mcpField
E
ELYREON JSON Schema Payload Validator

ELYREON JSON Schema Payload Validator

Remote
elyreon-payload-validator.colt2822.workers.devDeveloper Tools0Updated 4d ago

About ELYREON JSON Schema Payload Validator

ELYREON JSON Schema Payload Validator is a remote MCP server for checking API payloads against a bounded JSON Schema 2020-12 subset. It returns structured pass/fail outcomes, with explicit limits on inputs and supported schema features.

Key features

  1. 01Validate payloads against bounded schemas
  2. 02Return structured pass/fail outcomes
  3. 03Reject unsupported schema constructs
  4. 04Enforce request and schema limits

Use cases

  1. 01Check API payloads during evaluation
  2. 02Identify invalid data before processing
  3. 03Verify supported schema behavior

MCP support

The remote MCP server exposes the `validate_payload` tool over Streamable HTTP at `/mcp`. Clients provide a schema and payload; bearer-token authentication is required.

Configuration

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

Endpointhttps://elyreon-payload-validator.colt2822.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.

All endpoints
Streamable HTTPhttps://elyreon-payload-validator.colt2822.workers.dev/mcpAuth required

Tools

Details

From the project README

ELYREON Payload Validator

Small, deterministic first-party distribution test in the existing public Decision Gateway repository. This isolated Worker validates JSON against an explicitly bounded JSON Schema 2020-12 subset. It does not call Nace.AI, expose Drex inference, execute uploaded code, or accept payments.

Endpoint: https://elyreon-payload-validator.colt2822.workers.dev

MCP: append /mcp. Get a free bearer token at POST /trial with JSON {"source":"github"}; send {"test":true,"source":"github"} for controlled evaluations. Configure the bearer header in any Streamable HTTP MCP client, discover validate_payload, and call with {schema,payload}. Direct HTTP uses POST /validate with the same token and input.

Install the Agent Skill in the client's skill directory. Portable git install:

git clone --depth 1 https://github.com/colt2822/Drex-Decision-Gateway-for-Coding-Agents.git
mkdir -p ~/.agents/skills/elyreon-payload-validator
cp Drex-Decision-Gateway-for-Coding-Agents/distribution/payload-validator/skills/elyreon-payload-validator/SKILL.md ~/.agents/skills/elyreon-payload-validator/

Limits: 32 KiB request, depth 12, 2048 values, 128 schema nodes, 3-second body timeout; one validation error. Free quota: 20 invocations/token/day, 1000 invocations/service/day, 100 enrollments/service/day, 5 enrollments/IP/hour; edge limit 30 requests/IP/minute/location. Schema references, regex, formats and combinators are rejected. Supported keywords are documented in the skill. Validation does not certify runtime behavior. Malformed/unsupported input returns REJECTED; invalid data returns completed FAIL.

Deployment has a separate Worker and D1 database, no custom routes or other production bindings. Worker stores no input bodies, schemas or raw IPs. Token hashes and usage metadata are retained 30 days. Source is client-claimed; tokens are not verified customers. PHOENIX monitoring uses its existing controller timer and CRM; all five seats remain intact. Controlled tests are marked synthetic. No outbound sender or payment system is invoked. Provider inference cost is zero; hosting costs require billing evidence.

server.json is Official MCP Registry metadata. /.well-known/ai-catalog.json is a self-hosted catalog, not proof of a third-party listing. /x402-bazaar.json is inactive draft metadata with no accepted payment methods; it is not a paid Bazaar listing.

Validation: npm ci, npm test, python3 tests/reference_check.py, python3 -m unittest discover -s tests -p 'test_monitor.py', npm run dry-run. Local HTTP acceptance uses wrangler d1 execute elyreon-payload-validator --local --file migration.sql, then wrangler dev --port 18741 --var PRIVACY_SALT:local-only --var SYNC_TOKEN:local-only, then python3 tests/http_check.py.

Deploy with npm run deploy only to the named isolated Worker, preserving secrets. Roll back using wrangler rollback VERSION_ID; for the first deployment, disable only this Worker's workers.dev endpoint. Never change existing website routes. Secrets SYNC_TOKEN, TEST_TOKEN and PRIVACY_SALT are kept outside git. Registration authentication files must remain outside git.

The Official MCP Registry listing is co.com.elyraon/payload-validator version 1.0.0. Registry readback, clean public installation and MCP acceptance, and receipt attribution are recorded separately. This is controlled evidence, with zero independent customers or revenue.

VS Code MCP configuration prompts privately for the free token. The generic Agent Skill can also be installed in clients that read SKILL.md; no native VS Code GUI or other desktop client acceptance is claimed. Default Python urllib requests are blocked by Cloudflare error 1010; the standard MCP Python SDK, httpx and curl succeeded. No Cloudflare security setting was changed.

The PHOENIX monitor runs as an error-isolated post-command on the existing controller service, throttled to one network pass per 15 minutes. It records readback, usage, repeat tokens, per-seat responsibilities and explicit unknown hosting cost in the existing CRM. It reads existing demand feeds and never sends messages. See the systemd drop-in. Synthetic tests remain excluded from customer and installation totals.

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.