ALPNAI — Agent Performance Tools

io.github.fredericmagnathy-opsPublished by GitHub account fredericmagnathy-opsv0.1.1Updated Oct 27, 2026

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

VerifiedStreamable HTTPWeb executableFinanceData & AnalyticsAI & ML

Overview

AI-generated overview

Remote MCP server for analyzing AI agent cost, latency and quality, saving project reports, and buying paid analysis snapshots with USDC.

What you can do
  • Discover available analysis APIs and read a free dated sample
  • Audit cost per successful task and analyze latency and retry overhead from supplied traces
  • Check whether a candidate workflow regresses against a baseline before replacing it
  • Save an aggregate performance report to the account's Projects destination
  • Follow existing orders and purchase Snapshot, Change Set or Evidence Pack results
When to use it
Useful when you have recorded agent traces with costs and success labels and want to compare workflows, find slow or retry-heavy paths, or gate a replacement on quality, latency and cost before scaling.
Requirements
Remote streamable HTTP endpoint at alpnai.com; no local install. An active ALPNAI agent key sent in the Authorization header, obtained from the provider's start page; a sandbox key for the free audit tool. Paid purchases need commerce, an owner mandate and billing eligibility enabled.
Before you install
The Authorization header carries an agent key that grants access to the account's tools and reports. Paid tools spend USDC: purchase_snapshot, purchase_changes and purchase_evidence default to sandbox test budget but can run in live mode with x402 payments. save_project_report writes to the owner's Projects destination and needs explicit write permission. Traces and success labels you supply are sent to the provider.

Installation

In SourceWeft

  1. Open ALPNAI — Agent Performance Tools in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.fredericmagnathy-ops%2Falpnai/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "alpnai-agent-performance-tools": {
      "type": "http",
      "url": "https://alpnai.com/api/mcp"
    }
  }
}

Tools

10

get_catalog

ALPNAI service catalog

Discover cost, latency and quality analysis APIs, their inputs, outputs, free reproducible example, authentication and current payment availability. No payment or budget debit.

Takes no parameters.

get_free_sample

OpenAI source sample

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

Takes no parameters.

audit_agent_costs

Spend Proof cost analysis

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.

Parametersrunsrequiredconfig

analyze_agent_latency

Latency Lab

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.

Parametersrunsrequiredconfig

check_agent_quality

Quality Gate

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.

Parametersrunsrequiredconfig

save_project_report

Save an agent performance 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.

Parametersinputrequiredtitlerequiredrequest_idrequired

get_order

ALPNAI order status and delivery

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.

Parametersorder_idrequired

purchase_snapshot

Snapshot purchase

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.

Parametersmodesincemandate_ididempotency_keyrequired

purchase_changes

Change Set purchase

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.

Parametersmodesincemandate_ididempotency_keyrequired

purchase_evidence

Evidence Pack purchase

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.

Parametersmodesincemandate_ididempotency_keyrequired

Version history

1
  1. v0.1.1LatestSep 16, 2026

Score

83% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • LicenseNot applicable

    A hosted service is used under its provider's terms, so no license is expected here. This check is left out of the percentage.