Jsonaut
About
Repair malformed JSON from LLM tool calls and agent-to-agent handoffs — fixes trailing commas, single quotes, truncation, markdown code fences, comments, and python literals, and can validate/coerce the result against a JSON Schema. Free deterministic tier; pay-per-call LLM fallb
Details
- Transport
- SSE
Explore
- Repairs common JSON malformations from LLM output (trailing commas, single quotes, truncation, etc.)
- Validates and coerces results against a JSON Schema
- Free deterministic tier for most fixes
- Pay-per-call LLM fallback via x402 (USDC on Base)
- Exposes MCP endpoints (repair_json, validate_json), REST API, and local npm/Python clients
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
JsonautCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
You can use Jsonaut via its MCP server (exposing repair_json and validate_json tools), its REST API, or by installing its local-first npm or Python client libraries. Most JSON fixes happen deterministically without external calls.
repair_json
Repair malformed JSON (trailing commas, single quotes, truncation, markdown fences, comments, python literals) and optionally validate/coerce it against a JSON Schema. Deterministic repair is free. If it fails and allow_llm_fallback is true, a paid LLM repair is attempted (requires x402 payment; charged only on success).
validate_json
Validate a JSON string against a JSON Schema. Free. Returns validity and a list of violations.
extract_json
Extract JSON embedded in arbitrary text — LLM prose, chat messages, logs, emails — then repair and validate it. Deterministic extraction is free. If no JSON can be located and allow_llm_fallback is true, a paid LLM extracts structured data from the text (requires x402 payment; charged only on success). Pass a JSON Schema to shape the output.
infer_schema
Infer a JSON Schema (draft 2020-12) from an example JSON value. Free and deterministic. Set as_samples=true when the input is an array of example objects of the same shape to merge them into one schema. Turns sample agent/tool output into a reusable schema.
- repair_json: Repair malformed JSON (trailing commas, single quotes, truncation, markdown fences, comments, python literals) and optionally validate/coerce it against a JSON Schema. Deterministic repair is free. If it fails and allow_llm_fallback is true, a paid LLM repair is attempted (requires x402 payment; charged only on success).
- validate_json: Validate a JSON string against a JSON Schema. Free. Returns validity and a list of violations.
- extract_json: Extract JSON embedded in arbitrary text — LLM prose, chat messages, logs, emails — then repair and validate it. Deterministic extraction is free. If no JSON can be located and allow_llm_fallback is true, a paid LLM extracts structured data from the text (requires x402 payment; charged only on success). Pass a JSON Schema to shape the output.
- infer_schema: Infer a JSON Schema (draft 2020-12) from an example JSON value. Free and deterministic. Set as_samples=true when the input is an array of example objects of the same shape to merge them into one schema. Turns sample agent/tool output into a reusable schema.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"jsonaut": {
"jsonaut": {
"type": "http",
"url": "https://jsonaut.jsonaut-shaurya.workers.dev/mcp"
}
}
}
}McpServers
{
"jsonaut": {
"type": "http",
"url": "https://jsonaut.jsonaut-shaurya.workers.dev/mcp"
}
}Repair malformed JSON from LLM tool calls and agent-to-agent handoffs — fixes trailing commas, single quotes, truncation, markdown code fences, comments, and python literals, and can validate/coerce the result against a JSON Schema. Free deterministic tier; pay-per-call LLM fallback via x402 (USDC on Base). Exposes an MCP endpoint (repair_json, validate_json), a REST API, and local-first npm/Python clients that fix most JSON offline.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
