io.github.strale-io/strale

Official9 tools

by strale-io · TypeScript

Strale - 290+ API capabilities for AI agents

290+ quality-scored API capabilities for AI agents across 27 countries via MCP.

Connect to 290+ quality-scored APIs across 27 countries for AI agent use.

Topics

ai-agentsapieu-ai-actmcpqualitytrusttypescriptagentic-paymentscompliancecrewaidrizzle-ormhonoiban-validationkyblangchainmodel-context-protocolsanctions-screeningx402

Captured live from the server via tools/list.

strale_ping

Checks that the Strale API is reachable and the MCP server is running. Call this before a series of capability executions to verify connectivity, or when troubleshooting connection issues. Returns server status, version, tool count, capability count, solution count, and a timestamp. No API key required.

No parameters.

strale_getting_started

Lists the free capabilities available without an API key and explains how to get started. Call this on first connection to see what you can do immediately. Returns 5 free capability slugs (email-validate, dns-lookup, json-repair, url-to-markdown, iban-validate) with descriptions, example inputs, and instructions for accessing the full registry of 271 paid capabilities. No API key required.

No parameters.

strale_execute

Executes a Strale capability by slug and returns the result. Use this when you need to perform any verification, validation, lookup, or data extraction from the 271-capability registry. Call strale_search first to find the right slug and required input fields. Returns a result object with the capability output, quality score (SQS), latency, price charged, and data provenance. Five free capabilities work without an API key (10/day limit). Paid capabilities debit from the wallet — check strale_balance first for high-value calls.

Parameters (3)

slugstringrequired
Capability slug from strale_search results, e.g. 'swedish-company-data', 'vat-validate', 'iban-validate'
inputsobjectrequired
Input parameters matching the capability's required fields. Check strale_search results for the expected input_fields.
max_price_centsnumber
Maximum price in EUR cents. Default: 200 (€2.00). Execution fails if capability costs more.

strale_search

Searches the Strale capability registry by keyword, category, or natural language query. Use this when you need to find the right capability for a task but don't know the exact slug. Returns matching capabilities and solutions ranked by relevance, each with slug, name, description, category, price in EUR cents, and current SQS quality score. The registry contains 271 capabilities across compliance, finance, web intelligence, developer tools, and more. No API key required to search.

Parameters (3)

querystringrequired
Search keyword (matched against name, description, slug)
categorystring
Filter by category: compliance, validation, data-extraction, developer-tools, web3, security, domain-intel, recruiting, sales, legal, text
offsetnumber
Number of results to skip (for pagination). Default: 0

strale_balance

Returns the current Strale wallet balance. Call this before executing paid capabilities to verify sufficient funds, or after a series of calls to reconcile spend. Returns balance in EUR cents (integer) and formatted EUR string. Requires an API key — returns an auth instruction if none is configured.

No parameters.

strale_methodology

Returns Strale's trust methodology as a short reference document — covers test cadence, audit-trail integrity, and provenance. No API key required.

No parameters.

strale_trust_profile

Returns the trust profile for a capability or solution. Call this before relying on a capability for high-stakes decisions, or when a user asks how reliable a specific check is. Returns SQS score (0-100), Quality grade (A-F), Reliability grade (A-F), execution guidance (direct, retry, queue, or fallback), 30-day test history, known limitations, and cost envelope. No API key required.

Parameters (2)

slugstringrequired
Capability or solution slug, e.g. 'swedish-company-data' or 'eu-company-due-diligence'
typestring
Whether this is a capability or a bundled solution

strale_transaction

Retrieve a past execution record by transaction ID. Returns inputs, outputs, latency, price, data provenance, success/failure status, and failure categorization. Use this to inspect what a previous strale_execute call returned, debug failures, or provide an audit trail. Free-tier transactions are accessible by ID without an API key.

Parameters (1)

transaction_idstringrequired
Transaction ID returned from a strale_execute call

strale_web3_assurance

Returns a decision-ready answer about an on-chain counterparty (wallet, smart contract, token, DeFi protocol, or bridge) in a single call. Surfaces verdict (proceed/review/block/insufficient_evidence), reason_codes (machine-parsable UPPERCASE_SNAKE_CASE), critical_flags, suggested_action, evidence map (sanctions, mixer-graded, scam-cluster, wallet-history, token-safety, contract-verification, protocol-risk, EAS attestations, ERC-8004 reputation, more), and a sidecar audit_url. Two modes: 'outbound' (agent vetting recipient pre-payment, full evaluator set, 8s budget) or 'reverse-call' (service publisher gating an inbound x402 buyer in real-time, critical evaluators only, sub-second SLA). Use before any agent transacts on-chain — sending value, swapping, staking, minting, bridging, or interacting with a contract.

Parameters (8)

targetstringrequired
On-chain target. EVM wallet/contract/token (0x...), Solana address, or DeFi protocol slug (e.g. 'aave', 'uniswap-v3').
target_typestring
Target kind. Inferred when omitted: 0x... → wallet (default), .eth/.sol → wallet, slug → protocol.
chainstring
Chain. EVM: 'ethereum' (default), 'base', 'polygon', 'arbitrum', 'optimism', 'bsc'. Or 'solana'.
actionstring
Optional intended action. When provided, enables pre-trade simulation (outbound mode) and tunes verdict severity.
amount_usdnumber
Optional amount in USD. Sharpens verdict for high-value flows.
modestring
Default 'outbound' (agent → recipient, 8s budget, all evidence). Use 'reverse-call' when you are an x402 service publisher gating an inbound buyer (critical evidence only, sub-second SLA).
agent_idstring
Optional ERC-8004 agent identifier for the calling agent.
caller_jurisdictionstring
Optional ISO country code for jurisdiction-aware verdict (US, EU, UK, etc.).

README.md7 KBView on GitHub

Strale

Trust and quality infrastructure for AI agents.

What is Strale

Strale is a capability marketplace for AI agents. Agents call strale.do() at runtime to access 290+ verified capabilities — company lookups, compliance checks, financial validation, Web3 security, and more — plus 100 bundled solutions for multi-step workflows like full KYB checks or company due diligence. No hardcoded integrations or credential management.

Every capability is continuously tested and assigned a Strale Quality Score (SQS): a 0-100 confidence score derived from two independent profiles — a Quality Profile (code correctness, schema compliance, error handling, edge cases) and a Reliability Profile (current availability, rolling success, upstream health, latency) — combined via a published matrix. Agents get reliable, scored tools. You get observability into what your agent is actually doing.

Quick Start: MCP Server

Recommended: Streamable HTTP (remote, no install)

json

{
  "mcpServers": {
    "strale": {
      "type": "streamableHttp",
      "url": "https://api.strale.io/mcp",
      "headers": {
        "Authorization": "Bearer sk_live_your_key_here"
      }
    }
  }
}

No installation required. Works with Claude Desktop, Claude Code, Cursor, and any MCP client supporting Streamable HTTP.

Local (stdio)

json

{
  "mcpServers": {
    "strale": {
      "command": "npx",
      "args": ["-y", "strale-mcp"],
      "env": {
        "STRALE_API_KEY": "your_api_key"
      }
    }
  }
}

Five capabilities (email-validate, dns-lookup, json-repair, url-to-markdown, iban-validate) are available without an API key. Get a key and €2 free credits at strale.dev.

Quick Start: TypeScript SDK

bash

npm install straleio

typescript

import Strale from "straleio";

const strale = new Strale({ apiKey: process.env.STRALE_API_KEY });

const result = await strale.do("eu-vat-validate", { vat_number: "SE556000000001" });
console.log(result);

Quick Start: Python SDK

bash

pip install straleio

python

from straleio import Strale

strale = Strale(api_key="your_api_key")
result = strale.do("eu-vat-validate", {"vat_number": "SE556000000001"})

Packages

Package	Registry	Description
`strale-mcp`	npm	MCP server — 290+ capabilities via Claude, Cursor, any MCP host
`straleio`	npm	TypeScript/JavaScript SDK
`straleio`	PyPI	Python SDK
`langchain-strale`	PyPI	LangChain toolkit — 250+ tools via `StraleToolkit`
`crewai-strale`	PyPI	CrewAI integration — drop-in BaseTools for agents
`strale-semantic-kernel`	npm	Semantic Kernel plugin for .NET and TypeScript agents
`composio-strale`	PyPI	Composio integration — 250+ tools as Composio custom actions

Web3

17 Web3 capabilities and 9 bundled solutions for on-chain agents: wallet risk scoring (GoPlus), token honeypot detection, ENS resolution, DeFi protocol TVL and fees (DeFi Llama), gas oracle, EU MiCA VASP verification (ESMA register), and market sentiment. All available via the x402 payment protocol — pay per call with USDC on Base mainnet, no signup required.

code

GET https://api.strale.io/x402/catalog

Quality Scoring (SQS)

Every capability has a Strale Quality Score (SQS) from 0 to 100, built on a dual-profile model:

Quality Profile (QP): Measures code-level quality across four factors — correctness (50%), schema compliance (31%), error handling (13%), and edge case coverage (6%). Upstream failures are excluded.
Reliability Profile (RP): Measures operational dependability — upstream availability, latency consistency, error recovery, and degradation handling. Factor weights vary by capability type (API-dependent, algorithmic, mixed).

The two profiles combine via a published 5x5 matrix with interpolation into the final SQS score. Grades run A through E (A >= 90, B >= 75, C >= 50, D >= 25, E < 25), computed over a recency-weighted rolling 10-run window.

Scores are public. Check any capability:

code

GET https://api.strale.io/v1/quality/eu-vat-validate

Agents can set a min_sqs threshold on any POST /v1/do call — requests are rejected if the capability's current score falls below the threshold.

Agent Skills & Code Examples

Teach your AI coding agent how to use Strale:

Agent Skills — SKILL.md files for Claude Code, Cursor, Copilot, and Codex. Copy skills/strale/ into your project's .claude/skills/, .github/skills/, or .cursor/skills/ directory.

Code examples:

Verify a company with Strale (Python)
Validate IBANs — free, no API key (Python)
Build an agent with Strale (TypeScript)
Connect Strale to Claude (setup guide)

Strale is the trust layer for AI agents.

IDE Rules for Safe Data Handling

Drop these files into your project to give your coding agent security guidance for trust-sensitive data (IBANs, company registries, sanctions, PII):

Cursor: Copy docs/ide-rules/strale-compliance.mdc to .cursor/rules/
Windsurf: Copy docs/ide-rules/strale-compliance.windsurfrules to your project root, or into .windsurf/rules/ as a .md file
Claude Code: Copy the snippet from docs/claude-md-snippet.md into your project's CLAUDE.md

These rules prevent the most common vibe-coding vulnerabilities: client-side IBAN validation, hardcoded API keys, missing provenance metadata, and direct registry scraping. Free-tier endpoints are referenced as safe defaults that require no API key.

License

MIT

Install

Configuration

Environment variables

STRALE_API_KEYrequiredsecret

Your Strale API key (starts with sk_)

claude_desktop_config.json

{
  "mcpServers": {
    "strale": {
      "command": "npx",
      "args": [
        "-y",
        "strale-mcp@0.2.4"
      ],
      "env": {
        "STRALE_API_KEY": "<YOUR_STRALE_API_KEY>"
      }
    }
  }
}

Topics

strale_ping

strale_getting_started

strale_execute

strale_search

strale_balance

strale_methodology

strale_trust_profile

strale_transaction

strale_web3_assurance

Strale

What is Strale

Quick Start: MCP Server

Recommended: Streamable HTTP (remote, no install)

Local (stdio)

Quick Start: TypeScript SDK

Quick Start: Python SDK

Packages

Web3

Quality Scoring (SQS)

Links

Agent Skills & Code Examples

IDE Rules for Safe Data Handling

License

Install

Configuration