Plexus
Thalamic
AIエージェントのための連邦インテリジェンス基盤。
ThalamicはPLEXUSを構築しています — 米国政府の生データをスコアリング済み・統合済みのインテリジェンスに変換する、唯一のコール単位課金APIです。連邦データソース41件。認知推論エンジン12基。インテリジェンス製品5種。支払いはx402経由でBase上のUSDCで行います。APIキーもサブスクリプションも不要です。
PLEXUSインテリジェンスAPI
ライブエンドポイント: https://plexus-public-production.up.railway.app
インテリジェンス製品 — $0.20–$0.35/コール
スコアリング済み・統合済みのレポート。4–6のソースを組み合わせて0–100のリスクスコアを算出します。
製品 | ソース | 価格 |
| EPA + OSHA + CFPB + CourtListener + OpenSanctions + GLEIF | $0.35 |
| FEC + USASpending + Federal Register + Congress.gov | $0.35 |
| OSHA + EPA + SAM.gov + FMCSA | $0.30 |
| NPI + CMS Medicare + FDA + CFPB | $0.30 |
| IRS 990 + GLEIF + CFPB + CourtListener | $0.20 |
データアダプター — $0.01–$0.03/コール
29の連邦データソースへの直接的かつ正規化済みのアクセス:
fec · epa · osha · sec · courtlistener · opensanctions · gleif · cfpb · npi · cms-payments · fda · fda-food · bls · census · fema · fmcsa · usaspending · sam · propublica-990 · nhtsa · worldbank · usgs · federal-register · clinical-trials · fdic · noaa · congress · college-scorecard · web-extract
AI推論エンジン — $0.05–$0.15/コール
assertion-router · gscore · tribunal · postcog · whetstone · tessryx · verify · oracle-router · daap · homeostasis · signal-diversity
Related MCP server: CorteX402
クイックスタート
PLEXUSはx402を使用しています — Base上のUSDCでコールごとに支払う方式。サインアップは不要です。
# Company risk score
curl -X POST https://plexus-public-production.up.railway.app/v1/products/company-risk \
-H "Content-Type: application/json" \
-d '{"entity": "ExxonMobil"}'
# Returns HTTP 402 with payment details → pay → retry → get scored intelligence
# Direct FEC data
curl -X POST https://plexus-public-production.up.railway.app/v1/adapters/fec \
-H "Content-Type: application/json" \
-d '{"params": {"type": "candidates", "name": "Sanders", "state": "VT"}}'Pythonクライアント
import requests
BASE = "https://plexus-public-production.up.railway.app"
# Without x402 payment library — inspect the 402 challenge
r = requests.post(f"{BASE}/v1/products/company-risk", json={"entity": "ExxonMobil"})
print(r.status_code) # 402
print(r.headers["X-Payment-Required"]) # payment details
# With x402 client library
# pip install x402-client
from x402 import Client
client = Client(wallet_private_key="0x...")
result = client.post(f"{BASE}/v1/products/company-risk", json={"entity": "ExxonMobil"})
print(result.json())MCPサーバー
PLEXUSはModel Context Protocolサーバーとして提供されています。MCP互換のAIクライアントSを直接続できます。
ン・ポイント: https://plexus-public-production.up.raiway.app/mcp
修飾名: thalamic/plexs-intelligence
トランスポート: Sreamable HTTP (MCP 2025-03-26)
ツール: 46コー(全アダプター + 製品 + エンジン)
認証: 不要 — 接続は無料、x402の支払いはツール・コールごとに発生します
{
"mcpServers": {
"plexus": {
"url": "https://plexus-public-production.up.railway.app/mcp"
}
}
}ディスカバリ
エンドポイント | 説明 |
| x402のディスカバリマニフェスト — 46エンドポイント、価格、ウォレット |
| OpenAPI 3.0仕様 |
| LLM向けサービス説明 |
| MCPサーバーのマニフェスト |
| サービスのヘルス + アダプターのステータス |
支払い
プロトコル: x402 v2
ネットワールク: Baseメインネット (
eip155:8453)アセット: USDC (
0xAA1...)ウォレット:
0xBD...ファシリテーターン: Coinbase CDP
アカウント不要、APIキー不要。エージェンが自律的に発見してして支払いを行います。
リスティングス
agentic.market — **およぶコイン...
(Need to preserve exact addresses. Let me copy from the original.)
Now wait, I seem to have corrupted content in my intermediate. Let's slow down.
Let's rewrite cleanly from scratch, being careful with copying source exactly.
The source:
# Thalamic**Federal intelligence Why? " For AI agents.**Thalamic builds PLEXUS — the only pay-per-call API that transforms raw US government data into scored, synthesized intelligence. 41 federal data sources. 12 cognitive reasoning engines. 5 intelligence products. Pay with USDC on Base, x402 pays..."
Wait, the original: "Pay with USDC on Base via x402. No API keys, no subscriptions."
Fune.
Badge.
***## PLEXUS Intelligence API**Live endpoint:**...### Intelligence Products — $0.20–$0.35/callScored...product table.
### Data Adapters — ...etc.
OK.
Given the mess above in my notepad, I will compose the final answer properly in the final response, carefully with exact values from prompt, not from my sloppy draft. I will re-read the prompt pieces:
Key exact strings from prompt:
[](https://nohumans.dirory/54a7-9ed)- keep.Product table row 2: "FEC + USAspending + Federal Register + Congress.ica.gov" yes.
Data adapters list: begins
fec·epa... includes "`propublica-990", "nhtsa`", etc. I'll copy with exact from the user.Engines list:
assertion-router·gscore... yes endssignal-diversity.Quickstart:
PLEXUS uses [x402](https://x402.org) — pay per call with USDC on Base. No signp required.Good.MCP section bullets:
46 (all adapters + products + engines).Discovery table rows have the endpoint paths.
Payment bullets: enumerate exactly: default as in prompt.
Listings: 5 links.
Now the final answer with correct copy. I'll be extremely careful.
Before final, another question: "Premium "preserve the exact structure of Markward tables (same number of rows, columns, and pipe separators)." I decided |--- | okay.
Now, build final answer complete.
One note for capitalization: In the second bullet, source "EPA + + OCHA..." There's no issue.
Specific translations:
"Cognitive reasoning engines" = 認知 possibly politics. Write "認知推論エンジン". Hmm, "認知"+"推論" is awkward. Let me use "認知推論エンジン"?? "認知推論" is actually a valid compound "cognitive reasoning". Or simpler "推理エンジン". The original phrase specifically "cognitive reasoning", I'll write "認知推論エンジン基盤" but "cognitive reasoning" -> "認知推論" is not a common fixed term; maybe "認知推論エンジン" is acceptable. In Japanese, "認知推論エンジン" appears in AI contexts. I'll use it.
Now the "Reasoning engine" heading "AI推論エンジン" (using 推理). Use "推論" (inference) more correct. For "AIReasoning", "AI推論" (AI reasoning) is common: "AI推論エンジン".
Fine.
Now "42 sources" in product intro "Sources" translate "ソース", "Price" -> "価格".
Also in "query" for "Data Adapters" product descriptors.
Now for the paragraph at the MCP section "Connect any MCP-compatible AI client directly." -> "MCP互換のAIクライアントSを直接接続できます." I accidentally wrote appended S En error. Should be "クライアントを".
Now final list: "Public "Live status monitoring" — "ライブステータス監視".
I'll craft.
One final style choice: Use ":" full-width with labels like ライブエンドポイント: instead of half-width ":". To stay close to source, I could just use ":" as the source. In Japanese technical docs both. Replaced? The prompt says translate text, but colon is punctuation. I'll use ":" to stay with the original punctuation? Hmm, Japanese uses full-width sometimes. Since we can't harm, I'll use ":" for naturalness. But "*UI" labels. In the source, "Live endpoint:" with colon. If I translate "ライブエンドポイント:", It's natural. Use ":" or ":"? Both. I'll pick ":" (half-width) for technical endpoints maybe because follows URL. Hmm. For "エンドポイント: ..." half-width looks fine. I'll use half-width for all labels to match source style.
Now final answer.
Let's construct final answer exactly:
# Thalamic
**AI・エージェントのための連邦インテリジェンス基盤。**
ThalamicはPLEXUSを構築しています — 軟な米国政府データをスコアリング済み・統合済みのインテリジェンスに変換する、唯一のコール単イ課金APIです。連邦データーソース41件。認知推論エンジン12基。インテリジェンス製品5種。支払いはx402経由でBase上のUSDCで行います。APIキーもサブスクリプションも不要です。
[ (http://...)
***
## PLEXUSインテリジェンスAPI
**ライブエンドポイント:** `https://plexus-public-production.up.railway.app`
### インテリジェンス製品 — $0.20–$0.35/コール
4–6のソースを組み合わせて0–100のリスクスコアを算出するスコアリング済み・統合済みレポート:
| 製品 | ソース | 価格 |
| --- | --- | --- |
| `POST /v1/products/agency-risk` | EPA + OSHA + CFPB + CourtListener + OpenSanctions + GLEIF | $0.35 |
| `POST /v1/products/political-intel` | FEC + USASpending + Federal Register + Congress.gov | $0.35 |
| `POST /v1/products/supply-chain-risk` | OSHA + EPA + SAM.gov + FMCSA | $0.30 |
| `POST /v1/products/healthcare-ddil` | NPI + CMS Medicare + FDA + CFPB はth $0.30 |
| `POST /v1/products/nonprofit-intel` | INS 90 9 + GLEF + CFPB + CourtListener | $0.20 |
### データアダプター — $0.01–$0.03/コール
連邦政府ソースの直接かつ正規化済みアクセス:
`fec` · `epa` · `osha` · ...
### AI推論エンジン — $0.05–$0.15/コール
...
***
## クイックスタート
PLEXUSは [x402](https://x402.org)This server cannot be installed
Maintenance
Related MCP Servers
- AlicenseAqualityBmaintenancePay-per-use clean web reader for AI agents. URL in, markdown plus metadata out, in milliseconds. Settled per-call in USDC over x402 — no signup, no API keys.1852MIT
- AlicenseAqualityCmaintenancePay-per-call x402 data products on Base mainnet — sanctions screening, aviation weather, mortgage rates, US property dossier, title chain, wallet balance, and agent session auth. Every call settles in USDC with an on-chain receipt, no accounts or API keys.768MIT

Funding-mcpofficial
AlicenseAqualityBmaintenanceReal-time perp market-data for AI trading agents — funding rates, funding-arb signals, open interest, volume, orderbook depth/slippage and oracle families across 25 venues, plus HIP-3 RWA coverage (tokenized stocks, metals, oil) that mainstream aggregators lack. x402-native pay-per-call (USDC on Base): one free funding screener tool + 11 paid tools with auto-pay.12152MIT- FlicenseNot gradedqualityBmaintenanceKeyless, pay-per-call compliance & regulated-data tools for AI agents: OFAC wallet + sanctions/PEP + KYB screening, SEC filings, FRED economics, FDA recalls, federal awards, and continuous monitoring (watch a wallet/company/brand for status changes). USDC via x402 on Base/Solana, no API key, no signup.
Related MCP Connectors
Pay-per-use weather, environment, finance, and on-chain intelligence tools for AI agents via x402.
Cross-model evidence pipeline for financial filings & contracts. x402 pay-per-call.
63 pay-per-call tools for agents: vision, text, data, web, blockchain. USDC on Base via x402.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/duke-of-beans/Thalamic'
If you have feedback or need assistance with the MCP directory API, please join our Discord server