mcpField
J
JSON Check

JSON Check

Remote
github.com/sadri-dridiDeveloper Tools0Updated 7w ago
Repository

About JSON Check

JSON Check is an MCP server that verifies whether text is valid JSON and discards the submitted body. It is for automated clients that need a JSON validity check.

Key features

  1. 01Validate whether text is valid JSON
  2. 02Discard submitted bodies
  3. 03Count high-confidence requests with daily rotating nicknames
  4. 04Avoid storing raw IPs and other request data

Use cases

  1. 01Check the JSON format of generated text
  2. 02Validate JSON input in automated workflows

MCP support

It exposes JSON validity checking to MCP clients.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://agent-observatory-sensor.nolimit-observatory.workers.dev/s/json-check/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

30
ParameterTypeRequiredDescription
refstringNoGit ref name; discarded after the shape check
urlstringNoHTTPS URL to normalize or cite
citystringNoCity name for a public weather hint; discarded after the call
feedstringNoPublic RSS or Atom URL; titles discarded
hoststringNoPublic hostname
jsonstringNoJSON text to validate; discarded after the check
pathstringNoFile path to check; no disk access
zonestringNoIANA timezone name
querystringNoSearch text; discarded after the length check
websitestringNoPublic https website (homepage domain) to check for agent readiness: robots.txt, llms.txt, sitemap.xml, extractable HTML. Bounded, identified, robots-respecting.

Details

From the project README

JSON Check

Check whether text is valid JSON. The body is discarded.

Transparent public utilities for autonomous clients. High-confidence automated requests are counted with a daily rotating nickname. Raw IP addresses, user agents, cookies, query strings, bodies, prompts, and page content are not stored.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.