Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
JSON Schema validator for API payloads via MCP: bounded checks and structured pass/fail errors.
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
AuthorizationValues marked secret are keys to your account. Never share them or paste them into a chat.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
This address needs a key in a request header, which the add-connector menu cannot set. Use Claude Code, Cursor or VS Code instead.
Run this in your terminal
claude mcp add --transport http payload-validator https://elyreon-payload-validator.colt2822.workers.dev/mcp --header 'Authorization: your-value'Fill in the empty values before running it.
Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"payload-validator": {
"url": "https://elyreon-payload-validator.colt2822.workers.dev/mcp",
"headers": {
"Authorization": "your-value"
}
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"payload-validator": {
"type": "http",
"url": "https://elyreon-payload-validator.colt2822.workers.dev/mcp",
"headers": {
"Authorization": "your-value"
}
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
This address needs a key in a request header, which the add-connector menu cannot set. Use Claude Code, Cursor or VS Code instead.
Your choice stays on this device in a cookie; no account needed.
Authorization secret required HTTP headerThese settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
We have not read this server’s tool list yet; we check endpoints in rotation.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 6, 2026
The publisher (elyraon.com.co) is not the repo owner (colt2822); someone else may have listed it
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
Not checked yet; we check endpoints in rotation
Not checked yet; we check endpoints in rotation
Not checked yet; we read the tool list when we check the endpoint
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 0 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
You need to fill in: Authorization
It runs in the maker’s cloud. Connect over the internet with nothing to install, but what you send passes through the maker’s servers.
The GitHub repo last changed –, and the latest version (1.0.1) reached the registry 12 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. It connects by URL, so apps that accept remote MCP servers work too, such as ChatGPT in developer mode.
In the same category: Spec Driven Development, Remote Desktop Commander, yontu
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Türkçe yazı denetimi: TDK kuralları, yapay zekâ izleri, metin türüne göre üslup.
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
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.