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.

AgentObserver - Check x402 Dependencies Before Paying

REMOTE · ICQZBUUIX6E4BED2STNNBOQCTI.SRV.US · SCANNED SEP 28

Check Exa, BlockRun, OneSource, Apify and other x402 dependencies before invoking or paying.

23 Trust /100

Recent critical change

Authorization (23 Sept 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 Security57
Transport & Reachability0
Schema Quality & AI Usability0
  • Schema not yet verified: we couldn't read the endpoint's schema, or could read only part of its tool list.Unverified
Stability & Change Management0
  • Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage0
  • Tool coverage not yet verified: we couldn't read the endpoint's tools, or could read only part of the list.Unverified
Tool Safety0
  • Tool safety not yet verified: we couldn't read the endpoint's tools, or could read only part of the list.Unverified
Capabilities0
  • Capabilities not yet verified: we couldn't read the endpoint's capabilities.Unverified

Unverified: 5 categories

Categories scored 0 because we could not verify them: authentication we do not have, an unreachable endpoint, or not enough scan history. We only credit what we can confirm.

Install

How do I install the AgentObserver - Check x402 Dependencies Before Paying MCP server?

AgentObserver - Check x402 Dependencies Before Paying is a hosted endpoint at https://icqzbuuix6e4bed2stnnboqcti.srv.us/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 · icqzbuuix6e4bed2stnnboqcti.srv.us

# add to Claude Code
claude mcp add --transport http kaattaallaa-sketch-agentobserver 'https://icqzbuuix6e4bed2stnnboqcti.srv.us/mcp'
// .cursor/mcp.json
{
  "mcpServers": {
    "kaattaallaa-sketch-agentobserver": {
      "url": "https://icqzbuuix6e4bed2stnnboqcti.srv.us/mcp"
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "kaattaallaa-sketch-agentobserver": {
      "type": "http",
      "url": "https://icqzbuuix6e4bed2stnnboqcti.srv.us/mcp"
    }
  }
}
# ~/.codex/config.toml
[mcp_servers.kaattaallaa-sketch-agentobserver]
url = "https://icqzbuuix6e4bed2stnnboqcti.srv.us/mcp"
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "kaattaallaa-sketch-agentobserver": {
      "type": "remote",
      "url": "https://icqzbuuix6e4bed2stnnboqcti.srv.us/mcp",
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add kaattaallaa-sketch-agentobserver --url 'https://icqzbuuix6e4bed2stnnboqcti.srv.us/mcp' --transport streamable-http
# ~/.hermes/config.yaml
mcp_servers:
  kaattaallaa-sketch-agentobserver:
    url: "https://icqzbuuix6e4bed2stnnboqcti.srv.us/mcp"
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "kaattaallaa-sketch-agentobserver": {
      "Transport": "http",
      "Url": "https://icqzbuuix6e4bed2stnnboqcti.srv.us/mcp"
    }
  }
}
# add to Vellum
assistant mcp add kaattaallaa-sketch-agentobserver -t streamable-http -u 'https://icqzbuuix6e4bed2stnnboqcti.srv.us/mcp'
// mcp.json
{
  "mcpServers": {
    "kaattaallaa-sketch-agentobserver": {
      "type": "http",
      "url": "https://icqzbuuix6e4bed2stnnboqcti.srv.us/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.

  • 28 Sept 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 26 Sept 26 0
    • Endpoint reachability: reachable → not serving MCP ▼ security
  • 25 Sept 26 −44
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 24 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

  • 23 Sept 26 +1
    • Authorization: unverified → fail ▼ critical
    • Endpoint reachability: reachable → not serving MCP ▼ security
    • Tool safety: pass → unverified ▼ security
    • Transport: pass → fail ▼ security
    • Authorization: Authorisation not fully verified: no authorisation is required to connect, but we couldn't read the whole tool list to see what that exposes. security
    • New tool “agentobserver_dependency_preflight”, which the server declares destructive security
    • Tool “agentobserver_targets” rewrote its description, which is the text the model reads security
    • Tool “agentobserver_preflight” is now declared destructive security
    • Schema quality: 38 → 59 ▼ functional
    • Schema quality: 100 → unverified ▼ functional
    • Capabilities: pass → unverified ▼ functional
    • Tool coverage: 100 → unverified ▼ functional
    • Endpoint reachability: not serving MCP → reachable ▲ functional
    • Tool coverage: 75% → 80% ▲ functional
    • Stability: unverified → 0.03 ▲ functional
    • New resource “agentobserver_dependencies_resource” functional
    • New resource “agentobserver_dependency_watch_resource” functional
    • Server version: 0.7.2 → 0.8.1 functional
    • New tool “agentobserver_check_before_spend” functional
    • New tool “agentobserver_dependencies” functional
    • New tool “agentobserver_dependency_watch” functional
    • New tool “agentobserver_resolve” functional
    • New tool “agentobserver_spend_status” functional
  • 22 Sept 26 65

    First indexed and scored.

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 28 Sept 2026 · Probed https://icqzbuuix6e4bed2stnnboqcti.srv.us/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=srv.us CN=YR1,O=Let's Encrypt,C=US 7 Aug 2026 5 Nov 2026 RSA 2048 SHA256-RSA 593a66f6fe0c4fa08c9d03e57fd8824c66f
SANs: *.gh.srv.us, *.gl.srv.us, *.srv.us, srv.us
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 icqzbuuix6e4bed2stnnboqcti.srv.us. — Not signed

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
us. present 59017 8 Verified
srv.us. absent Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication Inconclusive

We could not reach the endpoint well enough to judge its authorisation posture.

Result Inconclusive
HTTP status 503

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

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://icqzbuuix6e4bed2stnnboqcti.srv.us/mcp HTTP error 503
http (plaintext) http://icqzbuuix6e4bed2stnnboqcti.srv.us/mcp HTTPS enforced 301 https://icqzbuuix6e4bed2stnnboqcti.srv.us/mcp
MCP tools · 10 exposed · ~737 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
agentobserver_check_before_spend ~145

Use immediately before invoking or paying a dependency. Checks Exa Search, BlockRun, OneSource, Apify, Laevitas or any AgentObserver catalog resource for current observable terms, endpoint-specific demand and drift without sending credentials or payment signatures.

NameTypeReqDescription
liveboolean–If true, run the safe unsigned live observation when the catalog explicitly allows it.
provider_idstringyesDependency provider id, for example exa, blockrun, onesource, apify or laevitas.
resource_idstringyesDependency resource id, for example search, chat-completions, deepstate-markets, x402-prepaid-token or instruments.

Structured output declared, but exposes no named fields.

No examples provided.

agentobserver_dependencies ~63

Discover x402 dependencies agents already use, including Exa Search, BlockRun, OneSource, Apify, Laevitas and others. Returns endpoint-specific demand evidence when available.

NameTypeReqDescription
capability––Optional exact capability filter such as web-search, market-data or automation.

Structured output declared, but exposes no named fields.

No examples provided.

agentobserver_dependency_preflight ~71

Paid x402 dependency Preflight for eligible resources such as OneSource, BlockRun Exa Find Similar, Apify and Laevitas. Returns fresh hash-bound pre-spend evidence.

NameTypeReqDescription
provider_idstringyesCatalog provider identifier.
resource_idstringyesEligible catalog resource identifier.

No output schema declared.

No examples provided.

agentobserver_dependency_watch ~52

Read persisted continuous-watch state for an eligible dependency. This tool never triggers an outbound probe.

NameTypeReqDescription
provider_id––Optional provider id.
resource_id––Optional resource id; supply together with provider_id.

Structured output declared, but exposes no named fields.

No examples provided.

agentobserver_interfaces ~28

Discover all public AgentObserver interfaces: HTTP/x402, MCP/x402 and A2A.

Input schema present but exposes no named parameters.

Structured output declared, but exposes no named fields.

No examples provided.

agentobserver_preflight ~72

Paid x402 Preflight: return fresh machine-readable evidence about a registered AI-agent counterparty.

NameTypeReqDescription
max_age_secondsinteger–Maximum acceptable evidence age in seconds; use a smaller value for stricter freshness.
targetstringyesRegistered AI-agent counterparty URL whose fresh evidence should be purchased.

No output schema declared.

No examples provided.

agentobserver_resolve ~118

Resolve providers for a capability using factual filters and dated demand evidence. Sorting is not a trust score.

NameTypeReqDescription
capabilitystringyesCapability the calling agent needs.
include_degradedboolean–Include providers explicitly observed as unreachable/dead. Default false.
limitinteger–Maximum providers returned.
max_price_usd––Optional maximum listed resource price in USD.
network––Optional payment network such as eip155:8453.
sort_bystring–Objective ordering basis, not a recommendation.

Structured output declared, but exposes no named fields.

No examples provided.

agentobserver_spend_status ~89

Check one dependency before spending. Use for Exa Search, BlockRun Chat Completions, OneSource, Apify or any catalog resource; never sends provider credentials or payment signatures.

NameTypeReqDescription
liveboolean–Run a safe unsigned live probe when the registry explicitly allows it.
provider_idstringyesCatalog provider identifier.
resource_idstringyesProvider resource identifier.

Structured output declared, but exposes no named fields.

No examples provided.

agentobserver_status ~59

Free preflight status: show freshness, reachability, material changes and factual reasons that deserve review before relying on or paying a registered counterparty.

NameTypeReqDescription
targetstringyesRegistered AI-agent counterparty URL to inspect before relying on or paying it.

Structured output declared, but exposes no named fields.

No examples provided.

agentobserver_targets ~40

Legacy registered-target catalog: list free status actions and any target-specific paid eligibility. Use agentobserver_dependencies/agentobserver_resolve for the primary dependency workflow.

Input schema present but exposes no named parameters.

Structured output declared, but exposes no named fields.

No examples provided.

Common questions

What is the AgentObserver - Check x402 Dependencies Before Paying MCP server?

AgentObserver - Check x402 Dependencies Before Paying is an MCP server listed in the public MCP registry as io.github.kaattaallaa-sketch/agentobserver. Check Exa, BlockRun, OneSource, Apify and other x402 dependencies before invoking or paying. This page covers its hosted endpoint (https://icqzbuuix6e4bed2stnnboqcti.srv.us/mcp).

Is the AgentObserver - Check x402 Dependencies Before Paying MCP server safe to use?

AgentObserver - Check x402 Dependencies Before Paying scores 23 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 AgentObserver - Check x402 Dependencies Before Paying MCP server expose?

AgentObserver - Check x402 Dependencies Before Paying exposes 10 tools: agentobserver_interfaces, agentobserver_targets, agentobserver_dependencies, agentobserver_resolve, agentobserver_spend_status, and 5 more. Their descriptions and schemas cost roughly 737 tokens of context every time the server is loaded.

Does the AgentObserver - Check x402 Dependencies Before Paying MCP server require authentication?

Its publisher declares no required credentials for AgentObserver - Check x402 Dependencies Before Paying. We have not been able to confirm that against the live endpoint, and a server can require authorisation without declaring it here.

Is the AgentObserver - Check x402 Dependencies Before Paying MCP server still maintained?

AgentObserver - Check x402 Dependencies Before Paying is still listed as active in the MCP registry. We last reached this channel on 28 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.