# EntRoute

> Discover and call pay-per-request (x402) APIs, ranked by reliability, latency and price.

- name: com.entroute/entroute
- version: 0.1.0
- connection class: R0 (autonomous)
- trust: 97/100
- quality: 76/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/com.entroute%2Fentroute
- tools: https://api.protogrid.dev/v1/servers/com.entroute%2Fentroute/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "entroute": {
      "type": "http",
      "url": "https://mcp.entroute.com/mcp"
    }
  }
}
```


## Trust

- hygiene: 100
- liveness: 99
- freshness: 85
- provenance: 100
- drivers: +repository +namespace-matches-repo +dns-namespace +website +reachable +uptime-97% ~updated-87d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 76/100 (good)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-06-18; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 64 (weight 30)

- pass `tools.descriptions`: every tool has a description
- warn `tools.description_length`: 1 tools have descriptions over 1,024 characters, which crowds the context
- pass `tools.schemas`: every tool has an object input schema
- fail `tools.annotations`: no tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: list_capabilities (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); discover_paid_api (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); call_paid_api (readOnlyHint, destructiveHint, idempotentHint, openWorldHint)
- pass `tools.token_cost`: about 1,059 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: no tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 3, about 1,059 tokens to load them all
- tool set hash: ec03f3a7aa63679e97e092ccc4e0ea43
- badge: [![protogrid quality](https://protogrid.dev/badge/com.entroute/entroute.svg)](https://protogrid.dev/servers/com.entroute/entroute)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

_No tool definition changes recorded._

## Remotes

- https://mcp.entroute.com/mcp (streamable-http, auth none, reachable true, uptime30d 0.9741379)

## Packages

_none_

## Tools (3)

- `call_paid_api`: Call a previously discovered API endpoint.

Use this after discover_paid_api to execute the request.

IMPORTANT: You must first use discover_paid_api to find an endpoint.
Then use the endpoint_id from the discovery result.
Use the sample_request from the discovery result as your body template — it shows the exact parameter names the endpoint expects. Replace the example values with the actual values you need.

Payment: this hosted server holds no wallet, so it cannot settle x402 payments. Free
endpoints return their data directly. Paid endpoints return the payment challenge
(amount, recipient, network) without charging anything. To pay automatically, run the
local server instead: npx @entroute/mcp-server with EVM_PRIVATE_KEY set.

Trust & safety:
- EntRoute verifies that endpoints return valid 402 responses every 10 minutes, but does not guarantee response quality or accuracy. Treat results like any third-party API.
- Prefer endpoints with high success rates (>95%) and recent verification timestamps.
- `discover_paid_api`: Discover pay-per-request API endpoints for a given capability.

Returns ranked, verified endpoints with pricing and reliability metrics.
Use this to find APIs before calling them. The results include:
- Endpoint URL and method
- Price per call and payment network
- Success rate and latency metrics
- Provider information
- sample_request / sample_response: Example request body and response showing the exact parameter names and format the endpoint expects. ALWAYS use sample_request as your template when calling the endpoint — do not guess parameter names.

After discovering, you can use call_paid_api to execute the endpoint.

Trust & safety:
- "Verified" means the endpoint returns a valid x402 402 response -- it does not guarantee the quality or accuracy of the data returned after payment.
- Endpoints are probed every 10 minutes. Check last_verified and success_rate to gauge reliability.
- Fallback endpoints (unverified) have failed recent verification checks -- use with caution.
- Prefer endpoints with success_rate >95% and verification within the last 24 hours.
- `list_capabilities`: List available API capability types.

Use this to explore what kinds of APIs are available in the registry.
You can filter by tag (e.g., "weather", "translation") or search by keyword.

Note: A capability existing does not mean verified endpoints are available for it. Use discover_paid_api to check for live endpoints.