MCP JSON Sanitizer

MCP JSON Sanitizer

Enables repair of malformed JSON strings into valid JSON for agent workflows by fixing common LLM formatting issues. Supports cleanup of code fences, smart quotes, unquoted keys, trailing commas, and missing brackets to ensure reliable data parsing.

Category
Visit Server

README

MCP JSON Sanitizer

Remote MCP server on Cloudflare Workers that repairs malformed JSON strings into valid JSON for agent workflows.

What It Does

json_sanitizer accepts a string that is supposed to be JSON but may have common LLM formatting issues. The Worker applies deterministic cleanup steps and returns valid JSON when recovery succeeds.

Handled fixes include:

  • code fence removal
  • smart quote normalization
  • extraction of the JSON body from surrounding prose
  • quoting bare object keys
  • conversion of single-quoted strings
  • trailing comma removal
  • closing missing } and ]

Tool

json_sanitizer

Input:

  • input: malformed JSON-like string
  • pretty?: pretty-print output JSON, defaults to true

Output:

  • repaired JSON text
  • structured metadata with applied fixes and parsed JSON value

Transport

  • MCP endpoint: https://<your-worker>.workers.dev/mcp
  • Well-known manifest: https://<your-worker>.workers.dev/.well-known/mcp/server.json
  • Health check: https://<your-worker>.workers.dev/health

Monetization

Only actual tool execution requires payment:

  • free: GET /mcp, tools/list, initialize, ping
  • paid: tools/call for json_sanitizer

Payment settings:

  • network: eip155:8453 (Base)
  • asset: USDC
  • price: 0.001
  • payTo: 0x4505A361611DebB4928Db488ad7E345cD5821cD4

Deploy

  1. Install dependencies with npm install.
  2. Authenticate Wrangler with npx wrangler login.
  3. Set the settlement signer privately with npx wrangler secret put EVM_PRIVATE_KEY.
  4. Update PUBLIC_BASE_URL in wrangler.toml to your final Worker URL.
  5. Deploy with npm run deploy.

Recommended Servers

playwright-mcp

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.

Official
Featured
TypeScript
Magic Component Platform (MCP)

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.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

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.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

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.

Official
Featured
TypeScript
Kagi MCP Server

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.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

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.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured