Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

AgentServices

REMOTE · AGENTSERVICES.TO · SCANNED SEP 20

52 paid x402 API endpoints for AI agents — crypto, data, DeFi, market intelligence.

Available components

0 this week 78 Trust /100

Recent critical change

TLS certificate (28 Jul 2026). See the changelog before you install this server.

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security63
Transport & Reachability100
Schema Quality & AI Usability80
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 3277 tokens (~49/item across 66 items; 64 tools + 2 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
  • No destabilizing schema changes in the last 30 days.Pass
Tool Coverage79
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 38% of tool parameters carry a description.Partial
Tool Safety75
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 0 of 3 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "trade_hyperliquid_eval_order" implies "eval" and declares readOnlyHint instead, contradicting what its own name says it does. See how to fix → Fail
  • An AI judge read all 65 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a current MCP spec version (2026-07-28).Pass
Install

How do I install the AgentServices MCP server?

AgentServices is a hosted endpoint at https://agentservices.to/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · agentservices.to

# add to Claude Code
claude mcp add --transport http to-agentservices-agentservices 'https://agentservices.to/mcp'
// .cursor/mcp.json
{
  "mcpServers": {
    "to-agentservices-agentservices": {
      "url": "https://agentservices.to/mcp"
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "to-agentservices-agentservices": {
      "type": "http",
      "url": "https://agentservices.to/mcp"
    }
  }
}
# ~/.codex/config.toml
[mcp_servers.to-agentservices-agentservices]
url = "https://agentservices.to/mcp"
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "to-agentservices-agentservices": {
      "type": "remote",
      "url": "https://agentservices.to/mcp",
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add to-agentservices-agentservices --url 'https://agentservices.to/mcp' --transport streamable-http
# ~/.hermes/config.yaml
mcp_servers:
  to-agentservices-agentservices:
    url: "https://agentservices.to/mcp"
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "to-agentservices-agentservices": {
      "Transport": "http",
      "Url": "https://agentservices.to/mcp"
    }
  }
}
# add to Vellum
assistant mcp add to-agentservices-agentservices -t streamable-http -u 'https://agentservices.to/mcp'
// mcp.json
{
  "mcpServers": {
    "to-agentservices-agentservices": {
      "type": "http",
      "url": "https://agentservices.to/mcp"
    }
  }
}

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 6 Sept 26 −1
    • Stability: 0.97 → pass security
    • Tool coverage: 48% → 38% functional
    • Schema quality: 2857 → 3277 functional
    • New tool “trade_pacifica_cancel” functional
    • New tool “trade_pacifica_eval_order” functional
    • New tool “trade_pacifica_get_policy” functional
    • New tool “trade_pacifica_order” functional
    • New tool “trade_pacifica_order_status” functional
    • New tool “trade_pacifica_paper_order” functional
    • New tool “trade_pacifica_set_policy” functional
  • 5 Sept 26 0
    • Stability: pass → 0.97 functional
  • 4 Sept 26 −3
    • Schema quality: 2050 → 2857 functional
    • Tool coverage: 85% → 48% functional
    • Destructive annotations: pass → 0 functional
    • New tool “hl_cancel_order” functional
    • New tool “hl_eval_order” functional
    • New tool “hl_get_policy” functional
    • New tool “hl_order_status” functional
    • New tool “hl_paper_order” functional
    • New tool “hl_place_order” functional
    • New tool “hl_set_policy” functional
    • New tool “trade_hyperliquid_cancel” functional
    • New tool “trade_hyperliquid_eval_order” functional
    • New tool “trade_hyperliquid_get_policy” functional
    • New tool “trade_hyperliquid_order” functional
    • New tool “trade_hyperliquid_order_status” functional
    • New tool “trade_hyperliquid_paper_order” functional
    • New tool “trade_hyperliquid_set_policy” functional
  • 2 Sept 26 0
    • Stability: 0.97 → pass security
  • 1 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

  • 31 Aug 26 −1
    • DNSSEC: unverified → fail security
    • Stability: pass → 0.93 functional
  • 30 Aug 26 0
    • DNSSEC: fail → unverified security
  • 28 Aug 26 0
    • Stability: 0.97 → pass security
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 20 Sept 2026 · Probed https://agentservices.to/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=agentservices.to CN=YR1,O=Let's Encrypt,C=US 16 Aug 2026 14 Nov 2026 RSA 2048 SHA256-RSA 692082d1bc6d998e844790eb4aa5ddfde9a
SANs: agentservices.to, api.agentservices.to
CN=YR1,O=Let's Encrypt,C=US (CA) CN=Root YR,O=ISRG,C=US 3 Sept 2025 2 Sept 2028 RSA 2048 SHA256-RSA a20253f15f2691c05dc1ce13b9bcca4e
CN=Root YR,O=ISRG,C=US (CA) CN=ISRG Root X1,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 RSA 4096 SHA256-RSA f24b6d17f9d9ad7cb1c9fea78782699f

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of agentservices.to. Not signed

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
to. absent Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200
Header Value
strict-transport-security max-age=63072000; includeSubDomains; preload
content-security-policy default-src 'self'; script-src 'self' 'unsafe-inline'; style-src 'self' 'unsafe-inline'; img-src 'self' data: https:; connect-src 'self' https:;
x-content-type-options nosniff
x-frame-options DENY
referrer-policy strict-origin-when-cross-origin

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://agentservices.to/mcp Verified 200
http (plaintext) http://agentservices.to/mcp HTTPS enforced 308 https://agentservices.to/mcp
MCP tools · 64 exposed · ~3,247 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
trade_hyperliquid_order_status ~43

Read Hyperliquid order status via info API (FREE)

NameTypeReqDescription
oidstringyesOrder id
userstringyesWallet address

No output schema declared.

No examples provided.

trade_hyperliquid_paper_order ~75

Paper/sim order — same shape as live, no HL call (FREE training gym)

NameTypeReqDescription
coinstring
market_typestring
pricenumber
principalstring
sidestring
sizenumber

No output schema declared.

No examples provided.

trade_hyperliquid_set_policy ~65

Set execution leash policy for a principal (FREE)

NameTypeReqDescription
allowed_coinsarray
enabledboolean
kill_switchboolean
max_notional_usdnumber
principalstringyes

No output schema declared.

No examples provided.

trade_pacifica_cancel ~50

Forward agent-signed Pacifica cancel after policy check (FREE — not x402)

NameTypeReqDescription
market_typestring
principalstringyes
signedobjectyes

No output schema declared.

No examples provided.

trade_pacifica_eval_order ~70

Pass/fail eval: candidate order vs principal policy (FREE training gym)

NameTypeReqDescription
coinstringyes
market_typestring
pricenumberyes
principalstringyes
sidestringyes
sizenumberyes

No output schema declared.

No examples provided.

trade_pacifica_get_policy ~40

Get execution leash policy for a principal (max notional, allowlist, kill switch) (FREE)

NameTypeReqDescription
principalstringyes

No output schema declared.

No examples provided.

trade_pacifica_order ~76

Forward agent-signed Pacifica order after policy check (FREE — not x402). market_type: spot|perp|future. Agent signs locally; no venue API keys.

NameTypeReqDescription
checkobject
market_typestring
principalstringyes
signedobjectyes

No output schema declared.

No examples provided.

trade_pacifica_order_status ~37

Read Pacifica order status via orders API (FREE)

NameTypeReqDescription
oidstringyes
userstringyes

No output schema declared.

No examples provided.

trade_pacifica_paper_order ~83

Paper/sim order — same shape as live, no Pacifica call (FREE training gym)

NameTypeReqDescription
coinstring
market_typestring
order_typestring
pricenumber
principalstring
sidestring
sizenumber

No output schema declared.

No examples provided.

trade_pacifica_set_policy ~64

Set execution leash policy for a principal (FREE)

NameTypeReqDescription
allowed_coinsarray
enabledboolean
kill_switchboolean
max_notional_usdnumber
principalstringyes

No output schema declared.

No examples provided.

url_metadata ~38

Extract metadata from a URL — title, description, images ($0.01 x402)

NameTypeReqDescription
urlstringyesURL to extract metadata from

No output schema declared.

No examples provided.

web_extract ~40

Extract clean text from any URL — strips ads, nav, scripts ($0.002 x402)

NameTypeReqDescription
urlstringyesURL to extract content from

No output schema declared.

No examples provided.

web_search ~47

Web search with structured results — same as GET /v1/search ($0.01 x402)

NameTypeReqDescription
num_resultsintegerMax results
qstringyesSearch query

No output schema declared.

No examples provided.

whale_tracking ~28

Large whale transactions on BTC (>=10 BTC) and ETH chains ($0.02 x402)

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

Common questions

What is the AgentServices MCP server?

AgentServices is an MCP server listed in the public MCP registry as to.agentservices/agentservices. 52 paid x402 API endpoints for AI agents, crypto, data, DeFi, market intelligence. This page covers its hosted endpoint (https://agentservices.to/mcp).

Is the AgentServices MCP server safe to use?

AgentServices scores 78 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the AgentServices MCP server expose?

AgentServices exposes 64 tools: crypto_prices, technical_indicators, defi_yields, fear_greed, ip_geolocation, and 59 more. Their descriptions and schemas cost roughly 3,247 tokens of context every time the server is loaded.

Does the AgentServices MCP server require authentication?

No. We connected to AgentServices without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the AgentServices MCP server still maintained?

AgentServices is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.