Sg Company Lookup Mcp

Created By
main2 months ago
Overview

DAEE Engine

Dominion Agent Economy Engine

The infrastructure layer for autonomous agents that earn, transact, and build trust in the open economy.

License: MIT Observatory x402 Extension Smithery npm PulseMCP


What is this?

DAEE is a monorepo powering the Dominion ecosystem — a set of MCP servers, trust infrastructure, and settlement tooling that lets AI agents operate as first-class economic actors.

The problem: Agents need to pay for APIs, but there's no way to know if the agent on the other side is trustworthy before settling a payment.

Our solution: Behavioral trust scoring that plugs directly into the payment flow.

Agent A wants to call a paid API
┌─────────────────────┐
│  x402 Payment Flow  │
│                     │
│  beforeSettle hook  │──► Query Dominion Observatory
│                     │       │
│  Trust score: 82    │◄──────┘
│  Decision: PASS     │
│                     │
│  Settlement: GO     │──► USDC transfer on Base
└─────────────────────┘

Architecture

ComponentWhat it does
Dominion ObservatoryLive behavioral trust registry — tracks interaction history, latency, success rates for MCP servers. Try it →
x402 Trust-Provider ExtensionPlugs Observatory data into x402's onBeforeSettle hook. Gates payments on trust. PR →
LangChain Trust GateDrop-in LangChain tool — TrustGateTool for agent pipelines
Testnet DemoEnd-to-end: Observatory query → trust gate → USDC transfer on Base Sepolia
Trust-Provider SpecFormal spec (v0.1) for the trust-provider interface

MCP Servers (Live)

Production MCP servers powering Singapore government data for AI agents:

ServerDomainStatus
sg-cpf-calculatorCPF contributions, age-banded rates, OA/SA/MA allocation✅ Live
sg-company-lookupUEN validation, ACRA lookups, officer data, SSIC codes✅ Live
sg-regulatory-dataLevy rates, filing deadlines, EP benchmarks, holidays✅ Live
sg-workpass-compassEmployment Pass COMPASS scoring✅ Live
asean-trade-rulesASEAN trade regulations and tariff data✅ Live

All servers are registered on the Dominion Observatory with behavioral trust scores.

Quick start

Try the trust gate (no wallet needed)

cd testnet-demo
npm install
npm run demo:dry-run

Use in LangChain

from langchain_trust_gate import TrustGateTool

tool = TrustGateTool()
result = tool.invoke({"agent_id": "sg-cpf-calculator"})
# {'decision': 'PASS', 'score': 0.82, ...}

Use in TypeScript

import { observatoryEvaluate } from "@dominion/trust-provider";

const evaluation = await observatoryEvaluate({
  schema: "x402-trust-query-v0.1",
  payer: { agent_id: "sg-cpf-calculator" },
  resource: { url: "https://api.example.com/data", method: "GET" },
  requested_at: new Date().toISOString(),
});

if (evaluation.decision === "PASS") {
  // proceed with payment settlement
}

Query the Observatory directly

curl https://dominionobservatory.com/api/agent-query/sg-cpf-calculator

Embed a trust badge

Display your MCP server's live trust score as a badge in any README or documentation:

![Trust Score](https://dominionobservatory.com/badge/your-server-slug)

Examples with real servers:

![Trust Score](https://dominionobservatory.com/badge/sg-cpf-calculator)

The badge auto-updates every 5 minutes and is color-coded:

ColorScoreDecision
Green60+PASS
Yellow40-59UNCERTAIN
Red< 40FAIL
GrayServer not found

Use it in your MCP server's README to signal trust to consumers.

How trust scoring works

The Observatory tracks behavioral attestation data for every registered MCP server:

SignalWhat it measures
Interaction countHow much real usage the server has
Success rateReliability under real-world conditions
Avg latencyPerformance consistency
Registration ageTime-based trust accumulation

These signals produce a trust score (0-100) mapped to decisions:

ScoreDecisionTier
60+PASSSilver+ — proceed with settlement
40-59UNCERTAINReview band — apply extra checks
<40FAILBelow Bronze — block settlement

Integrations

Packages

PackageRegistryDescription
@dominion/trust-providernpmTypeScript trust-provider with Observatory adapter
langchain-trust-gatePyPILangChain tool for behavioral trust scoring

Project structure

daee-engine/
├── dominion-observatory/       # Trust registry (Cloudflare Workers)
├── packages/
│   ├── trust-provider/         # npm: @dominion/trust-provider
│   └── langchain-trust-gate/   # PyPI: langchain-trust-gate
├── specs/                      # Formal specifications
├── testnet-demo/               # x402 + Base Sepolia demo
├── sg-cpf-calculator-mcp/      # MCP server: CPF
├── sg-company-lookup-mcp/      # MCP server: Company data
├── sg-regulatory-data-mcp/     # MCP server: Regulatory
├── sg-workpass-compass-mcp/    # MCP server: Work passes
├── asean-trade-rules-mcp/      # MCP server: ASEAN trade
├── benchmarks/                 # Performance benchmarks
├── decisions/                  # Architecture decision records
└── docs/                       # Documentation

Contributing

PRs welcome. See individual package READMEs for development setup.

License

MIT

Server Config

{
  "mcpServers": {
    "sg-company-lookup-mcp": {
      "url": "https://sg-company-lookup-mcp.sgdata.workers.dev/mcp"
    }
  }
}
Project Info
Created At
2 months ago
Updated At
6 days ago
Author Name
main
Star
-
Language
-
License
-
Category
Tags

Recommend Servers

View All
Thousand Api

8 hours ago
Meok Bs7121 Mcp

17 hours ago
Hellogrowthcrm

2 days ago
GovQL
@Alex Stout

# govql-mcp-server An MCP (Model Context Protocol) server for [GovQL](https://govql.us) — gives AI clients like Claude Desktop, Claude Code, and Cursor direct access to the US Congressional GraphQL API at [api.govql.us/graphql](https://api.govql.us/graphql) without bespoke HTTP wiring. For the design rationale (why FastMCP-Python, the passthrough+curated philosophy, roadmap through v0.4), see [design.md](https://github.com/govql/govql/blob/main/mcp-server/docs/design.md). ## What you can do with it Ask an agent questions like: - *"How did Vermont's two senators vote on the most recent nomination?"* - *"Which legislators in the 118th Congress switched parties during their service?"* - *"Compare Senator Sanders' voting record to Senator Murkowski's on cloture votes in the most recent Congress."* The agent picks the right tool, writes the GraphQL query against the live schema, and parses the response — no manual API wrangling. ## Install The server runs as a per-client subprocess over stdio. Pick your client: ### Claude Desktop Edit `claude_desktop_config.json` (Settings → Developer → Edit Config): ```json { "mcpServers": { "govql": { "command": "uvx", "args": ["govql-mcp-server"] } } } ``` Restart Claude Desktop. The `govql` tools appear in the tools panel. ### Claude Code Add to `.mcp.json` in your project (or `~/.mcp.json` for global): ```json { "mcpServers": { "govql": { "command": "uvx", "args": ["govql-mcp-server"] } } } ``` ### Cursor Settings → MCP → Add Server. Use the same `command` / `args` as above. ### Other clients Any MCP-compatible client that supports stdio servers will work. The command is `uvx govql-mcp-server` with no required arguments. ## Tools | Tool | Purpose | |---|---| | `execute_graphql` | Run any GraphQL query against the GovQL endpoint. Returns the result plus an `last_ingest` timestamp so the agent can reason about data freshness. | | `list_types` | Returns the names and kinds of every type in the GovQL schema. Optional `kind` filter (`"OBJECT"`, `"INPUT_OBJECT"`, `"ENUM"`, etc.) to narrow further. Start here when you don't know what's queryable. | | `describe_type` | Returns one type's full details — fields, arg signatures, input fields, enum values. Call after `list_types` to learn the shape of a specific type before writing a query. | ## Configuration All env vars are optional — the package is zero-config for end users. | Env var | Default | Purpose | |---|---|---| | `GOVQL_ENDPOINT` | `https://api.govql.us/graphql` | Endpoint to query. Override to point at a local dev stack. | | `GOVQL_TIMEOUT_MS` | `30000` | Per-request HTTP timeout. | | `LOG_LEVEL` | `INFO` | Logging level. Logs go to stderr only (stdout is reserved for the MCP transport). | ## Limits (enforced by the upstream API) - Max query depth: 10 - Max query complexity: ~10 billion points (`first: N` multiplies child cost by N — keep page sizes reasonable on deeply nested queries) - Rate limit: 100 requests / 60 s per source IP A depth or complexity violation surfaces as a GraphQL `errors` entry in the tool response so the agent can adjust and retry. ## Data freshness Every `execute_graphql` response includes a `last_ingest` ISO timestamp. Vote data refreshes hourly; legislator data refreshes daily. ## Status Version 0.1.0 ships three foundational tools: a GraphQL passthrough (`execute_graphql`) and two narrow schema-discovery tools (`list_types`, `describe_type`). Curated higher-level tools (`find_legislator`, `get_voting_record`, `compare_voters`, etc.) are planned for subsequent releases — see [design.md](https://github.com/govql/govql/blob/main/mcp-server/docs/design.md) for the roadmap. ## Links - [GovQL project site](https://govql.us) - [GraphQL API](https://api.govql.us/graphql) - [Source / issues](https://github.com/govql/govql)

a day ago
Meok Bs7121 Mcp

17 hours ago
Meteomatics

2 days ago