wmcp.sh

MCP serverDev tools

trust-oracle gives any tool or integration in your AI's setup an independent trust grade from A to F, so you can see at a glance how reliable it is before you rely on it. Grades are watched over time, so you'll know if a tool's trustworthiness drifts. It is free and never for sale.

Use wmcp.sh in Claude, ChatGPT or Ahel Desktop

Free. Sign in, add wmcp.sh and connect your AI. About a minute.

Also: Claude Code · Cursor · Codex

Then ask your AI: use the grade mcp server tool from wmcp.sh

Details

Available today. Use it from your connected AI after setup.

Add trust-oracle, then check the trust grade of the tools already connected to your AI before adding new ones.

wmcp.shStart free

What your AI can do with it

  • Get an independent A to F trust grade for any tool your AI uses
  • Compare trust grades across tools before deciding what to connect
  • Spot when a tool's trust grade drifts over time
  • Check a tool's trustworthiness before giving your AI new abilities

Install wmcp.sh

The server’s own address, for the clients that take one directly. Or connect Ahel once and every client you use reads it from one address, with the account kept on Ahel rather than in each client’s config.

  • Claude Code

    claude mcp add --transport http --scope user wmcp-sh 'https://wmcp.sh/mcp/trust'

    Run it once in your project, then open /mcp to approve any sign-in the server asks for.

  • Claude Desktop

    https://wmcp.sh/mcp/trust

    Add a custom connector in Settings, paste this address, and approve the sign-in.

  • Cursor

    cursor://anysphere.cursor-deeplink/mcp/install?name=wmcp-sh&config=eyJ1cmwiOiJodHRwczovL3dtY3Auc2gvbWNwL3RydXN0In0=

    Open the link and Cursor adds the server at that address.

  • ChatGPT

    https://wmcp.sh/mcp/trust

    In Settings, enable Developer mode, create an MCP app, and paste this address. Your plan and workspace must allow custom apps.

  • Codex

    codex mcp add wmcp-sh --url 'https://wmcp.sh/mcp/trust'

    Run it once, then sign in with codex mcp login wmcp-sh if the server asks for an account.

From the project's README

As published by new1direction/webmcp-anything in README.md.

Add any website to Claude, Cursor, or Codex as agent-callable MCP tools — in one line of config. No per-server build, no SDK.

wmcp.sh is a real, spec-compliant MCP server (JSON-RPC 2.0 over Streamable HTTP) that turns any URL into agent-callable tools — Shopify product pages, OpenAPI specs, JSON-LD pages, OAuth-protected APIs. Every other MCP server is one-per-service and hand-built; wmcp is one endpoint that adapts to whatever URL you point it at. Paste a config line and your agent can read prices, list variants, or call an API on a site that ships no MCP server of its own.

Live now: wmcp.sh · Directory · Blog · /llms.txt


30-second quickstart

Connect any URL to your MCP client (the flagship)

Point any MCP client — Claude Code, Claude Desktop, Cursor, Codex, Cline, VS Code — at a per-URL endpoint: /mcp/u/<base64url-of-your-url>. That's the whole install. The server exposes that page's extracted tools natively (tools/list + tools/call):

{
  "mcpServers": {
    "allbirds": {
      "type": "http",
      "url": "https://wmcp.sh/mcp/u/aHR0cHM6Ly93d3cuYWxsYmlyZHMuY29tL3Byb2R1Y3RzL21lbnMtd29vbC1ydW5uZXJz"
    }
  }
}

That base64url string decodes to https://www.allbirds.com/products/mens-wool-runners. Encode your own:

node -e "process.stdout.write(Buffer.from('https://your-url.example').toString('base64url'))"

Compose several sites into one MCP server — repeat the url param; tool names are namespaced per host (site_a__add_to_cart):

{ "mcpServers": { "wmcp": { "type": "http", "url": "https://wmcp.sh/mcp/url?url=https://site-a.example&url=https://site-b.example" } } }

tools/list (discovery) is free. tools/call (live execution) needs a paid key, passed as a Bearer header:

{ "mcpServers": { "wmcp": { "type": "http", "url": "https://wmcp.sh/mcp/u/<base64url>", "headers": { "Authorization": "Bearer webmcp_live_…" } } } }

type may be "http" or "streamable-http" (same transport). For Claude Desktop builds without remote-MCP support, bridge with npx mcp-remote <url>. Full walkthrough: /how-to/install-claude-desktop-mcp.

Or just hit the REST API (no client, no key for reads)

# any URL → MCP-shaped tool list
curl 'https://wmcp.sh/api/v1/tools?url=https://www.allbirds.com/products/mens-wool-runners'

Returns a JSON tool list in the Claude tool_use / OpenAI function_call / MCP shape — get_price, add_to_cart, list_variants — that any agent can invoke.


How it works

A 5-tier extraction chain turns most URLs into tools with zero per-site work. Each tier is tried in order; the first that detects the URL wins. The last tier is an LLM fallback that produces best-effort tools and caches the result.

┌──────────────────────────────────────────────────┐
│  URL in →                                          │
│    1. Shopify       (~4M storefronts, <50ms)       │
│    2. JSON-LD       (schema.org Product, etc.)     │
│    3. OpenAPI       (any 3.x / Swagger 2.0 → tools)│
│    4. Provider      (Stripe, GitHub, Slack…)       │
│    5. LLM-fallback  (Claude Haiku, cached 30d)     │
│  → MCP tools out                                   │
└──────────────────────────────────────────────────┘

Cached on Cloudflare KV; sub-50ms on a cache hit. Discovery (tools/list) is free; live execution (tools/call) runs through the same engine and needs a paid key. For sites that block bot fetches or hydrate client-side from authed APIs, a Chrome extension extracts schemas in your browser and pushes them back to the shared cache. Full design in docs/ARCHITECTURE.md.


What makes it different

Today, "an MCP server for X" means someone wrote, built, and deployed a dedicated server for service X. There are hundreds of them, each one a separate repo and a separate install.

wmcp inverts that:

Hand-built MCP serverwmcp.sh
CoverageOne service per serverAny URL, one endpoint
SetupClone, build, configure, deployPaste one config line
New targetWrite & ship a new serverEncode the URL — done
Auth'd upstreamsBake credentials into each serverShared OAuth/credential vault proxy at /mcp/<provider>
DiscoveryFind/trust each repoPublic directory of what's already cached

There's also a saved toolset endpoint — /mcp/set/<id> — that bundles a curated set of URLs behind one stable MCP server (a Pro feature). It's genuinely novel: instead of one-per-service, wmcp turns arbitrary URLs into MCP tools on demand.


Directory, SDKs & extension

  • Directory — every URL the community has indexed, browsable and searchable: wmcp.sh/directory. Submit your site (free): wmcp.sh/directory/submit.
  • OAuth-vault proxy — connect an OAuth-protected upstream once; call it as MCP from any client: https://wmcp.sh/mcp/<provider> (Google, GitHub, Slack, Notion, Linear, Discord, Stripe, Anthropic).
  • Python SDK — pip install wmcp. Native fetch-style client, zero required deps.
  • JavaScript/TypeScript SDK — npm install @wmcp/sdk with one-line adapters for @wmcp/sdk/anthropic, @wmcp/sdk/openai, @wmcp/sdk/langchain, and @wmcp/sdk/vercel-ai.
import { WmcpClient } from "@wmcp/sdk";
import { toAnthropicTools } from "@wmcp/sdk/anthropic";

const client = new WmcpClient(); // anonymous = 100 reads/day per IP
const tools = toAnthropicTools(await client.tools("https://www.allbirds.com/products/mens-wool-runners"));
  • Chrome extension — for SPA / bot-walled / auth-walled sites. Extracts client-side, pushes cached schemas back to the hosted API so the next person gets them instantly — even if they never install it.

Pricing

Two separate ladders. Self-serve API plans for anyone, and a done-for-you service if you want a custom adapter built and run for you.

Self-serve API (manage at /dashboard):

TierCostWhat you get
Free$0tools/list + REST reads, IP-rate-limited, no live execute
Builder$39/moEntry paid tier: live tools/call execute, OAuth vault, higher quotas
Pro$99/moHigh quotas, priority cache, full execute + vault
Reseller$299/moHigh-volume quotas, email support

Done-for-you service (/managed):

TierCostWhat you get
Starter$499 one-timeCustom adapter built for your site + verified directory badge
Managed Retainer$999/moOngoing maintenance, featured listing, white-label MCP at mcp.yourbrand.com
Enterprise$4,999+/moSelf-hosted deployment + SLA + dedicated support

What's in the repo

.
├── adapters/                Shared adapter library (worker + extension import the same files)
│   ├── shopify.js           ~4M storefronts, read + add_to_cart
│   ├── jsonld.js            generic schema.org Product
│   ├── openapi.js           any OpenAPI 3.x / Swagger 2.0 → tools
│   ├── llm.js               Claude Haiku fallback
│   ├── CONTRACT.md          the detect() / extract() / actions interface
│   ├── _template/           starter scaffold for new adapters
│   └── _test/run.mjs        node:test harness, zero deps
│
├── worker/                  Hosted API + MCP server at wmcp.sh
│   └── src/                 Hono routes, mcp_server.ts, OAuth, billing, SEO pages, token vault
│
├── extension/               Chrome MV3 extension (cache-back path)
│
├── sdks/
│   ├── python/wmcp/         pip install wmcp
│   └── javascript/src/      @wmcp/sdk (+ anthropic / openai / langchain / vercel-ai adapters)
│
├── docs/                    QUICKSTART · ARCHITECTURE · API · SELF_HOSTING
├── launch/                  Launch artifacts (HN draft, registry submissions, demo)
├── AGENTS.md                rules for AI coding agents working on this repo
├── CONTRIBUTING.md          how to send a PR
├── ADAPTERS_WANTED.md       open targets, ranked by difficulty
└── LICENSE                  MIT

Contributing

New adapters are welcome via PR. The whole point is that adding a site shouldn't mean building a new server.

git clone https://github.com/New1Direction/webmcp-anything
cd webmcp-anything
cp -r adapters/_template adapters/mysite
# edit adapters/mysite/adapter.js — implement detect() + extract()
node adapters/_test/run.mjs

Adapter files are plain ES modules with zero npm deps so the same file runs in Cloudflare Workers, Chrome MV3 service workers, and Node 18+. Read CONTRIBUTING.md, the adapter contract, and open targets in ADAPTERS_WANTED.md. If you're an AI coding agent, read AGENTS.md first.


Status

  • ✅ Production at wmcp.sh (Cloudflare Workers + KV)
  • ✅ Spec-compliant MCP server (JSON-RPC 2.0 over Streamable HTTP) — per-URL, multi-URL, and saved-toolset endpoints
  • ✅ 5-tier extraction chain + free REST API (/api/v1/tools)
  • ✅ OAuth-vault proxy for 8+ providers (Google, GitHub, Slack, Notion, Linear, Discord, Stripe, Anthropic)
  • ✅ Public directory (submit, badge, verified/featured)
  • ✅ Python (pip install wmcp) + JS (@wmcp/sdk) SDKs and a Chrome extension
  • 🟡 Stripe billing wired; self-serve dashboard upgrade in progress
  • 🟡 Registry submissions in progress — see launch/registry/SUBMISSION_PLAYBOOK.md

Found a bug? Open an issue. Have a site we should support? ADAPTERS_WANTED.md.


License

MIT. See LICENSE. Repo: github.com/New1Direction/webmcp-anything.

Tools it offers (3)

What this server listed when Ahel dialed its public endpoint in Sep 2026, with no key and no account of yours. The names are the server’s own.

  • grade_mcp_server
  • check_mcp_drift
  • verify_before_execute

Signals

GitHub stars
6
Forks
2
Last commit
Jun 2026
Advanced
Delivery
trust-oracle MCP server → your Ahel connector (mcp.ahel.ai) → your AI.
Item type
mcp-server
Key
io-github-new1direction-trust-oracle
Source
github.com/new1direction/webmcp-anything
Hosted endpoint
https://wmcp.sh/mcp/trust