mcpField
J
Jsonaut

Jsonaut

Remote
jsonaut.jsonaut-shaurya.workers.devAI & Agents1Updated 16w ago

About Jsonaut

Jsonaut is an MCP server for agents that repairs malformed JSON and can validate it against a JSON Schema. It combines deterministic fixes with an optional paid LLM fallback, and reports the changes made.

Key features

  1. 01Repairs common JSON syntax errors
  2. 02Validates against JSON Schema
  3. 03Coerces values and applies defaults
  4. 04Reports changes for auditing
  5. 05Optional paid LLM fallback

Use cases

  1. 01Repair malformed agent tool-call output
  2. 02Check and coerce data to a schema
  3. 03Recover JSON that deterministic fixes cannot repair

MCP support

Exposes `repair_json` and `validate_json` tools through a stateless Streamable HTTP MCP endpoint. The optional LLM fallback can use x402 per-call payments.

Configuration

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

Endpointhttps://jsonaut.jsonaut-shaurya.workers.dev/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

4
ParameterTypeRequiredDescription
inputstringYesThe possibly-malformed JSON text
schemaobjectNoOptional JSON Schema the output must conform to
allow_llm_fallbackbooleanNoPermit the paid LLM repair tier

Details

From the project README

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

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:

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

API

RouteWhat it does
POST /v1/repairRepair + optional schema validation/coercion. Body: {input, schema?, allow_llm_fallback?}
POST /v1/validateValidate only, no repair. Body: {input, schema}
POST /mcpMCP server (Streamable HTTP, stateless). Tools: repair_json, validate_json
GET /Interactive demo page
GET /llms.txtAgent-readable capability + pricing description
GET /openapi.yamlOpenAPI 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)

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

Or in any MCP client config:

{ "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)

  1. Agent calls /v1/repair with allow_llm_fallback: true; deterministic repair fails.
  2. Server responds 402 with an x402 accepts array (USDC on Base, amount = PRICE_USD).
  3. 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 varPurposeRequired for
OPENROUTER_API_KEYEnables the paid LLM-fallback tier (via OpenRouter; free model by default)Paid tier
OPENROUTER_MODELOverride the model (default meta-llama/llama-3.3-70b-instruct:free)—
X402_PAY_TOWallet address on Base receiving USDCx402 rail
X402_NETWORKbase or base-sepolia (default base)x402 rail
FACILITATOR_URLx402 facilitator for verify/settlex402 rail
FREE_DAILY_LIMITFree calls per IP per day (default 100)—
PRICE_USDPaid-tier price (default 0.01)—
DEV_ALLOW_FREE_LLMtrue 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)

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

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).

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.