ALPNAI — Agent Performance Tools MCP server

• analyze_agent_latencyFree

  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_costsFree

  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_qualityFree

  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_catalogFree

  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_sampleFree

  Read a dated primary-source sample about OpenAI. Not real-time or exhaustive.

• get_orderwrite actionFree

  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_changeswrite actionFree

  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_evidencewrite actionFree

  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_snapshotwrite actionFree

  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_reportFree

  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.

• –Code scanremote-only server, no package to scann/a
• Live reliabilityremote reachable in 2284ms17/20
• Tool poisoning10 tool descriptions checked15/15
• Auth qualityAPI key sent as a header8/15
• Maintenanceno repository listed3/15
• Maintainer identityno repository or website to verify2/10

ALPNAI — Agent Performance Tools: common questions

Is ALPNAI — Agent Performance Tools MCP server safe?

With care: it is graded C, so read the findings first (60/100). Read the ALPNAI — Agent Performance Tools safety report

How do I install ALPNAI — Agent Performance Tools?

It runs remotely at alpnai.com. Add it to Claude Code, Claude Desktop or Cursor with the snippets above, or call it through the mcp.market gateway without installing anything.

Does ALPNAI — Agent Performance Tools need an API key?

Yes. The registry entry asks for Authorization.

Is ALPNAI — Agent Performance Tools maintained?

The latest release is v0.1.1.

Is ALPNAI — Agent Performance Tools up?

100% of our last 3 checks got an answer. We check remote servers about four times a day.

What can I use instead of ALPNAI — Agent Performance Tools?

Servers from other publishers that do the same job: Shopware MCP server, 내만집 (nmjib) — Korean semi-self interior renovation MCP server and Work Order MCP server. Compare all ALPNAI — Agent Performance Tools alternatives.