JSON MCP Tools for AI Agents

Your agent needs to extract a nested value from a JSON response, but it hallucinates a field name that doesn't exist. JSON path extraction, validation, and transformation need to operate on actual data structures, not LLM predictions. These tools parse and manipulate real JSON.

All JSON Tools (14)

Your agent gets access to 14 json tools via the /mcp/json/ endpoint. Here's the complete list:

Agent Scenarios

Here's how real agents use these tools:

{ "json": "{...}", "path": "data.users[0].email" }

{ "json": "{ \"key\": \"value\" }" }

{ "json1": "{...}", "json2": "{...}" }

MCP Setup

Add json tools to your agent in under 2 minutes. Choose your client:

Claude Desktop / Claude Code

Add this to your MCP config:

{
  "mcpServers": {
    "tinyfn-json": {
      "url": "https://api.tinyfn.io/mcp/json/",
      "headers": {
        "X-API-Key": "your-api-key"
      }
    }
  }
}

Cursor

Go to Settings > MCP and add a new server:

• Type: SSE
• URL: https://api.tinyfn.io/mcp/json/sse
• Headers: X-API-Key: your-api-key

Tip: Use the category-specific endpoint (/mcp/json/) for the best experience. The all-in-one endpoint (/mcp/all/) works too but has 500+ tools which some clients handle less efficiently.

When to Use These Tools

Use json MCP tools when your agent needs to:

• Guarantee correctness — when wrong answers have real consequences
• Process user data — when you're operating on actual user input, not hypothetical examples
• Maintain consistency — when the same input must always produce the same output

You don't need these tools for casual conversation or rough estimates. Use them when precision matters.

Frequently Asked Questions