
AgentServices
to.agentservicesPublished by agentservices.toOfficial publisherv6.0.0Updated Oct 24, 2026
52 paid x402 API endpoints for AI agents — crypto, data, DeFi, market intelligence.
Overview
Remote MCP server exposing crypto, DeFi, market-intelligence, AI inference and Hyperliquid trading endpoints, mostly paid per call via x402 USDC micropayments.
- What you can do
- Fetch free crypto market data: prices, trending tokens, global metrics, fear-and-greed, gas, news, social trends, swap quotes and predictions. Retrieve paid data and synthesis: technical indicators, DeFi yields, on-chain analytics, token risk, signals, research, portfolio and market-pulse reports. Run AI inference, image generation and text-to-speech through paid endpoints. Submit and cancel policy-gated Hyperliquid orders, check order status, set execution policy, and run paper or evaluation orders. Resolve disputes using policy templates.
- When to use it
- Useful when an assistant needs crypto or DeFi market data, on-chain analytics, bundled research reports, or a paid inference gateway without managing API keys. Also relevant for agents that want policy-checked Hyperliquid order forwarding or paper-trading evaluation.
- Requirements
- Remote Streamable HTTP endpoint; no local runtime or API keys. Free endpoints need nothing; paid endpoints require an x402-capable client with a USDC wallet on Base. Human access through ChatGPT or Claude connectors uses Google OAuth and Stripe prepaid credits. Hyperliquid trading needs a locally signed agent wallet approved via approveAgent.
Installation
In SourceWeft
- Open AgentServices in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Use with an agent
Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.
Read https://sourceweft.com/mcp/to.agentservices%2Fagentservices/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.Other MCP clients
Add this to your client's mcpServers config.
{
"mcpServers": {
"agentservices": {
"type": "http",
"url": "https://agentservices.to/mcp"
}
}
}README
AgentServices
The paid API layer for AI agents — data, intelligence, inference, and media via x402 micropayments
Canonical project: https://github.com/vbkotecha/agentservices-api Official site: https://agentservices.to License: Apache-2.0
AgentServices is an independent project. It is not affiliated with, endorsed by, or a replacement for any other x402 market-data provider.
[Version] [Network] [Payment] [MCP] [Status]
Live at: agentservices.to | MCP Server: https://agentservices.to/mcp (Streamable HTTP) | Discovery: /.well-known/x402
What is this?
AgentServices is the monetized API layer for AI agents. No API keys, no subscriptions — agents pay per-request with USDC on Base using the x402 payment protocol.
60+ endpoints across crypto data, market intelligence, DeFi analytics, on-chain analytics, 400+ LLM models, image generation, text-to-speech, portfolio intelligence, and dispute resolution. 12 are free. 48+ are paid via x402 (from $0.002 to $0.25 per call).
What's new in v6.0
- 400+ LLM models via OpenAI-compatible
/v1/chat/completions— GPT, Claude, Gemini, DeepSeek, Grok, Llama, and more - Smart router — use
model: "auto"and the gateway classifies your task and picks the cheapest model that handles it - Image generation —
/v1/images/generationsvia gpt-image-2 ($0.05) - Text-to-speech —
/v1/audio/speechwith natural voices ($0.05) - 3 new MCP tools —
chat,generate_image,text_to_speech
Buyer path: discover → try → pay → retain
Use the buyer quickstart for the complete path. The exact next action is to run the no-credential discovery check:
Then follow the same buyer journey:
- Discover: confirm the hosted MCP server and free tool catalog with the MCP discovery proof.
- Try free: retrieve a real price result with the free SDK proof.
- Inspect the paid challenge: decode the live 402 terms with the paid SDK proof. It never signs or settles payment.
- Buy an outcome: pay the returned x402 terms, retry the same request, and retain the returned paid result. See the token-risk, market-pulse, and research-brief contracts for result limits and provenance.
- Retain evidence: run the existing receipt builder with the original challenge, paid response, and your wallet authorization or transaction reference.
The four proofs have different limits: discovery and free SDK verify no-spend access; the paid SDK proof verifies challenge shape only; the receipt builder hashes buyer-held evidence and does not verify settlement. None of them claims adoption, settlement, or revenue.
For activation measurement definitions, see Activation Metrics. To probe the live funnel, run python3 examples/check_activation_funnel.py.
Buyer path: discover → try → pay → retain
Use the buyer quickstart for the complete path. The exact next action is to run the no-credential discovery check:
Then follow the same buyer journey:
- Discover: confirm the hosted MCP server and free tool catalog with the MCP discovery proof.
- Try free: retrieve a real price result with the free SDK proof.
- Inspect the paid challenge: decode the live 402 terms with the paid SDK proof. It never signs or settles payment.
- Buy an outcome: pay the returned x402 terms, retry the same request, and retain the returned paid result. See the token-risk, market-pulse, and research-brief contracts for result limits and provenance.
- Retain evidence: run the existing receipt builder with the original challenge, paid response, and your wallet authorization or transaction reference.
The four proofs have different limits: discovery and free SDK verify no-spend access; the paid SDK proof verifies challenge shape only; the receipt builder hashes buyer-held evidence and does not verify settlement. None of them claims adoption, settlement, or revenue.
Endpoints
Free (no payment required)
Trade API — venue doors (FREE — not x402)
AgentServices is building venue trade doors under /v1/trade/{venue}/…. Hyperliquid ships first; more venues and a venue-neutral /v1/trade/execute router follow.
Each door is a policy leash + forward — not a smarter router. We do not claim better fills than the venue direct. Execution is free at the call (no x402 on the order path). Builder fees are omitted so routing through us is not more expensive than going direct.
We never collect venue API keys. Agents sign orders locally with an HL-approved agent wallet (approveAgent on the main wallet is the one human bootstrap step). AgentServices policy-checks (max notional, coin allowlist, kill switch) and forwards the signed payload.
Request bodies accept market_type: spot, perp, or future. Hyperliquid implements perp and spot today; unsupported types return a machine-readable market_type_not_supported error.
Legacy hl_* MCP tool names remain as aliases. See GET /v1/trade/hyperliquid/bootstrap for the approveAgent signing model.
Roadmap: /v1/trade/{venue} for additional venues; /v1/trade/execute for venue-neutral routing later.
Paid — Data APIs (x402)
Paid — Synthesis APIs (x402)
Paid — Bundled Intelligence (x402)
Paid — AI Inference (x402)
Paid — Dispute Resolution (x402)
Use Cases — What Agents Can Build
Portfolio Monitor
DeFi Yield Optimizer
Market Intelligence Agent
Technical Analysis Bot
Developer Research Agent
AI Chat / Inference
On-Chain Analytics
Quick Start
Using curl
Using as MCP Server (Claude Desktop, Cursor, etc.)
13+ MCP tools available: crypto_prices, trending_tokens, global_market, gas_prices, market_predictions, crypto_news, social_trending, technical_indicators, defi_yields, search_web, token_risk, crypto_signals, onchain_analytics, deep_research, portfolio_intelligence, defi_strategy, market_pulse, onchain_overview
Using with Python
Using with JavaScript/TypeScript
Dispute Resolution Engine
AgentServices includes an AI-powered dispute resolution system with 7 policy templates:
Human billing door (ChatGPT / Claude)
Wallet agents continue to pay via x402 on REST — unchanged. Humans connecting through ChatGPT Developer Mode or Claude custom connectors can use Google OAuth + Stripe prepaid credits on MCP.
MCP URL for ChatGPT: https://agentservices.to/mcp
Environment variables
Copy .env.example. Required to enable the human door:
Prepaid credit balances are stored in Stripe Customer Balance (one Stripe Customer per Google sub). No Redis, Postgres, or other database is required.
Without Google/Stripe vars the API boots in x402-only mode.
Google Cloud Console redirect URIs
Add both hosts:
https://agentservices.to/oauth/google/callbackhttps://api.agentservices.to/oauth/google/callback
Stripe webhook
Point Stripe to:
https://agentservices.to/billing/webhookhttps://api.agentservices.to/billing/webhook
Event: checkout.session.completed
Discovery & Listings
- x402 Discovery — Live
- MCP Registry — Listed as
to.agentservices/agentservices - CDP Bazaar — Extension enabled
- awesome-x402 — PR submitted
Tech Stack
- FastAPI (Python 3.11+)
- x402 v2 payment middleware (Coinbase CDP facilitator)
- USDC on Base Mainnet (EIP-3009 gasless transfers)
- Deployed on Vercel (
agentservices.to+api.agentservices.to, auto-deploy frommain)
Coinbase AgentKit Integration
AgentServices includes a built-in Coinbase AgentKit action provider (agentkit/ directory). This lets any AgentKit agent use AgentServices APIs with typed, documented actions:
18 actions covering free (prices, fear-greed, trending, gas) and paid endpoints (indicators, DeFi yields, portfolio intelligence, research, onchain analytics, AI inference, and more). See agentkit/README.md for full documentation.
License
MIT — Build on it, fork it, integrate it.
Links
- API: agentservices.to
- MCP: agentservices.to/mcp
- Discovery: agentservices.to/.well-known/x402
- GitHub: github.com/vbkotecha/agentservices-api
- x402 Protocol: x402.org
- Base: base.org
Source: README.md at commit a9a5fd8
Tools
0Version history
1- v6.0.0LatestSep 16, 2026
Score
85% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 daysRequired25 pts
- Auth declaredRequired10 pts
- Tools listedRequired15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts