portal

portal is a skill for Claude Code from subsquid-labs/portal-mcp-server. It costs 64 tokens per session (6,529 once invoked), scanned A, original, MIT.

A guide for querying and analyzing data from more than 130 blockchain networks, including transactions, events, traces, instructions, and other chain-specific records.

In plain words
What is it for?
Use it to find datasets, inspect token transfers or contract activity, analyze trades and deployments, or build longer-running data pipelines.
Why use it?
It helps choose between an interactive query, a raw data export, or a durable indexer when investigating blockchain activity.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the portal plugin — 4 skills, 1 MCP server shipped together

Good fit Use it to find datasets, inspect token transfers or contract activity, analyze trades and deployments, or build longer-running data pipelines.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/subsquid-labs/portal-mcp-server/portal
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 subsquid-labs/portal-mcp-server --skill portal
Clone the repo
git clone --depth 1 https://github.com/subsquid-labs/portal-mcp-server

Made for: Claude Code.

Or install portal, the plugin that ships this one along with the rest of its 4 skills, 1 MCP server.

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.

agentmods badge for portal

README.md
[![agentmods](https://agentmods.dev/badge/skills/subsquid-labs/portal-mcp-server/portal/github.svg)](https://agentmods.dev/skills/subsquid-labs/portal-mcp-server/portal)
Your own site
<a href="https://agentmods.dev/skills/subsquid-labs/portal-mcp-server/portal"><img src="https://agentmods.dev/badge/skills/subsquid-labs/portal-mcp-server/portal/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.

agentmods 80×15 button for portal

Your own site · 80×15
<a href="https://agentmods.dev/skills/subsquid-labs/portal-mcp-server/portal"><img src="https://agentmods.dev/badge/skills/subsquid-labs/portal-mcp-server/portal.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,529 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00064 $0.06529
Opus 5 $0.00032 $0.03265
Sonnet 5 $0.00013 $0.01306
Haiku 4.5 $0.00006 $0.00653

Measured 4d ago against content hash 41a4c9486809, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

portal 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 4d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

description: "Query blockchain data across 130+ networks with SQD Portal, including EVM, Solana, Substrate, Bitcoin, Tron, and Hyperliquid, and choose the right execution path: Portal MCP for bounded answers, Portal Stre
plugins/portal/skills/portal/SKILL.md · 487 lines

How it starts

The opening of the file, as written. The whole thing — 487 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Portal

Query and analyze blockchain data across 130+ networks using SQD Portal. Use this skill to decide whether the job belongs in SQD Portal MCP tools, a raw Portal Stream API/curl request, or a durable Pipes/Squid indexer.

This skill should not be treated as a static copy of the MCP tool catalog. When the SQD Portal MCP server is available, read sqd://tools for the current grouped tool guide and sqd://tools/{tool_name} for exact per-tool guidance.

When to Use This Skill

Use this skill when you need to:

  • Query blockchain event logs, transactions, traces, instructions, Substrate events/calls, Bitcoin UTXOs, Tron transfers, or trade fills
  • Find the correct Portal dataset name for a blockchain
  • Analyze on-chain activity (token transfers, DeFi events, contract deployments, trading)
  • Choose between Portal MCP tools, raw Portal Stream API/curl, or a durable Pipes/Squid indexer

Use Portal MCP tools for bounded interactive answers, summaries, charts, investigation pivots, entity resolution, and normal chat-sized evidence.

Use raw Portal Stream API or curl when the user asks for raw rows, full exports, exact reproducible requests, NDJSON/CSV/files, or a query shape that should run outside the MCP client.

Recommend Pipes or a Squid when the user needs recurring sync, long backfills, joins, transformations, database storage, production APIs, alerts, dashboards, or app-owned indexed state.

Choose the Right SQD Surface

Need Use Why
Bounded answer in chat Portal MCP tools Best defaults, validation, normalized envelopes, pagination, freshness, and coverage notes
Network, entity, or tool discovery sqd://tools, sqd://datasets, discovery MCP tools Keeps routing current without duplicating catalogs
Raw rows or export Portal Stream API / curl Produces reproducible NDJSON and avoids chat preview truncation
Production data product Pipes / Squid Durable indexing, transforms, storage, retries, and serving APIs

Read the full file on GitHub · 487 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.

  1. 4d ago Changed · +3 lines 41a4c9486809
  2. 7d ago Changed · -16 lines 8b7f99b96b45
  3. 11d ago First seen · 500 lines · 64 tokens per session scan A e697cc351d1a

Subscribe to this mod's changes

portal is a skill published in the GitHub repository subsquid-labs/portal-mcp-server (1 stars, last pushed 3d ago), licensed MIT. It adds 64 tokens to every session and 6,529 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 2026-08-31.

Related

Other skills, from other repositories

walkeros-create-destination

Use when creating a new walkerOS destination to send events to a vendor or API (GA4/gtag, Meta/Facebook Pixel, Mixpanel, Amplitude, a custom HTTP API, Measurement Protocol), web or server-side. Example-driven workflow: research the vendor SDK and define step examples before implementing the destination interface, env…

elbwalker/walkerOS · 77 tokens

walkeros-create-source

Use when creating a new walkerOS source to capture events (browser source, dataLayer interception, server/HTTP source, webhook receiver, event capture), web or server-side. Example-driven workflow: research the input format and define step examples before implementing the push interface, createTrigger, and env pattern.

elbwalker/walkerOS · 65 tokens

implementing-mcp-tools

Guide for exposing PostHog product endpoints as MCP tools. Use when creating new or updating API endpoints, adding MCP tool definitions, scaffolding YAML configs, or writing serializers with good descriptions. Covers the full pipeline from Django serializer to generated TypeScript tool handler.

PostHog/posthog · 58 tokens

subgraph-development-guide

Guide to building blockchain data indexes with The Graph — subgraph architecture, schema design, mapping handlers, deployment, and querying. Covers GraphQL APIs for DEX data, token transfers, and DeFi protocol events. Use when explaining blockchain indexing or building custom data pipelines.

nirholas/three.ws · 59 tokens

chainlink-oracle-guide

How Chainlink oracle price feeds work — architecture, reading feeds on-chain, available pairs, the aggregator model, and oracle security. Covers how DeFi protocols (Aave, Sperax, Compound) rely on Chainlink for accurate pricing. Use when explaining oracles, price feeds, or DeFi infrastructure.

nirholas/three.ws · 68 tokens

bnb-chain-toolkit-guide

Guide to the BNB Chain Toolkit — a modular TypeScript toolkit for building, deploying, and interacting with smart contracts on BNB Chain. Includes BEP-20 token utilities, DeFi integrations, wallet management, and cross-chain bridging. Built for BNB Chain Hackathon by the Sperax team.

nirholas/three.ws · 67 tokens