Skip to content

RealtimeAPI.ai MCP server

ai.realtimeapi/mcprealtimeapi.aistreamable-httpv1.0.0Scanned

Live data for AI agents: crypto, Hyperliquid, stocks, news, macro, predictions. Free key or x402.

6 tools: 2 change things and 4 only read.

Tools: 0 delete, 0 irreversible, 2 write, 4 read.
  • Reads private data · 0
  • Reads text others write · 4
  • Can send data out · 3
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

2 tools here change things. Govern them.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the RealtimeAPI.ai MCP server can do

The RealtimeAPI.ai MCP server is published by realtimeapi.ai, a domain the MCP Registry verified. It has 6 tools. It can create or change data (2 tools: call_feed and create_free_key), but cannot delete data. 4 tools only read.

4 tools bring in text other people can write (get_sample, list_feeds, get_quote and 1 more); 3 tools can send data out of your system (get_sample, get_quote and call_feed).

None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 9, 2026, version 1.0.0.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

6 tools

Changes things 2Claude Code: ask
  • call_feedCall a feed endpoint through the gateway with your API key (or an x402 payment).Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "call_feed" says "call": a word for a change.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
    Description, as the server wrote it
    Call a feed endpoint through the gateway with your API key (or an x402 payment). Without either it returns the 402 payment options.

    Annotations the server declares

    • readOnlyHint: false
    • openWorldHint: true
  • create_free_keyCreate a free API key (1,000 calls/month, all feeds) for the user's real email.No findings

    Why it is in this group

    • The name "create_free_key" says "create": a word for a change.
    Description, as the server wrote it
    Create a free API key (1,000 calls/month, all feeds) for the user's real email. Works at once; signing in at realtimeapi.ai with that email later re-issues the secret once.

    Annotations the server declares

    • readOnlyHint: false
    • openWorldHint: false
    • idempotentHint: false
Only reads 4Show 4 read-only tools
  • discoverSearch all feeds for endpoints matching a need.No findings

    Why it is in this group

    • The description's first verb is "search": a word for reading.
    Description, as the server wrote it
    Search all feeds for endpoints matching a need. Returns up to `limit` ranked endpoints with price and params.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • get_quotePrice an endpoint without calling it: x402 `accepts` for one call plus time-pass plans.Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "get_quote" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
    • outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.

    Claude Code: ask, because it is tagged outbound.

    Description, as the server wrote it
    Price an endpoint without calling it: x402 `accepts` for one call plus time-pass plans. Nothing is charged.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • get_sampleFree trimmed sample of an endpoint's real response from the probe's cached copy (no key, no payment): see the data shape before paying.Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "get_sample" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
    • outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.

    Claude Code: ask, because it is tagged outbound.

    Description, as the server wrote it
    Free trimmed sample of an endpoint's real response from the probe's cached copy (no key, no payment): see the data shape before paying. Works for results discover marks sample: true.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • list_feedsList all live feeds with endpoint counts, per-call price range, plans and their paid MCP URL.Reads text others writeNo findings

    Why it is in this group

    • The name "list_feeds" says "list": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "list" and "url": it reads web pages, which anyone can write.
    Description, as the server wrote it
    List all live feeds with endpoint counts, per-call price range, plans and their paid MCP URL.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write4
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out3
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 16, 2026, 14:20 UTC, unchanged since Nov 9, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
2
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed
  • WarnThe whole server

    The endpoint served tools/list without credentials, and the list has 2 tools that change things (2 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://mcp.realtimeapi.ai/mcp: tools/list returned 6 tools to an anonymous client, including call_feed (write), create_free_key (write)

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

No check matched anything in these tool definitions. That is not a safety guarantee.

History

Changes to its tool definitions and to its remote endpoint, newest first.

No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.

Install

Pinned to version 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http realtimeapi https://mcp.realtimeapi.ai/mcp
claude mcp add --transport http realtimeapi https://mcp.realtimeapi.ai/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__realtimeapi__discover",
      "mcp__realtimeapi__list_feeds"
    ],
    "ask": [
      "mcp__realtimeapi__get_sample",
      "mcp__realtimeapi__get_quote",
      "mcp__realtimeapi__call_feed",
      "mcp__realtimeapi__create_free_key"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as realtimeapi. Review it before you use it.

Capability tags behind 4 rules
  • mcp__realtimeapi__get_sample untrusted-input, outbound
  • mcp__realtimeapi__list_feeds untrusted-input
  • mcp__realtimeapi__get_quote untrusted-input, outbound
  • mcp__realtimeapi__call_feed untrusted-input, outbound

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/ai.realtimeapi/mcp/verify?hash=a9def978be5402674872eec3e39528063e831dd0e55b399da0e22c2b04d8b7ed" | jq -e '.changed == false'

Pinned hash a9def978be54, from Nov 9, 2026, 00:17 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/ai.realtimeapi/mcp/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for ai.realtimeapi/mcp
[![Anlyon Radar](https://radar.anlyon.com/badge/ai.realtimeapi/mcp.svg)](https://radar.anlyon.com/servers/ai.realtimeapi/mcp)

Source: MCP Registry. Synced Nov 9, 2026, 00:17 UTC.

RealtimeAPI.ai MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the RealtimeAPI.ai MCP server safe?

No scan can promise that. What its definitions show: 6 tools, 2 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the RealtimeAPI.ai MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the RealtimeAPI.ai MCP server do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the RealtimeAPI.ai MCP server have?

6 tools: 2 write, 4 read. call_feed, create_free_key, discover, get_sample, list_feeds and get_quote.

Does the RealtimeAPI.ai MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the RealtimeAPI.ai MCP server send data to outside services?

3 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): get_sample, get_quote and call_feed.

Has the RealtimeAPI.ai MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 9, 2026.