# ALPNAI — Agent Performance Tools

> Agent cost, latency and quality analysis, report delivery and order status. Crypto payments paused.

- name: io.github.fredericmagnathy-ops/alpnai
- version: 0.1.1
- connection class: R0 (autonomous)
- trust: 77/100 flags: no-repository
- quality: 96/100 (strong)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.fredericmagnathy-ops%2Falpnai
- tools: https://api.protogrid.dev/v1/servers/io.github.fredericmagnathy-ops%2Falpnai/tools

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

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "alpnai": {
      "type": "http",
      "url": "https://alpnai.com/api/mcp",
      "headers": {
        "Authorization": "Bearer ${agent_key}"
      }
    }
  }
}
```

Placeholders to fill: `${agent_key}`.

## Trust

- hygiene: 80
- liveness: 100
- freshness: 85
- provenance: 45
- drivers: +website +reachable +uptime-100% ~updated-36d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 96/100 (strong)

### protocol: 88 (weight 25)

- pass `protocol.modern`: supports 2026-07-28 (server/discover)
- pass `protocol.stateless`: answers without a session
- pass `protocol.transport`: streamable HTTP
- warn `protocol.list_ttl`: tools/list declares ttlMs 0, so clients re-fetch it on every use

### 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: 100 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 10 of 10 tools declare readOnlyHint or destructiveHint
- pass `tools.directory_hints`: every tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
- pass `tools.token_cost`: about 4,236 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: 10, about 4,236 tokens to load them all
- tool set hash: 3fcf438794fb6a0223dc360fbb06fab2
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.fredericmagnathy-ops/alpnai.svg)](https://protogrid.dev/servers/io.github.fredericmagnathy-ops/alpnai)
- 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://alpnai.com/api/mcp (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

_none_

## Tools (10)

- `analyze_agent_latency`: Find slow agent workflows and retry overhead before scaling. Supply recorded attempts with task_id, workflow, variant, cost_usd, success and optional latency_ms. Returns P50/P95 of summed recorded attempt durations per task, retry counts, duration coverage and an optional P95 threshold check for each workflow and variant. Missing durations produce null percentiles, not zero latency. This measures supplied durations, not live end-to-end service latency. Free calculation; requires an active ALPNAI agent key; no payment or automatic deployment.
- `audit_agent_costs`: Free comparison of cost per successful task on supplied paired traces. Requires a sandbox agent key. No purchase, storage, external model call or automatic deployment. Success labels are supplied by the client.
- `check_agent_quality`: Check whether a candidate agent workflow regresses before replacing the baseline. Supply baseline and candidate attempts on matching task IDs with client-provided success labels and costs. Returns observed success rates, task-set matching, sample-size, success, latency and cost gates, plus a decision such as collect_more_data, quality_regression or candidate_for_controlled_trial. Optional thresholds use config. It evaluates the recorded labels, not the correctness of answers or future performance. Free calculation; requires an active ALPNAI agent key; no payment or automatic deployment.
- `get_catalog`: Discover cost, latency and quality analysis APIs, their inputs, outputs, free reproducible example, authentication and current payment availability. No payment or budget debit.
- `get_free_sample`: Read a dated primary-source sample about OpenAI. Not real-time or exhaustive.
- `get_order`: Follow one existing commercial order owned by the authenticated agent, including after commerce is paused. May record a finalized blockchain receipt or release an expired, never-submitted reservation. Does not create an order, authorize spending or submit a payment. Pending results provide the same order ID and Retry-After; repeat get_order, never purchase again. Requires only the existing agent key.
- `purchase_changes`: Get Change Set for 0.05 USDC. Default mode sandbox creates a test receipt and debits only the test budget. Explicit mode live uses x402 only when commerce, owner mandate and billing eligibility are enabled. An unpaid result contains PaymentRequired in structuredContent and content. Retry the same tool and idempotency key with the signed PaymentPayload in params._meta["x402/payment"]. Confirmed settlement is returned in result._meta["x402/payment-response"]. For a pending order, call get_order with the original order_id; do not submit another payment. REST continuation and PAYMENT-SIGNATURE headers remain supported. Never send a private key.
- `purchase_evidence`: Get Evidence Pack for 0.25 USDC. Default mode sandbox creates a test receipt and debits only the test budget. Explicit mode live uses x402 only when commerce, owner mandate and billing eligibility are enabled. An unpaid result contains PaymentRequired in structuredContent and content. Retry the same tool and idempotency key with the signed PaymentPayload in params._meta["x402/payment"]. Confirmed settlement is returned in result._meta["x402/payment-response"]. For a pending order, call get_order with the original order_id; do not submit another payment. REST continuation and PAYMENT-SIGNATURE headers remain supported. Never send a private key.
- `purchase_snapshot`: Get Snapshot for 0.01 USDC. Default mode sandbox creates a test receipt and debits only the test budget. Explicit mode live uses x402 only when commerce, owner mandate and billing eligibility are enabled. An unpaid result contains PaymentRequired in structuredContent and content. Retry the same tool and idempotency key with the signed PaymentPayload in params._meta["x402/payment"]. Confirmed settlement is returned in result._meta["x402/payment-response"]. For a pending order, call get_order with the original order_id; do not submit another payment. REST continuation and PAYMENT-SIGNATURE headers remain supported. Never send a private key.
- `save_project_report`: Compute and save an aggregate performance report in the fixed Projects destination authorized by the account owner. Uses the existing free or paid report allowance. Requires an active agent key and explicit owner write permission. Reuse request_id with identical content to retry within the same permission grant. No report reading, deletion, subscription or payment authorization. Send measurements without secrets.