io.github.shoggi211/jsonaut

Official4 toolsLive

by shoggi211 · TypeScript

Repair malformed JSON from LLM/agent output; optional JSON Schema coercion. Free + x402 paid.

JSON repair & validation built for AI agents as the customer. Send possibly-malformed JSON (LLM tool-call output, another agent's message, a flaky upstream), get back parsed, schema-valid JSON.

Free tier: deterministic repair — trailing commas, single quotes, truncation, markdown code fences, comments, Python literals — plus JSON Schema validation with type coercion (string→number, defaults, stripping hallucinated fields). Rate-limited per IP.
Paid tier: LLM-fallback repair for inputs the deterministic pass can't fix. $0.01/call, charged only on success, paid autores.

Captured live from the server via tools/list.

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).

Parameters3

input	string	required	The possibly-malformed JSON text
schema	object	optional	Optional JSON Schema the output must conform to
allow_llm_fallback	boolean	optional	Permit the paid LLM repair tier

Raw schema

{
  "type": "object",
  "properties": {
    "input": {
      "type": "string",
      "description": "The possibly-malformed JSON text"
    },
    "schema": {
      "type": "object",
      "description": "Optional JSON Schema the output must conform to"
    },
    "allow_llm_fallback": {
      "type": "boolean",
      "default": false,
      "description": "Permit the paid LLM repair tier"
    }
  },
  "required": [
    "input"
  ]
}

validate_json

Validate a JSON string against a JSON Schema. Free. Returns validity and a list of violations.

Parameters2

input	string	required	The JSON text to validate
schema	object	required	The JSON Schema to validate against

Raw schema

{
  "type": "object",
  "properties": {
    "input": {
      "type": "string",
      "description": "The JSON text to validate"
    },
    "schema": {
      "type": "object",
      "description": "The JSON Schema to validate against"
    }
  },
  "required": [
    "input",
    "schema"
  ]
}

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.

Parameters3

input	string	required	Text that may contain JSON
schema	object	optional	Optional JSON Schema the output must conform to
allow_llm_fallback	boolean	optional	Permit the paid LLM extraction tier

Raw schema

{
  "type": "object",
  "properties": {
    "input": {
      "type": "string",
      "description": "Text that may contain JSON"
    },
    "schema": {
      "type": "object",
      "description": "Optional JSON Schema the output must conform to"
    },
    "allow_llm_fallback": {
      "type": "boolean",
      "default": false,
      "description": "Permit the paid LLM extraction tier"
    }
  },
  "required": [
    "input"
  ]
}

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.

Parameters2

input	string	required	A JSON value (or array of samples) to infer a schema from
as_samples	boolean	optional	Treat a top-level array as multiple samples of one shape

Raw schema

{
  "type": "object",
  "properties": {
    "input": {
      "type": "string",
      "description": "A JSON value (or array of samples) to infer a schema from"
    },
    "as_samples": {
      "type": "boolean",
      "default": false,
      "description": "Treat a top-level array as multiple samples of one shape"
    }
  },
  "required": [
    "input"
  ]
}

README.md5 KBView on GitHub

Jsonaut

JSON repair & validation built for AI agents as the customer. Send possibly-malformed JSON (LLM tool-call output, another agent's message, a flaky upstream), get back parsed, schema-valid JSON.

Free tier: deterministic repair — trailing commas, single quotes, truncation, markdown code fences, comments, Python literals — plus JSON Schema validation with type coercion (string→number, defaults, stripping hallucinated fields). Rate-limited per IP.
Paid tier: LLM-fallback repair for inputs the deterministic pass can't fix. $0.01/call, charged only on success, paid autonomously per-call via x402 (USDC on Base) — no accounts, no signup.

Business context, market research, and the full 3-day plan live in IDEA.md and PLAN.md.

Quickstart

bash

npm install
npm test          # 27 tests: repair battery, schema coercion, HTTP API, MCP protocol
npm run dev       # http://localhost:8787 — demo page + API + MCP endpoint

Try it:

bash

curl -s -X POST http://localhost:8787/v1/repair \
  -H "content-type: application/json" \
  -d "{\"input\": \"{'name': 'alice', 'count': '42',}\", \"schema\": {\"type\":\"object\",\"properties\":{\"count\":{\"type\":\"number\"}}}}"

json

{
  "valid": true,
  "repaired": { "name": "alice", "count": 42 },
  "method": "deterministic-repair",
  "changes": ["repaired JSON syntax (jsonrepair)", "$.count: coerced string \"42\" to number"]
}

API

Route	What it does
`POST /v1/repair`	Repair + optional schema validation/coercion. Body: `{input, schema?, allow_llm_fallback?}`
`POST /v1/validate`	Validate only, no repair. Body: `{input, schema}`
`POST /mcp`	MCP server (Streamable HTTP, stateless). Tools: `repair_json`, `validate_json`
`GET /`	Interactive demo page
`GET /llms.txt`	Agent-readable capability + pricing description
`GET /openapi.yaml`	OpenAPI 3.1 spec

Response method values: direct (was already valid), deterministic-repair (free fix), llm-repair (paid fix), failed. changes[] lists every modification so callers can audit what was done to their data.

Using it from an agent (MCP)

bash

claude mcp add --transport http jsonaut https://YOUR-DEPLOYMENT/mcp

Or in any MCP client config:

json

{ "mcpServers": { "jsonaut": { "type": "http", "url": "https://YOUR-DEPLOYMENT/mcp" } } }

For the paid tier, clients pay via x402 and retry with the X-PAYMENT header (the payment receipt). No accounts or API keys — agents pay per call.

Payment flow (x402)

Agent calls /v1/repair with allow_llm_fallback: true; deterministic repair fails.
Server responds 402 with an x402 accepts array (USDC on Base, amount = PRICE_USD).
Agent pays and retries with the X-PAYMENT header; server verifies via the facilitator, runs the LLM repair, and settles only if the repair succeeds.

Configuration

Env var	Purpose	Required for
`OPENROUTER_API_KEY`	Enables the paid LLM-fallback tier (via OpenRouter; free model by default)	Paid tier
`OPENROUTER_MODEL`	Override the model (default `meta-llama/llama-3.3-70b-instruct:free`)	—
`X402_PAY_TO`	Wallet address on Base receiving USDC	x402 rail
`X402_NETWORK`	`base` or `base-sepolia` (default `base`)	x402 rail
`FACILITATOR_URL`	x402 facilitator for verify/settle	x402 rail
`FREE_DAILY_LIMIT`	Free calls per IP per day (default 100)	—
`PRICE_USD`	Paid-tier price (default 0.01)	—
`DEV_ALLOW_FREE_LLM`	`true` opens the paid tier for local dev only	—

Local dev secrets go in a .dev.vars file (git-ignored) or your shell env.

Deployment (Cloudflare Workers)

bash

npx wrangler login
npx wrangler kv namespace create KV      # then paste the id into wrangler.toml
npx wrangler secret put OPENROUTER_API_KEY
npx wrangler deploy

The same codebase runs on Node for local dev (npm run dev) and on Workers in production — storage falls back to in-memory when no KV binding exists.

Project structure

code

src/core/      pipeline.ts (repair engine) · coerce.ts (schema coercion) · llm.ts (paid tier)
src/http/      app.ts (routes) · payment.ts (x402 rail) · ratelimit.ts · demo.ts · billing.ts (parked, unused)
src/mcp/       server.ts (stateless Streamable HTTP MCP server)
src/worker.ts  Cloudflare Workers entry
src/dev.ts     Node dev entry
test/          full battery: broken-JSON cases, coercion, HTTP, MCP protocol

Known limitations (MVP)

Schema coercion does not resolve $ref or oneOf/anyOf branches.
x402 verification requires an external facilitator (FACILITATOR_URL); there is no on-chain verification built in.
Free-tier rate limiting is approximate under high concurrency (KV read-modify-write).

Install

Tools (4)

repair_jsonvalidate_jsonextract_jsoninfer_schema

Remote endpoint

Streamable HTTP

Hosted server - connect over the network, no local install.

url

https://jsonaut.jsonaut-shaurya.workers.dev/mcp

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "jsonaut": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://jsonaut.jsonaut-shaurya.workers.dev/mcp"
      ]
    }
  }
}

Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.

repair_json

validate_json

extract_json

infer_schema

Jsonaut

Quickstart

API

Using it from an agent (MCP)

Payment flow (x402)

Configuration

Deployment (Cloudflare Workers)

Project structure

Known limitations (MVP)

Install

Remote endpoint

Related servers