Bugs
Integration test your MCP server by spinning it up with STDIO and sending real tools/call requests. This catches startup races, JSON-RPC framing errors, and state bugs that 90% unit test coverage missed.
3 MCP Production Failures This Developer Hit Automating Tax Returns (And
MCP's JSON-RPC can't handle binary uploads, 270-tool servers bloat context, and rate limits fail silently. Use CLI scripts for files, allow-list tools, and prompt-based throttling.
Build an MCP-Powered SaaS Discovery Engine with Next.js and PostgreSQL
Build an AI-ready SaaS directory by designing a canonical product entity first, then exposing it via MCP. Use Prisma, Zod, and JSON-LD to serve humans, search engines, and AI agents from one source of truth.
Port Claude Code Workflows to Codex
gpt-workflow brings Claude Code-style deterministic workflows to Codex CLI with resumable journals and JSON schema validation. Install via Codex plugin and store workflows under .codex/workflows/.
Lovable Now Exports Any App as an MCP Server — Here's How to Use It with
Lovable now exports any app as an MCP server. Add the URL to Claude Code's claude.json for instant live data access — no manual API wiring required.
Drive After Effects from Claude Code: Generate Production Videos via MCP
aftr is an open-source MCP server that lets Claude Code drive After Effects programmatically via JSON commands over WebSocket, enabling automated video rendering without manual work.
Stop Relying on CLAUDE.md for Guarantees: Build Deterministic Hooks Instead
Claude Code hooks in settings.json let you run deterministic shell commands on SessionStart, PreToolUse, PostToolUse, and other events—replacing unreliable CLAUDE.md instructions for critical behaviors like blocking dangerous commands or injecting context.
Confessor: The Forensic Tool That Shows You Exactly What Claude Code
Confessor replays Claude Code's JSONL session logs to show every file read, command, and network call — flagging sensitive data followed by exfiltration. Run `npx confessor` for a full HTML report.
Write MCP Servers in Python in 10 Lines with FastMCP
FastMCP from the official Python SDK v1.x turns type-hinted functions into MCP tools. Add @mcp.tool() to any function and Claude Code discovers it via tools/list and tools/call JSON-RPC calls.
Generate Branded PDFs Directly from Claude Code with PaperQuire v0.3.0's
PaperQuire v0.3.0's MCP server lets Claude Code render Markdown to branded PDFs. Add `paperquire mcp-server` to `.mcp.json` and ask for a PDF.
How to Cut Agent Token Waste: CLI Over GraphQL + Server-Pushed Hints
Replace raw GraphQL with typed CLI commands to eliminate JSON assembly errors, then add server-pushed hints via MCP to prevent judgment failures. Your agent burns 1,500+ tokens per operation otherwise.
Build a Zero-Dependency MCP Server
Build a zero-dependency MCP server in 50 lines of Python to give Claude Code direct file access. Register it in claude.json and skip SDK bloat.
SSL: Structured Skill Language Boosts Skill Discovery MRR to 0.707
Researchers propose SSL, a three-layer typed JSON representation for AI agent skills, replacing unstructured SKILL.md prose. Using an LLM normalizer, SSL improves Skill Discovery MRR from 0.573 to 0.707 and Risk Assessment macro F1 from 0.744 to 0.787 on a newly released 6,184-skill corpus.
DharmaOCR: New Small Language Models Set State-of-the-Art for Structured
A new arXiv preprint presents DharmaOCR, a pair of small language models (7B & 3B params) fine-tuned for structured OCR. They introduce a new benchmark and use Direct Preference Optimization to drastically reduce 'text degeneration'—a key cause of performance failures—while outputting structured JSON. The models claim superior accuracy and lower cost than proprietary APIs.
Claude Code Hooks: How to Auto-Format, Lint, and Test on Every Save
Configure hooks in .claude/settings.json to run prettier, eslint, and tests automatically, ensuring clean code without manual intervention.
BloClaw: New AI4S 'Operating System' Cuts Agent Tool-Calling Errors to 0.2% with XML-Regex Protocol
Researchers introduced BloClaw, a unified operating system for AI-driven scientific discovery that replaces fragile JSON tool-calling with a dual-track XML-Regex protocol, cutting error rates from 17.6% to 0.2%. The system autonomously captures dynamic visualizations and provides a morphing UI, benchmarked across cheminformatics, protein folding, and molecular docking.
What Cursor's 8GB Storage Bloat Teaches Us About Claude Code's Clean Architecture
A deep dive into Cursor's scattered 8GB local storage reveals why Claude Code's ~/.claude/projects/*.jsonl approach is better for developers.
How This Developer Built a Production-Ready RAG System with Claude Code in One Weekend
A developer used Claude Code to create a structured JSON-to-PDF knowledge base with 105 quotes, demonstrating how to build RAG-ready datasets faster than ever.
Give Claude Code Live B2B Lead Enrichment
Add @agent-infra/mcp-server-lead-enrichment to Claude Code for live firmographics, technographics, and intent signals. Pay only when confidenceScore > 0.6—zero cost for low-quality matches.
stryker-mcp-reporter v1.13.0: AI Agents Hit 100% Mutation Score
stryker-mcp-reporter v1.13.0 adds an ESLint hook and lets AI agents run Stryker mutation tests to chase 100% mutation score. The claim lacks reproducible proof.
selenium-mcp: Let Claude Code Write Real Selenium Tests by Seeing the Page
Install selenium-mcp to give Claude Code a real browser. It writes standard Selenium tests with accurate locators from live page inspection, integrating into your existing Java project.
Agents Signal via Filenames, Base64 Attachments
Simon Willison shared agents communicating via filenames with base64 attachments and zz prefixes. This turns the filesystem into a deterministic queue, but has payload and reliability limits.