MCP servers › io.github.horizon-pulse › horizon-pulse
MCP server · registry snapshot 2026-10-23 · last tested 2026-10-23
io.github.horizon-pulse/horizon-pulse
28 agent tools via x402: crypto data, tx checks, web fetch. MCP pays Base USDC; HTTP adds 3 rails. — the publisher's description
Summary
io.github.horizon-pulse/horizon-pulse is a remote MCP server listed in the official MCP registry at version 0.1.5. On 2026-10-23 ProtocolProbe connected to it in read-only mode and read its inventory: 32 tools, 0 resources and 0 prompts.
Record checks
4 of 5 record checks met · 4 do not apply
- met: Registry entry is active and says how to run it
- met: Source repository link opens
- met: Repository is not archived
- met: Code pushed to the repository in the 90 days before our check
- not met: Repository publishes a security policy (SECURITY.md)
- not applicable: Package names its licence with a standard (SPDX) identifier
- not applicable: The version the registry lists can be installed and is not withdrawn
- not applicable: npm package carries build provenance (attestation)
- not applicable: No known critical or high advisory in the package or its dependencies
- Not ranked by downloads: a remote server publishes no download figure
- Not ranked by stars: 0 stars (ranked from 10)
From public records, not a safety rating. Each check with its reason · Is it safe to install?
Key facts
- Runs
- remote (hosted by the publisher)
- Transport
- streamable HTTP
- Sign-in
- none needed to open a session
- Repository
- public
- Tools
- 32
- Described as changing data
- 2 of 32 toolsAI-classified
- Mainly works on
- accounts and data in outside web servicesAI-classified
- Topic
- finance-and-paymentsAI-classified
- Pricing
- usage-basedAI-classified
- Last tested
- 2026-10-23
Observed fact
This server accepted a session without any credential and lists 1 tool whose name or declaration suggests it changes data (http). That is our reading of the names; we did not call it. Source: our connection, 2026-10-23.
Worth knowing before you connect it
- 2 tools are described as changing something (http, submit_feedback): our AI model's reading of the descriptions, not something we tested, and the server opened a session without any credential. We did not call them.
Each line comes from a section below, with its source and date.
How fresh this is
- Live-tested
- yes, a real session (not a text-only review)
- Last tested
- 2026-10-23
- Mode
- read-only (no tool calls)
- Latest version
- 0.1.5, published 2026-10-17 (registry, as of the 2026-10-23 snapshot)
- First listed version
- 2026-10-12 (earliest version still in the registry; older removed versions would be earlier)
- Version history
- 6 versions listed, 2026-10-12 to 2026-10-17; 6 in the 90 days before the 2026-10-23 snapshot.(versions still listed in the registry only)
Most recent 6 versions
0.1.5· 2026-10-170.1.4· 2026-10-160.1.3· 2026-10-160.1.2· 2026-10-140.1.1· 2026-10-120.1.0· 2026-10-12
- Registry data
- snapshot 2026-10-23
- Package and repository
- checked 2026-10-23
- Engine
- mcp-runtime-engine@0.1.0 · sdk@1.32.0
Changes since the last refresh
New in the registry: not in the list of 2026-10-04, listed on 2026-10-23 with version 0.1.5 (published 2026-10-17).
Source: the official MCP Registry list on 2026-10-04 and on 2026-10-23.
What it is
What does this server offer?
Observed inventoryWhat it mainly works on, as our AI model read its tool descriptions: accounts and data in outside web services.
2 of 32 tools are described as changing something (creating, editing, deleting, sending or running).
“Crypto market data: a current USD price snapshot for BTC, ETH and SOL, or one coin via symbol= (bad symbol: 400, no charge), for quick market context.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
Takes no inputs.
“Crypto market data: precomputed RSI-14, MACD and Bollinger Bands plus latest OKX perp funding for BTC, ETH and SOL, or one coin via symbol= (bad symbol: 400, no charge), with no candle fetching neede…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
Takes no inputs.
- yieldreads or searches
“DeFi yield API: current APY for stablecoin and DeFi pools in one GET, no parameters.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
Takes no inputs.
“Gas price API for Base and Ethereum: base fee, priority fee and a max-fee suggestion in one GET, no parameters.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
Takes no inputs.
“Crypto market data: current OKX USDT-swap perp funding rates for BTC, ETH and SOL, or one coin via symbol= (bad symbol: 400, no charge), showing whether longs or shorts are paying.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
Takes no inputs.
“Wallet balance and portfolio API for one EVM address on Base and Ethereum: ETH, USDC, WETH, WBTC/cbBTC and DAI holdings with USD value.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
1 input, 1 required
addressstringrequired“EVM address (0x…) to snapshot on Base + Ethereum”
“URL to markdown API: a public web page as clean text or markdown for an LLM.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
1 input, 1 required
urlstringrequired“Public http(s) URL to fetch as clean text/markdown”
- httpdescribed as changing data
“HTTP request proxy API for public URLs: GET url (optional method GET/POST/HEAD/PUT/PATCH/DELETE; headers JSON), or POST JSON {url, method, headers, body}.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world yes
4 inputs, 1 required
urlstringrequired“Public http(s) URL”methodstring“HTTP method (default GET)”headersobject“Request headers (string values)”bodystring“Request body as text”
“Web scraping API: a public page or supplied HTML to JSON fields.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
3 inputs
urlstring“Public http(s) URL to extract from”htmlstring“Raw HTML to extract from (instead of url)”fieldsobject“Optional CSS-selector fields (max 20): name -> selector or {selector, attr ("text" default, "html", or an attribute name), all, limit 1-50}.”
“x402 endpoint checker: decodes an x402 endpoint's 402 payment terms without paying.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
3 inputs, 1 required
urlstringrequired“Public http(s) URL of the x402 endpoint to audit”methodstring“Probe method: GET (default; retries POST on 405) or POST”bodystring“Optional JSON body (string, <=8KB) for a POST probe; implies POST”
- x402_check_deepreads or searches
“x402 endpoint deep check, never pays or signs: the full /api/x402-check report plus live checks.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
3 inputs, 1 required
urlstringrequired“Public http(s) URL of the x402 endpoint to check”methodstring“Probe method: GET (default; retries POST on 405) or POST”bodystring“Optional JSON body (string, <=8KB) for a POST probe; implies POST”
- bazaar_checkreads or searches
“x402 Bazaar listing checker: is an x402 seller listed in Coinbase CDP Bazaar, on which networks, and if not, why.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
1 input, 1 required
urlstringrequired“Seller host (e.g.”
Show 20 more tools
“x402 API search: find paid x402 APIs for a task in Coinbase CDP Bazaar.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
6 inputs, 1 required
qstringrequired“What the agent needs, in words (<=200 chars)”ninteger“Offers to return, 1-10 (default 5); the top 3 are re-checked live”kindstring“Product kind filter (api_route, mcp_tool, data_feed, ...)”railstring“Payment rail filter: base | solana | xrpl | evm (any EVM chain except Base) | polygon (eip155:137 only) | an exact CAIP-2 network (e.g.”max_pricenumber“Max USD price per call, e.g.”min_healthnumber“Minimum health score 0-1”
- discourse_splitreads or searches
“Hacker News and Bluesky opinion split, NOT a poll: how public posts divide on a question.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
3 inputs, 1 required
qstringrequired“Question or topic, 3-200 chars.”sidesstring“2-4 comma-separated side labels (default yes,no)”windowstring“Look-back window 1-30 days, e.g.”
“Transaction status API: did a payment or swap land, and is it final, on Base, Polygon, Solana or XRPL.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
2 inputs, 1 required
txstringrequired“Transaction id: 0x + 64 hex (Base/Polygon), 64 hex (XRPL) or a base58 Solana signature”networkstring“base, polygon, solana or xrpl; required for 0x hashes.”
- tokenized_stockreads or searches
“Tokenized stock status API for Coinbase tokenized stocks on Base (AAPLc, NVDAc, TSLAc...).”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
1 input
symbolstring“Ticker (AAPL or AAPLc) or the token address on Base; omit for all listed Coinbase tokenized stocks.”
“Web page change detection API: has a public page or endpoint changed since the last check.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
2 inputs, 1 required
urlstringrequired“Public http(s) URL of the page or endpoint to check”sincestring“The state token from your previous watch answer for this url; omit on the first check”
“Wallet balance API for x402 payers: USDC on Base, Polygon and Solana, RLUSD on XRPL, and whether the wallet can pay now.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
3 inputs
evmstring“0x address checked on Base and Polygon (USDC + gas)”solanastring“Solana address (USDC + SOL)”xrplstring“XRP Ledger r-address (RLUSD, trust line, reserve, fee).”
- tx_guardreads or searches
“Address poisoning and OFAC SDN snapshot match before a crypto transfer, mechanical.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
4 inputs, 2 required
chainstringrequired“Chain of the transfer”tostringrequired“Recipient address you are about to send to”expectedstring“The address you meant to send to (for the lookalike check)”tokenstring“Token contract on Base or Polygon (ScamSniffer public list, GPL-3.0, up to 7-day delay)”
- grocery_normalizecalculates or converts
“Recipe ingredient parser and shopping list API: POST JSON {ingredients: [lines], servings?, targetServings?} (or GET ingredients=line|line).”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
3 inputs, 1 required
ingredientsarrayrequired“Recipe ingredient lines, one per item (max 100, 200 chars each)”servingsinteger“Servings the recipe makes (1-100); give with targetServings to scale”targetServingsinteger“Servings you want (1-100)”
- grocery_ingredientreads or searches
“Ingredient nutrition facts API: GET q (ingredient name or normalize canonicalId) and/or barcode (GTIN), optional n 1-5; POST JSON {items:[{q|barcode}]} max 10.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
2 inputs, 1 required
itemsarrayrequired“Up to 10 items, each with q and/or barcode; one price per call”ninteger“USDA matches per item (1-5, default 3)”
“Block height API: current block number, slot or ledger index for Base, Polygon, Ethereum, Solana and XRPL in one GET.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
1 input
networkstring“Comma list of base, polygon, ethereum, solana, xrpl (or CAIP-2 ids); default all five”
“Token metadata API: ERC-20 name, symbol, decimals and total supply on Base, Polygon or Ethereum; Solana mint decimals, supply, authorities (Token-2022 on-chain name and symbol); XRPL issued-currency …”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
2 inputs, 2 required
networkstringrequired“base, polygon, ethereum, solana or xrpl (or CAIP-2 id)”tokenstringrequired“EVM: 0x contract address.”
- name_resolvereads or searches
“ENS and Basenames resolver API: name to address (vitalik.eth, jesse.base.eth) or address to primary name, read on-chain.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
2 inputs
namestring“ENS name or Basename to resolve (vitalik.eth, jesse.base.eth).”addressstring“0x address for reverse lookup (ENS and Basename primary names).”
“Batch chain checks API: up to 10 checks for one payment.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
1 input, 1 required
itemsarrayrequired“1-10 checks; one $0.01 charge for the whole call if at least one item succeeds”
“x402 price quote and payTo check for one x402 seller URL, without paying.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
2 inputs, 1 required
urlstringrequired“https URL of the x402 resource to quote before paying”methodstring“Probe method GET (default; one POST retry on 405) or POST”
- screenshoton 82 other servers
“Website screenshot API: how a public page renders, as PNG or JPEG.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
5 inputs, 1 required
urlstringrequired“Public http(s) URL to render”widthinteger“Viewport width 320-1920 (default 1280)”heightinteger“Viewport height 240-2000 (default 800)”fullPageboolean“Capture full page (clipped at 4000px)”formatstring“Image format (default png)”
“Web search API with page contents: current results with sources as markdown.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
2 inputs, 1 required
qstringrequired“Web search query (<=300 chars)”ninteger“Result pages to fetch as clean text, 1-5 (default 3)”
“PDF to text API: the text of a public PDF, page by page.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
2 inputs, 1 required
urlstringrequired“Absolute http(s) URL of a public PDF (max 10MB)”pagesinteger“Max pages to return, 1-50 (default 50)”
- money_market_ratesreads or searches
“FREE (no x402, no payment).”
4 inputs
ratesstring“Comma list from SOFR,EFFR,OBFR,TGCR,BGCR (default all five)”lastinteger“Last n observations per rate, 1-10 (exclusive with startDate/endDate)”startDatestring“YYYY-MM-DD, >= 2018-04-02; needs endDate; span <= 31 days”endDatestring“YYYY-MM-DD, >= startDate”
“FREE (no payment).”
4 inputs, 2 required
typestringrequired“What is missing: coin, data, route or other”textstringrequired“1-500 characters, plain text.”symbolstring“Optional coin ticker, 2-10 ASCII letters or digits”routestring“Optional route path, e.g.”
- verified_brief_quotereads or searches
“Returns the payment instructions (the unpaid HTTP 402) for the $1 verified brief; this tool never runs the brief or pays.”
2 inputs, 1 required
qstringrequired“Question about Base or Ethereum gas, USDC supply on Ethereum and Base, or an x402 spec fact.”typestring“Optional: skip phrase matching and use this question type.”
Each quoted sentence is the first sentence of the publisher’s own description. The kind of tool and the “changes data” mark are our AI model’s reading of that description, not something we tested: two differently worded runs had to agree, otherwise no label is shown, and nobody has checked them by hand. A tool without the “changes data” mark is described as only reading, searching or calculating, or the two runs did not agree. No tool was called. Read the publisher’s full description before relying on it. “Publisher declares” lists the hints the server itself sends with the tool (MCP annotations: read-only, destructive, idempotent, open-world); they are the publisher's claims, not checked by us. Inputs are the parameters in the tool's own input schema: name, declared type, whether it is required, and the first sentence of its description. Read 2026-10-23.
How well are its tools described?
Features #4 and #5
How clearly this server's own tool descriptions say what a tool does, and how consistent its tool list is. The first part is an AI model's yes/no reading of each description; the second part is counted. We do not turn it into a grade.
Descriptions
AI reading of each description
- Says what the tool does
- 100% of 32 tools
- Says what it returns
- 100% of 32 tools
- States limits, defaults or errors
- 100% of 32 tools
- Says when to use it
- 100% of 32 tools
- Items covered per tool
- 4.0 of 4 on average
Counted from the listing
- Parameters with a description
- 100% of 69
- Tools with a description
- 100% of 32
- Typical description length
- 571 characters
The tool set
Counted from the listing
- Tools
- 32
- Size of the list
- about 9,099 tokens for an agent to load (characters ÷ 4)
- Naming
- 17 of 32 names use snake_case
AI reading: easy to mix up
No pair found.
The AI items cover 32 of 32 tools: for a tool where two differently worded runs disagreed, that item is left out. They were not checked by hand, and no tool was called. “Easy to mix up” means two tools whose names or descriptions overlap without saying how they differ; the AI found none. We do not rate whether the tool set is complete or whether side effects are spelled out, because our AI reading of those was not reliable enough.
How do I add it to my client?
Config from the registry entry
From the remote endpoint (Streamable HTTP)
We connected to this URL on 2026-10-23 (a read-only session: no tool was called).
Add to CursorAn install link in the format Cursor documents, holding the Cursor config below.
Claude Desktop or claude.ai
Settings → Connectors → Add custom connector, then paste: https://horizonpulse.dev/mcp
Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json
{
"mcpServers": {
"horizon-pulse": {
"url": "https://horizonpulse.dev/mcp"
}
}
}VS Code · .vscode/mcp.json
{
"servers": {
"horizon-pulse": {
"type": "http",
"url": "https://horizonpulse.dev/mcp"
}
}
}VS Code (command line) · Bash or zsh terminal (macOS, Linux)
code --add-mcp '{"name":"horizon-pulse","type":"http","url":"https://horizonpulse.dev/mcp"}'Claude Code
claude mcp add --transport http horizon-pulse https://horizonpulse.dev/mcp
Try it in the MCP Inspector · runs on your machine, opens in your browser · Node 22.19+
npx @modelcontextprotocol/inspector@2.11.0 --server-url https://horizonpulse.dev/mcp --transport http
- The server runs on the operator's infrastructure; it may ask you to sign in when you first connect.
- The MCP Inspector lists the server's tools, resources and prompts; a tool you call there runs for real.
Built from the server's registry entry with each client's documented format (checked 2026-10-14; the Cursor link and the VS Code command 2026-10-19; the MCP Inspector command 2026-10-21). Values in < > are yours to fill in; this page never contains a key. Where the server needs a setting the entry does not declare, it can still fail to start.
Does the registry listing match what we found?
Feature #6The registry verifies a package once, when it is published, and does not re-check it. A difference below is about the listing, not a judgement of the publisher.
| Registry says | We found | Result | Source · date |
|---|---|---|---|
| Remote endpoint horizonpulse.dev/mcp | Session opened | matches | our test · 2026-10-23 |
| No credential declared as required | Opened a session without any credential | matches | our test · 2026-10-23 |
| Repository github.com/horizon-pulse/horizon-pulse | Opens publicly | matches | api.github.com · 2026-10-23 |
Who made it?
Feature #7 · lineage
Facts about the publisher. We do not turn them into a trust score.
- Namespace
- io.github.horizon-pulse
- GitHub owner
- a personal account (horizon-pulse)
- Repository
- github.com/horizon-pulse/horizon-pulse
- Stars
- 0
- Repository age
- 31–90 days
- Last push
- 0–30 days ago
- Archived
- no
- Security policy
- none found (we looked for SECURITY.md in the repository and in its owner’s .github repository)
Source: the registry entry and api.github.com · 2026-10-23; security policy read from GitHub · 2026-10-23.
Publish this server? Run these checks against it yourself before release, from your own machine: a server the command starts, or your own server at its URL after a one-time proof that you control it: npx protocolprobe-selftest.
Choosing
Record checks
Public records · not a safety rating4 of 5 record checks met · 4 do not apply
- Not ranked by downloads: a remote server publishes no download figure
- Not ranked by stars: 0 stars (ranked from 10)
- MetRegistry entry is active and says how to run itActive, with a package or a remote address.
- MetSource repository link opensThe linked GitHub repository is public.
- MetRepository is not archivedNot archived.
- MetCode pushed to the repository in the 90 days before our checkLast push 0-30 days before our check.
- Not metRepository publishes a security policy (SECURITY.md)No SECURITY.md in the places GitHub reads it from.
- Does not applyPackage names its licence with a standard (SPDX) identifierRemote server: it ships no package.
- Does not applyThe version the registry lists can be installed and is not withdrawnRemote server: it ships no package.
- Does not applynpm package carries build provenance (attestation)Remote server: it ships no package.
- Does not applyNo known critical or high advisory in the package or its dependenciesRemote server: it ships no package.
Read from public records only: the registry entry, npm/PyPI, GitHub and advisory databases, checked 2026-10-23. No tool was called. Only “met” and “not met” are counted, so the total differs between servers; a check that does not apply or that we could not run is listed, never counted against it. It is not a safety rating. How each check works · Leaderboards
Common questions about io.github.horizon-pulse/horizon-pulse
Answered from the data aboveIs io.github.horizon-pulse/horizon-pulse safe to install?
We do not rate servers as safe or unsafe. 4 of its 5 applicable record checks are met (facts from public records, each listed on this page). What the records show: Its source repository opens publicly. Its repository had a push in the last 90 days. 2 of its tools describe changing data (our AI model's reading of the descriptions). These are facts with their sources on this page, not a safety guarantee, and we did not run its tools.
Is io.github.horizon-pulse/horizon-pulse free to use?
Its website (horizonpulse.dev/) describes a usage-based pricing model. This is an AI-classified reading of the page on 2026-10-23, so check the page itself before relying on it.
Does io.github.horizon-pulse/horizon-pulse need an API key or sign-in?
It opened a session without any credential on 2026-10-23. The registry entry declares no required credential; no declaration is not a guarantee.
Has io.github.horizon-pulse/horizon-pulse been security tested?
Partly. 2 of the 14 checks that apply to it were exercised. It accepted a session without any credential and lists tools whose names suggest they change data. We did not call them. No security verdict is published before verification.
What can io.github.horizon-pulse/horizon-pulse do?
It lists 32 tools. In our AI model's reading of their descriptions (two runs had to agree, nobody checked it by hand), they include tools that read or search and calculate or convert. We did not call any tool, so this describes the text, not the behaviour.
Can io.github.horizon-pulse/horizon-pulse change or delete data?
2 of its tools say in their description that they create, edit, delete, send or run something (our AI model's reading). We did not call any tool, so we cannot say what actually happens.
Does io.github.horizon-pulse/horizon-pulse publish a security policy?
We found no SECURITY.md in its repository (root, .github/ or docs/) or in its owner's .github repository.
Where is the source code of io.github.horizon-pulse/horizon-pulse?
In github.com/horizon-pulse/horizon-pulse, which opens publicly.
Found this page useful?
Anonymous · no sign-inA quick, anonymous reaction — no account, no email. One per kind from your browser. The tally updates when the page is next refreshed, and it is only a rough count, never a safety rating or a measured number of people.
Similar servers
Same topic · AI-read
- io.github.mnemox-ai/tradememory-protocolalso has tools that calculates or converts, reads or searchescompare with this one
- io.github.DeHor-Labs/mcp-fiscal-brasilMCP Fiscal Brasilalso has tools that calculates or converts, reads or searchescompare with this one
- io.github.YichengYang-Ethan/oracle3Oracle3 prediction-market arbitrage checksalso has tools that calculates or converts, reads or searchescompare with this one
- io.github.nikolasdehor/mcp-fiscal-brasilMCP Fiscal Brasilalso has tools that calculates or converts, reads or searchescompare with this one
- io.github.pyth-network/mcpPyth Pro MCP Serveralso has tools that calculates or converts, reads or searchescompare with this one
- io.github.nirholas/pumpfun-solana-mcppump.fun Solana Dataalso has tools that calculates or converts, reads or searchescompare with this one
Active servers whose topic is also “finance-and-payments” and that have at least one tool of the same kind; most kinds in common first, then most GitHub stars. The topic and the tool kinds are an AI model's reading of the publishers' descriptions, not checked by hand. Similar is not a recommendation.
Compare with another server
Side by side: registry entry, our read-only session, the tools and the 18 classification fields. Same values as each page; no score.
Security testing
What did we test, and what did we leave out?
18 checks · features #1, #2
Open without sign-in
It accepted a session without any credential and lists tools whose names suggest they change data. We did not call them. No security score is given; a check we did not run is never counted as passed.
- Inventory: exercised
- Hidden instructions: exercised
- Real execution: not run · our policy
- Secret leak: not run · nothing to check it against
- Internal addresses: not run · our policy
- Unconfirmed changes: not run · our policy
- Bad input: not run · our policy
- Model requests: not run · nothing to check it against
- Sensitive questions: not run · nothing to check it against
- Folder boundary: not run · our policy
- Log leaks: not run · nothing to check it against
- Hidden content: not run · nothing to check it against
- Fake assistant turns: not applicable
- Token passthrough: not applicable
- Token audience: not applicable
- Sign-in redirect: not run · our policy
- Consent handling: not testable from outside
- Sign-in metadata: not applicable
2 exercised12 not run (reason given)4 not applicable
Each check ends in exactly one state: exercised, not run (with the reason), or not applicable (with the reason). 2 of the 14 checks that apply to it were exercised. We do not publish security-check outcomes for named servers.
- 1Inventory
tool-listReads the declared tools, resources and prompts.exercised - 2Hidden instructions
description-poisoningLooks for hidden instructions in tool descriptions.exercised
- 3Real execution
real-executionCalls a tool and checks what really happens.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy - 4Secret leak
canary-leakPlants a fake secret and checks whether it leaks.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 5Internal addresses
ssrfChecks whether a tool can be steered to internal addresses.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy - 6Unconfirmed changes
write-without-confirmationChecks whether tools that change data act without asking.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy - 7Bad input
error-handlingSends bad input and watches how the server answers.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy - 8Model requests
samplingChecks whether the server asks the client's model to act for it.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 9Sensitive questions
elicitation-sensitive-dataChecks whether the server asks users for sensitive data.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 10Folder boundary
root-boundaryChecks whether the server reaches outside the folders it was given.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy - 11Log leaks
logging-side-channelChecks whether log messages carry data they should not.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 12Hidden content
audience-hidingChecks resources that hide content from the user.This check needs content the server returns, and nothing was read or called.not run · nothing to check it against - 16Sign-in redirect
open-redirectChecks the sign-in redirect for abuse.Testing the sign-in redirect means sending probes to the operator's sign-in service, which we do not do.not run · our policy - 17Consent handling
confused-deputyChecks consent handling when one service acts for another.Depends on the operator's own consent screen, which differs per server and cannot be tested from outside.not testable from outside
- 13Fake assistant turns
fake-assistant-turnChecks prompts that pose as the assistant's own words.The server exposes no prompts.not applicable - 14Token passthrough
token-passthroughChecks whether the server forwards a user's token to other services.The server opened a session without sign-in, so there is no token flow to check.not applicable - 15Token audience
token-audience-validationChecks whether tokens meant for another service are accepted.The server opened a session without sign-in, so there is no token flow to check.not applicable - 18Sign-in metadata
oauth-url-schemeChecks the published sign-in metadata for unsafe URLs.No sign-in (OAuth) metadata is published, so there are no sign-in addresses to check.not applicable
Source: our own test, 2026-10-23, mcp-runtime-engine@0.1.0. Which checks count and why follows our published scoring model.
What happened during the test?
Feature #8
The steps in order, as the test record holds them.
- 0 msStarted a read-only session with the server's remote endpoint
- 806 msConnected after 0 redirects. No credential was sent or needed.
- Read the inventory: 32 tools, 0 resources, 0 prompts.
- 3,540 msFinished: 2 checks exercised.
Reference
How is it classified?
18 fields
One value per field, each with its source. Fields written by AI models are marked. A field with no value says why.
“Your agent pays $0.002 – $0.04 per call in USDC on Base, Solana or Polygon, or RLUSD on the XRP Ledger, and gets JSON back.”
“Not stated” means the source did not state it; “does not apply” means it does not apply to this kind of server; “our limit” means our own lookup failed. A linked value opens the directory filtered to the same value.
Cite or correct this page
Sources and corrections
Suggested citation
ProtocolProbe. “io.github.horizon-pulse/horizon-pulse: MCP server record.” Data checked 2026-10-23. https://protocolprobe.com/mcp/servers/io.github.horizon-pulse/horizon-pulse
Figures are valid for the date shown. Our facts on this page are CC BY 4.0: reuse them with a link and the check date. Quoted text (the publisher’s descriptions, website quotes, tool names) is not ours to license.
As JSON: this record in the API · API documentation.
Badge for your README
[](https://protocolprobe.com/mcp/servers/io.github.horizon-pulse/horizon-pulse)
It shows this server's record-check count: facts from public records, no tool called. It is not a security rating or a pass. It links here and updates after each data reload.
Something wrong, or is this yours?
If a fact here is wrong, tell us and we will re-check it. If you operate this server, you can run our checks on it yourself with the free self-test command; we call no server’s tools ourselves for anything shown here.
Write to hello@protocolprobe.com · corrections log · methodology