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.
npx skills add lidonation/Cardano-mcp --skill indexer-setupgit clone --depth 1 https://github.com/lidonation/Cardano-mcpWrote 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.
[](https://agentmods.dev/skills/lidonation/cardano-mcp/indexer-setup)<a href="https://agentmods.dev/skills/lidonation/cardano-mcp/indexer-setup"><img src="https://agentmods.dev/badge/skills/lidonation/cardano-mcp/indexer-setup/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.
<a href="https://agentmods.dev/skills/lidonation/cardano-mcp/indexer-setup"><img src="https://agentmods.dev/badge/skills/lidonation/cardano-mcp/indexer-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00059 | $0.00746 |
| Opus 5 | $0.00030 | $0.00373 |
| Sonnet 5 | $0.00012 | $0.00149 |
| Haiku 4.5 | $0.00006 | $0.00075 |
Grade A, and why
indexer-setup scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Kupo: `curl -sf -m 3 "${KUPO_URL:-http://localhost:1442}/health"` How it starts
The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Check the local indexer before calling it, not after it fails
The indexer module's four tools (watch_address, query_kupo_matches,
get_rollup_status, query_custom_indexer — src/modules/indexer/index.ts)
all assume a local sidecar process is already running: Kupo for the
first three, Yaci Store for the fourth. Nothing calls them proactively —
KUPO_URL and YACI_STORE_URL just default to http://localhost:1442 and
http://localhost:8080 (src/config.ts) whether or not anything is
actually listening there. If no sidecar is running, the tool call fails
with a raw fetch/connection error that doesn't say "start Kupo" — it says
something like ECONNREFUSED.
Workflow
-
Before calling any
watch_address,query_kupo_matches,get_rollup_status, orquery_custom_indexertool, check reachability directly:- Kupo:
curl -sf -m 3 "${KUPO_URL:-http://localhost:1442}/health" - Yaci Store:
curl -sf -m 3 "${YACI_STORE_URL:-http://localhost:8080}"(or whatever base path the specific query in question targets — Yaci Store doesn't have a single fixed health path the way Kupo does, so a plain reachability check against the configured base URL is the honest floor here).
- Kupo:
-
If unreachable, tell the user plainly that no local sidecar is running at that URL — don't call the tool and let it fail first. Point them at:
- Kupo: the official setup docs (
https://cardanosolutions.github.io/kupo/) - Yaci Store:
https://github.com/bloxbean/yaci-store(already linked inquery_custom_indexer's own tool description)
Do not invent a specific
docker runone-liner unless you have actually verified the exact flags for the user's setup (node socket path, network magic, etc.) — Kupo in particular needs either a local node connection or Ogmios, which varies by environment, so a wrong guessed command would send the user down the wrong path. - Kupo: the official setup docs (
-
If
KUPO_URL/YACI_STORE_URLare unset, note they're defaulting tolocalhost, which only works if the sidecar happens to be running on this same machine — remote indexer setups need the env var set explicitly. -
Once reachable, proceed with the requested indexer tool call normally.
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.
- today First seen · 55 lines · 59 tokens per session scan A 675f46da8e71
indexer-setup is a skill published in the GitHub repository lidonation/Cardano-mcp (2 stars, last pushed yesterday), licensed MIT. It adds 59 tokens to every session and 746 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-21.
Other skills, from other repositories
midnight-network
Guide to Midnight Network infrastructure, validators, indexers, and network operations. Use when users need to run Midnight validators and participate in consensus, set up and configure Midnight indexers for blockchain data, configure network nodes and infrastructure, monitor validator performance and network health…
cli-anything-eth2-quickstart
Use eth2-quickstart to autonomously deploy a hardened Ethereum node, install execution and consensus clients, configure validator metadata, expose RPC safely, and inspect node health with structured JSON output.
devloop
Goal-driven development loop — define objective, write rules with key-results, verify visually, sync to issue tracker.
skill0
Root index of x-cmd skill0 sub-skills. Defines the OKR-style agent workflow (goal → rule-verified results → execute), skill discovery, and agent tooling preferences. Style: principle-first, concise, delegate specifics to authoritative external sources.
multichain-deployment
Use when deploying the same protocol to multiple chains at the same address. Covers CREATE2 for deterministic addresses, deployment registries, chain-specific configuration, multi-chain testing, and canonical deployment patterns.
l2-deployment
Use when deploying contracts to L2 networks (Base, Optimism, Arbitrum). Covers L2-specific considerations, PUSH0 compatibility, gas estimation, L1 data costs, bridge integration, and deployment scripts.