JSONShelf
Deterministic JSON repair, validation, example-generation, and schema-coercion for AI agents — zero LLM calls, sub-10ms, $0.0005 per call.
README
jsonshelf
Deterministic JSON repair, validation, example-generation, and schema-coercion for AI agents. Zero LLM calls. Sub-10ms. $0.0005 per call. Agents only.
Live endpoint: https://jsonshelf.vercel.app/
curl https://jsonshelf.vercel.app/ returns a full machine-readable manifest. No HTML. No humans.
What it does
Four tools, all pure compute, 100% deterministic:
| Endpoint | Purpose |
|---|---|
POST /v1/repair |
Fix malformed JSON. Optional schema to conform to. |
POST /v1/validate |
Validate JSON against a schema. Returns structured errors with fix fields telling the agent exactly what to change. |
POST /v1/example |
Generate a minimal valid example from a JSON schema. |
POST /v1/coerce |
Soft-cast values to match a schema (e.g. "42" → 42 for integer fields). |
Every error response includes { error, code, message, fix, docs, http_status } — agents never have to guess.
Discovery (no humans required)
GET /.well-known/ai-plugin.json— OpenAI plugin manifestGET /.well-known/mcp.json— MCP server manifestGET /llms.txt— machine-readable docsGET /openapi.json— OpenAPI 3.1 specGET /v1/pricing— machine-readable pricingGET /v1/errors— full error catalog
Auth
# 1. Issue a key (100 free credits)
curl -X POST https://jsonshelf.vercel.app/v1/keys
# 2. Use the key
curl -X POST https://jsonshelf.vercel.app/v1/repair \
-H "Authorization: Bearer sk_live_..." \
-H "Content-Type: application/json" \
-d '{"input":"{name:\"alice\", skills:[\"code\",]}"}'
Billing
Prepaid credits. Single POST returns a payment URL the agent follows autonomously:
curl -X POST https://jsonshelf.vercel.app/v1/credits \
-H "Authorization: Bearer sk_live_..." \
-H "Content-Type: application/json" \
-d '{"pack":"starter"}'
Returns { payment_url, x402: { ... } }. x402 headers are emitted for protocol-compatible clients.
MCP
Use over HTTP at https://jsonshelf.vercel.app/mcp (JSON-RPC 2.0, protocol version 2024-11-05). Four tools: jsonshelf_repair, jsonshelf_validate, jsonshelf_example, jsonshelf_coerce.
License
Apache 2.0.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.