json-repair-mcp

Repairs truncated or malformed LLM JSON outputs (trailing commas, markdown fences, unquoted keys).

Should I use this

Quality & Safety

A
Description quality
100%
Schema completeness
85%
Naming quality
90%
Poisoning risk
100%
Permission match
100%
Protocol compliance
100%

Based on automated analysis of tool definitions and protocol compliance.

Context Cost

~397Tokens (tool definitions)
~549 BTypical response size
Minimal attention impact (0.31% of 128k context)

This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.

Install

One-Click Install

Add this to your `claude_desktop_config.json` file:

{
  "mcpServers": {
    "json-repair-mcp": {
      "url": "https://agentdiet-72343955726.us-central1.run.app/mcp/json-repair"
    }
  }
}

Remote endpoints

https://agentdiet-72343955726.us-central1.run.app/mcp/json-repairstreamable-http
https://json-repair-72343955726.us-central1.run.app/mcp/json-repairstreamable-http

What it can do

Tool inventory

Tools (2)

🟢 Read-only🟡 Write🔴 Delete⚪ Unknown
🟢repair_malformed_json(raw_json)

Deterministic A2A Broken-JSON Repair & Schema Validator (0.002 USDC via x402): Repairs truncated or malformed LLM JSON outputs (trailing commas, markdown fences, single quotes) so multi-agent pipelines never crash. WHEN TO USE: Call for deterministic, token-efficient `repair_malformed_json` execution. WHEN NOT TO USE: Skip on binary media or unrelated domains. BEHAVIOR: Read-only, idempotent, 1h cache (<5ms HIT), SHA-256 ROI proof (HTTP 402 / x402 Base USDC / L402).

Input Schema

{
  "type": "object",
  "properties": {
    "raw_json": {
      "type": "string",
      "description": "Malformed, truncated, or markdown-wrapped JSON string to deterministically repair",
      "minLength": 1,
      "maxLength": 99999
    }
  },
  "required": [
    "raw_json"
  ],
  "additionalProperties": false
}
🟢get_agent_wallet_status(agent_id)

Returns the calling agent's remaining free quota, USD balance, and total tokens saved. WHEN TO USE: Call for deterministic, token-efficient `get_agent_wallet_status` execution. WHEN NOT TO USE: Skip on binary media or unrelated domains. BEHAVIOR: Read-only, idempotent, 1h cache (<5ms HIT), SHA-256 ROI proof (HTTP 402 / x402 Base USDC / L402).

Input Schema

{
  "type": "object",
  "properties": {
    "agent_id": {
      "type": "string",
      "minLength": 1,
      "maxLength": 99999
    }
  },
  "additionalProperties": false
}

Community

Rate this Server

Evidence

Recent observations

verifiedversion not recorded2 tools
verifiedversion not recorded2 tools