A developer guide for connecting applications to the aurora-agent backend over HTTP or MCP’s standard tool-call connection. It covers the bioprism-api gateway, which exposes the same backend through web requests or MCP.

Use it to start the gateway, call tools from TypeScript or Python, choose REST or MCP, and test the wiring. It documents bearer authentication, API discovery, request IDs, and the required response checks.

It helps developers choose a connection method and understand authentication, health checks, and failure responses. It also clarifies that an HTTP success status alone does not mean the requested tool succeeded.

aurora-sdks — Skill for Claude Code by AURORA-NEURO

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add AURORA-NEURO/aurora-agent --skill aurora-sdks

Clone the repo

git clone --depth 1 https://github.com/AURORA-NEURO/aurora-agent

Made for: Claude Code.

Or install aurora-agent, the plugin that ships this one along with the rest of its 4 skills, 7 commands, 1 agent.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/aurora-neuro/aurora-agent/aurora-sdks/github.svg)](https://agentmods.dev/skills/aurora-neuro/aurora-agent/aurora-sdks)

Your own site

<a href="https://agentmods.dev/skills/aurora-neuro/aurora-agent/aurora-sdks"><img src="https://agentmods.dev/badge/skills/aurora-neuro/aurora-agent/aurora-sdks/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/aurora-neuro/aurora-agent/aurora-sdks"><img src="https://agentmods.dev/badge/skills/aurora-neuro/aurora-agent/aurora-sdks.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 685 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00062	$0.00685
Opus 5	$0.00031	$0.00342
Sonnet 5	$0.00012	$0.00137
Haiku 4.5	$0.00006	$0.00068

Measured 10d ago against content hash 428e2ed23297, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade B, and why

aurora-sdks scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Asks the agent to reveal its instructionsmediumSystem prompt leakage

Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.

header, or secret argument* — keys come only from a no-echo prompt or a named

plugins/aurora-agent/skills/aurora-sdks/SKILL.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Integrating with aurora-agent

Three transports, one Rust implementation — a REST call and an MCP tools/call reach exactly the same code and produce the same evidence-bearing result.

HTTP gateway (`bioprism-api`)

Launch (from the checkout root; docs/HTTP_API.md is the full reference):

cargo run -p bioprism-api -- --root . --bind 127.0.0.1:8787 \
  --token <at-least-16-visible-bytes> \
  --mission-state .local/mission-state.json \
  --mission-queue-state .local/mission-queue.json \
  --event-state .local/event-state.json \
  --reconciliation-state .local/reconciliation-state.json \
  --artifact-state .local/artifact-state.json

Health (public): GET /healthz, GET /readyz. Machine contract: GET /v1/openapi.json; link index GET /v1.
Any of the MCP tools: POST /v1/tools/{name} with a JSON object body; JSON-RPC at POST /v1/rpc.
Bearer auth, constant-time compare; CORS for local tools; every response carries X-Request-Id. No TLS/HTTP2 — put a reverse proxy in front.
Refusal semantics ride INSIDE the envelope: check mcp.result.isError plus the inner {"ok": false, "error": ...} — outer HTTP 200 does not mean the tool succeeded.

TypeScript SDK

typescript/ in the checkout — @aurora-neuro/prism-sdk, ESM, zero runtime dependencies. ApiClient covers essentially the whole REST surface (~349 methods) plus helpers: waitMission, eventStream (SSE), toolChecked (schema-aware preflight then call). Build: npm ci --ignore-scripts && npm run build; tests use Node's built-in runner.

Python SDK

python/ in the checkout — prism-sdk, requires-python >= 3.11, zero dependencies, console script aurora-agent (python -m prism_sdk also works). Sync + asyncio MCP clients and ApiClient/AsyncApiClient for HTTP. Security invariant worth preserving in anything you build on it: the CLI parser deliberately has no API-key, token, header, or secret argument — keys come only from a no-echo prompt or a named environment variable, and no shell is ever started by that boundary.

Read the full file on GitHub · 59 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

10d ago First seen · 59 lines · 62 tokens per session scan B 428e2ed23297

Subscribe to this mod's changes

aurora-sdks is a skill published in the GitHub repository AURORA-NEURO/aurora-agent (1 stars, last pushed today), licensed Apache-2.0. It adds 62 tokens to every session and 685 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (asks the agent to reveal its instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Backend and APIs Data and AI claude claude-plugin decision-support mcp mcp-server model-context-protocol

microsoft-graph

The maintained single-binary successor to the retiring mgc - every MSP-relevant Microsoft Graph surface, plus an offline store that finds wasted licenses, privileged-access risks, over-privileged third-party app consents, and stale devices no single API call can. Trigger phrases: find unused microsoft 365 licenses…

Servosity/msp-skills · 129 tokens

gradient

The Synthesize partner API from the terminal - every endpoint, plus a usage-push ledger, billing drift detection, and alert-to-ticket tracing no other Gradient tool has. Trigger phrases: push usage counts to gradient, sync usage to synthesize, check my synthesize integration status, find unmapped gradient accounts…

Servosity/msp-skills · 86 tokens

apiany-integration

Use when a user asks to integrate with APIAny, choose or compare APIAny models, estimate APIAny credits or pricing, migrate OpenAI-compatible clients to APIAny, generate APIAny model usage examples, or run confirmed APIAny image and video tasks through the APIAny MCP server.

ailingqu/ApiAny.AI-MCP · 62 tokens

api-services

API reference for built-in service providers (LLM, Speech, Graph). Use when looking up service interfaces, provider capabilities, or integration patterns.

cyanheads/secedgar-mcp-server · 32 tokens

opik-instrument

Add Opik tracing to an existing app and verify a real trace lands. Installs the Opik package, detects the language and LLM framework, adds the minimum tracing, runs a safe representative path, confirms a trace in Opik, and returns the trace link. Use for "instrument my code", "add opik tracing", "add observability"…

comet-ml/opik-mcp · 101 tokens

aba-precision-protocol

FOUNDATIONAL BEHAVIORAL PROTOCOL — ABA-based precision execution rules. Every prompt processed must follow these rules. Mistakes caught late create intermittent reinforcement of wrong patterns. Stop-fix-verify before proceeding.

dcostenco/prism-coder · 48 tokens

aurora-sdks