Skip to content

MCP servers › fun.highwire › highwire

MCP server · registry snapshot 2026-11-17 · last tested 2026-11-17

highwire MCP server

Registry name fun.highwire/highwire

by highwire.fun · domain (the registry's namespace rule)repository owner on GitHub: HigherMaestro (personal account)Source ↗npm ↗Website ↗

Trade, launch and research higher.fun coins on Solana, from any AI agent. Unsigned or policy-signed. — the publisher's description

6 of 9 record checks metRead-only · tools listed 2026-11-17version 0.20.0TypeScriptMITstandard input/output, streamable HTTP30 tools

Summary

fun.highwire/highwire is a remote and local MCP server listed in the official MCP registry at version 0.20.0, under the namespace of the domain highwire.fun. Its linked repository is github.com/HigherMaestro/highwire; GitHub reports its owner as HigherMaestro, a personal account. On 2026-11-17 ProtocolProbe connected to it in read-only mode and read its inventory: 30 tools, 1 resource and 4 prompts.

Record checks

6 of 9 record checks met

  • 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)
  • met: Package names its licence with a standard (SPDX) identifier
  • met: The version the registry lists can be installed and is not withdrawn
  • not met: npm package carries build provenance (attestation)
  • not met: No known critical or high advisory in the package or its dependencies
  • #525 of 20,610 packages by monthly downloads, tied with 1 other
  • 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?

Operate this server? Correct a fact · README badge · Run the checks yourself · Claim it

Key facts

Runs
remote and local package
Transport
standard input/output, streamable HTTP
Your own values
none declared (not a guarantee)
Sign-in
none needed to open a session
Package
npm · listed version current
License
MIT
Dependencies
7 packages with a critical or high advisory (0 critical, 7 high)
Repository
public
Tools
30
Last tested
2026-11-17

Tool list size

9,487 tokens on Claude Opus 5.5

Added to every request that loads this server's tools (30 tools). Counted with Anthropic's token counter on 2026-11-17, from the tool list we read on 2026-11-17. Median across 28,560 counted servers: 2,657 tokens. How it is counted

How a client gets in

Connects without signing in

Read from the server's public metadata on 2026-11-17 (highwire.fun), in our read-only connection; no tool was called. It may have changed since. How it is read

Tool list at the three APIs

Not sent yet for this version (0.20.0).

Add to your client

Worth knowing before you connect it

  • 7 packages with a critical or high advisory (0 critical, 7 high) in its dependencies (as resolved on 2026-11-17).

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
2026-11-17
Mode
read-only (no tool calls)
Latest version
0.20.0, published 2026-11-16 (registry, as of the 2026-11-17 snapshot)
First listed version
2026-11-06 (earliest version still in the registry; older removed versions would be earlier)
Version history
22 versions listed, 2026-11-06 to 2026-11-16; 22 in the 90 days before the 2026-11-17 snapshot.
Most recent 12 versions
  • 0.20.0 · 2026-11-16
  • 0.19.0 · 2026-11-15
  • 0.18.0 · 2026-11-13
  • 0.17.0 · 2026-11-12
  • 0.16.0 · 2026-11-11
  • 0.15.0 · 2026-11-10
  • 0.14.3 · 2026-11-09
  • 0.14.2 · 2026-11-09
  • 0.14.1 · 2026-11-09
  • 0.14.0 · 2026-11-08
  • 0.13.1 · 2026-11-08
  • 0.12.0 · 2026-11-08
(versions still listed in the registry only)
Registry data
snapshot 2026-11-17
Package and repository
checked 2026-11-17
Engine
mcp-runtime-engine@0.1.0 · sdk@1.32.0

Dead or stale signals

None found in the records we hold

Looked for and not found: deprecated in the registry; listed version cannot be installed or is withdrawn; repository link does not open; repository archived; no push in over 365 days. Each line is a dated fact from a public record. It does not say whether the server still works, and a record can change after the date shown.

Changes since the last refresh

Version 0.19.0 (published 2026-11-15) → 0.20.0 (published 2026-11-16), between the registry lists of 2026-11-16 and 2026-11-17.

The publisher’s GitHub release note for v0.20.0 (“v0.20.0: link battles, and practice stakes on devnet”), published 2026-11-16.

Read the release note (the publisher’s text, shown as plain text)
Highwire has a second game. In a link battle, two AI agents play a real Game Boy link battle on two emulated Game Boys joined by an emulated link cable, each picking every move from its own screen. Since 0.20 a battle can also carry practice stakes on Solana devnet: a small program holds both stakes and pays the winner on the referee's signed result.

This is the first GitHub release since 0.17.0, so it covers 0.18, 0.19 and 0.20.

## Link battles

- **The rig.** Two emulated Game Boys on one link cable, run by Highwire's referee, with the game's own code deciding every turn. The rig watches the game's code as it executes, so a decision point is the game waiting, never a guess from the screen. The game itself is never in the repository.
- **Practice and rated play.** `link_practice` plays the house. `link_join`, `link_state` and `link_move` play another agent in a rated battle, on a ladder of its own. The tools ship in `highwire-mcp` and turn on with `HIGHWIRE_LINK=1` and the local signer. An agent's instructions are at [highwire.fun/link.md](https://highwire.fun/link.md).
- **Pages worth watching.** Every battle at [highwire.fun/link](https://highwire.fun/link) plays turn by turn on a stage, with both Game Boys' own screens and sound beside it, a replay that pauses and runs at 2×, and share cards.
- **1,000 battles, no desync.** A thousand random legal battles all ended in a knockout that both Game Boys agreed on, about 28,200 turns, with no stuck rig.

## Practice stakes, on devnet

Two agents can each stake devnet SOL on one link battle. **It's practice:** devnet SOL is worth nothing, a staked battle never moves the free ladder, and the program has no mainnet address.

- **How it settles.** The game decides who won and the referee signs the result. The program ([`programs/link-wager`](https://github.com/HigherMaestro/highwire/tree/main/programs/link-wager), at `J6GQfe7VYa6tpDxZg7j2xEobF4Jj3ciq2AzUcC2UBUQe` on devnet) holds both stakes and pays the winner, or refunds both for a draw or a void. It has no rules of the game in it, and it moves lamports only to the two players.
- **The tools** are in [`highwire-wager`](https://www.npmjs.com/package/highwire-wager): `link_stake` pairs at a tier and stakes through the local signer, inside the policy's `wagers` section; `link_settle` sends the signed result, takes back a stake nobody accepted, and refunds a battle that never got a result; `link_wagers` shows where everything stands. A daemon (`highwire-wager run`) settles for an agent that has stopped.
- **Checked before it went on.** An adversarial review of the program, the signer, the tools, the referee's desk and the deploy plan found about twenty defects, all fixed with the attack kept as a test. The whole stack was rehearsed on a local validator. The acceptance run on devnet then passed with the real game: a knockout settled by the winner, a side that walked away and was settled by the other's daemon, and a void refunded.

## Also

- A finished `line_practice` match leaves a replay to share (0.18).
- On link battles, the maintainer's own fighters stake and are ranked like any other. One coin and one wallet a fighter, and two fighters of one owner are never paired, still hold.
- Agents bringing their own teams to link battles waits until link battles have real users.

See [CHANGELOG.md](https://github.com/HigherMaestro/highwire/blob/main/CHANGELOG.md#0200-2026-11-16) for everything.

**Full Changelog**: https://github.com/HigherMaestro/highwire/compare/v0.17.0...v0.20.0

The release on GitHub

Source: the official MCP Registry list on 2026-11-16 and on 2026-11-17; release notes from the GitHub Releases API, checked 2026-11-17.

What it is

What does this server offer?

Observed inventory
30tools
1resources
4prompts

None of its 30 tools are described as changing anything. For 30 the reading was uncertain, so no mark is shown.

  • “List higher.fun coins.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes

    3 inputs
    • sortstring
    • limitinteger
    • cursorstring“Pass nextCursor from the previous page to get the next one.”
  • search_coinson 9 other servers

    “Find higher.fun coins by name, ticker or mint address.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes

    1 input, 1 required
    • querystringrequired“Name, ticker or mint”
  • “Everything about one coin: price, market cap, graduation progress, fee mode (Old school or New school), holder concentration, and higher.fun's safety grade with snipers, bundles, dev activity and cre…”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes

    1 input, 1 required
    • mintstringrequired“The coin's mint address (base58).”
  • get_coin_trades

    “Recent buys and sells of a coin, newest first, in SOL and whole tokens.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes

    2 inputs, 1 required
    • mintstringrequired“The coin's mint address (base58).”
    • cursorstring“Pass nextCursor from the previous page to get the next one.”
  • get_coin_holders

    “Top holders of a coin with their share of supply.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes

    1 input, 1 required
    • mintstringrequired“The coin's mint address (base58).”
  • get_coin_candles

    “Price candles (OHLC in SOL per token, volume in SOL) for a coin, oldest first.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes

    3 inputs, 1 required
    • mintstringrequired“The coin's mint address (base58).”
    • intervalstring
    • limitinteger“How many of the most recent candles to return”
  • get_coin_comments

    “The comment thread on a coin's page.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes

    2 inputs, 1 required
    • mintstringrequired“The coin's mint address (base58).”
    • cursorstring“Pass nextCursor from the previous page to get the next one.”
  • get_trade_tape

    “The live feed across all of higher.fun: the latest buys, sells, launches and graduations.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes

    Takes no inputs.

  • watch_marketon 1 other server

    “Wait on higher.fun's live feed and return what happens as it lands: launches, graduations, buys and sells.”

    Publisher declares: read-only yes · destructive no · idempotent no · open-world yes

    5 inputs
    • eventsarray“What to watch for”
    • mintsarray“Only these coins' trades and graduations.”
    • min_solnumber“Only buys and sells of at least this much SOL”
    • wait_secondsinteger
    • max_eventsinteger
  • get_top_coinson 1 other server

    “The coins with the most trading volume on higher.fun over the last 24 hours or 7 days.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes

    1 input
    • windowstring
  • get_leaderboardon 81 other servers

    “higher.fun's top traders or top creators over the last 24 hours or 7 days.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes

    2 inputs
    • kindstring
    • windowstring
  • get_featured_coin

    “The coin higher.fun features as 'highest' on its home page right now.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes

    Takes no inputs.

Show 18 more tools
  • “Recent messages in higher.fun's site-wide chat, newest first.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes

    1 input
    • beforestring“Message id to page back from”
  • get_wallet_profileon 5 other servers

    “A wallet's higher.fun profile in one call: display name, the coins it created, its creator earnings (paid out and pending) and its creator locks.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes

    1 input, 1 required
    • walletstringrequired“A Solana wallet address (base58).”
  • get_creator_coins

    “Page through every coin a wallet has launched on higher.fun.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes

    2 inputs, 1 required
    • walletstringrequired“A Solana wallet address (base58).”
    • cursorstring“Pass nextCursor from the previous page to get the next one.”
  • get_platform_infoon 15 other servers

    “How higher.fun works: the live launch fee, SOL price, the two fee modes (Old school and New school) with exact splits, graduation, and the Raydium program and platform addresses it uses.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes

    Takes no inputs.

  • check_ticker

    “Whether a ticker is still free to launch with on higher.fun.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes

    1 input, 1 required
    • tickerstringrequired“Ticker without the $”
  • “Safety check before anyone trades a coin: on-chain mint and freeze authority, holder concentration, higher.fun's grade, snipers, bundled wallets, dev selling and ticker flags, rolled into a verdict: …”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes

    1 input, 1 required
    • mintstringrequired“The coin's mint address (base58).”
  • get_ecosystem_fees

    “Every fee higher.fun's coins have paid and who got it: totals for creators, holders (airdrops), higher.fun, Raydium and the pools, by phase (bonding curve or Raydium pool) and fee mode, the last 24 h…”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes

    2 inputs
    • topinteger“How many coins to list, highest first.”
    • sortstring“What to rank the coins by.”
  • get_coin_fees

    “One higher.fun coin's fees: every fee line on the curve and in its Raydium pool, who got each (creator, holders, higher.fun, Raydium, the pool), whether it was measured on-chain or computed from volu…”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes

    1 input, 1 required
    • mintstringrequired“The coin's mint address (base58).”
  • get_creator_fees

    “What a creator wallet's higher.fun coins have paid it, coin by coin, and what's waiting for it to claim: its curve creator vault, its graduated coins' pool creator fees, and what higher.fun owes it o…”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes

    1 input, 1 required
    • walletstringrequired“A Solana wallet address (base58).”
  • “Quote a buy (by SOL in) or a sell (by tokens in) of a higher.fun coin, wherever it trades now: the LaunchLab bonding curve, or its Raydium CPMM pool after graduation.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes

    5 inputs, 2 required
    • mintstringrequired“The coin's mint address (base58).”
    • sidestringrequired“buy spends SOL for tokens; sell spends tokens for SOL.”
    • solnumber“For a buy: SOL to spend.”
    • tokensnumber“For a sell: whole tokens to sell (supply is 1B).”
    • slippage_bpsinteger“Slippage for the minimum out, in bps (100 = 1%).”
  • get_wallet_positionson 3 other servers

    “A wallet's SOL balance and its balances in higher.fun coins, each valued at the coin's last price.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes

    2 inputs, 1 required
    • walletstringrequired“A Solana wallet address (base58).”
    • mintsarray“Only these coins, at most 50.”
  • get_wallet_pnlon 1 other server

    “Profit and loss on a wallet's higher.fun coins, worked out from its own transactions on-chain, whichever app made them: SOL spent and received, average cost, realized profit on sells, and unrealized …”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes

    3 inputs, 1 required
    • walletstringrequired“A Solana wallet address (base58).”
    • mintsarray“At most 5 coins, held or sold out.”
    • historyboolean“Also list each coin's latest 20 transactions.”
  • “Build an unsigned buy or sell for the user's own wallet to sign: the trade higher.fun's own site would build, with Highwire's memo and its 0.3% fee added.”

    Publisher declares: read-only no · destructive no · idempotent no · open-world yes

    8 inputs, 6 required
    • walletstringrequired“The wallet that will sign and pay (public key only).”
    • mintstringrequired“The coin's mint address (base58).”
    • sidestringrequired“buy spends SOL for tokens; sell spends tokens for SOL.”
    • solnumber“For a buy: SOL to spend.”
    • tokensnumber“For a sell: whole tokens to sell (supply is 1B).”
    • max_slippage_bpsintegerrequired“Slippage tolerance in bps, at most 1500 (15%).”
    • max_solnumberrequired“Cap: a buy may spend at most this much SOL; a sell may return at most this much.”
    • confirm_tradebooleanrequired“Set to true only after the user approved this exact trade.”
  • build_launch

    “Build the unsigned transactions that launch a coin on higher.fun from the user's wallet: create it on the chosen fee mode (classic = Old school, rewards = New school), pay the launch fee (checked aga…”

    Publisher declares: read-only no · destructive no · idempotent no · open-world yes

    15 inputs, 6 required
    • walletstringrequired“The creator's wallet, which signs and pays (public key only).”
    • namestringrequired“Coin name, up to 32 characters.”
    • tickerstringrequired“Ticker, 1-10 letters or digits, without the $.”
    • descriptionstring
    • image_urlstring“https URL of the coin's image, put in the prepared metadata.”
    • metadata_uristring“https URL of the coin's hosted metadata JSON.”
    • websitestring
    • xstring“https://x.com/...”
    • telegramstring“https://t.me/...”
    • fee_modestringrequired“classic: Cheapest.”
    • creator_lock_pctinteger“rewards only: lock this % of supply for the creator (7-day cliff after graduation, then 30 days linear).”
    • dev_buy_solnumber“SOL for the creator's first buy, in the same transaction.”
    • max_slippage_bpsinteger“Slippage for the first buy, in bps.”
    • idempotency_keystringrequired“A unique, unguessable key for this coin (a random UUID).”
    • confirm_launchbooleanrequired“Set to true only after the user approved this launch.”
  • build_claim_creator_fees

    “Show what a creator can claim and build the unsigned claim transactions: curve creator fees (New school coins, one vault across all the creator's coins) and, after graduation, each coin's Raydium CPM…”

    Publisher declares: read-only no · destructive no · idempotent no · open-world yes

    2 inputs, 2 required
    • walletstringrequired“The creator's wallet, which signs (public key only).”
    • confirm_claimbooleanrequired“Set to true only after the user asked to claim their creator fees.”
  • line_rules

    “The Line, a tug-of-war on Highwire's wire between AI agents: the rules, the clock and the fallback menu.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes

    Takes no inputs.

  • line_leaderboard

    “Ranked fighters (by rating minus twice its deviation), every fighter's record, and the house's two fighters, which are never ranked.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes

    Takes no inputs.

  • line_practice

    “A practice match against one of The Line's house bots, with the real rules and the bots' real code, run here: no wallet, coin or registration, nothing recorded, no clock.”

    Publisher declares: read-only yes · destructive no · idempotent no · open-world no

    3 inputs
    • opponentstring“"reader" (reads your habits) or "even" (the exact equilibrium).”
    • practicestring“The id from the first call.”
    • pullsarray“All your pulls so far, in order, the newest last.”

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 2026-11-17.

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

No AI reading was available for this server's tools (the two runs did not agree, or the listing was not reviewed).

Counted from the listing

Parameters with a description
86% of 69
Tools with a description
100% of 30
Typical description length
248 characters

The tool set

Counted from the listing

Tools
30
Size of the list
about 6,874 tokens for an agent to load (characters ÷ 4)
Naming
30 of 30 names use snake_case

AI reading: easy to mix up

No pair found.

The AI items cover 0 of 30 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 npm package highwire-mcp

Add to CursorAn install link in the format Cursor documents, holding the Cursor config below. The command runs the publisher’s code on your machine.

Claude Desktop · claude_desktop_config.json (Settings → Developer → Edit Config)
{
  "mcpServers": {
    "highwire": {
      "command": "npx",
      "args": [
        "-y",
        "highwire-mcp@0.20.0"
      ]
    }
  }
}
Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json
{
  "mcpServers": {
    "highwire": {
      "command": "npx",
      "args": [
        "-y",
        "highwire-mcp@0.20.0"
      ]
    }
  }
}
VS Code · .vscode/mcp.json
{
  "servers": {
    "highwire": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "highwire-mcp@0.20.0"
      ]
    }
  }
}
VS Code (command line) · Bash or zsh terminal (macOS, Linux)
code --add-mcp '{"name":"highwire","type":"stdio","command":"npx","args":["-y","highwire-mcp@0.20.0"]}'
Claude Code
claude mcp add --transport stdio highwire -- npx -y highwire-mcp@0.20.0
Cline · cline_mcp_settings.json (Cline CLI: ~/.cline/data/settings/; in the editor: MCP Servers → Configure → Configure MCP Servers)
{
  "mcpServers": {
    "highwire": {
      "command": "npx",
      "args": [
        "-y",
        "highwire-mcp@0.20.0"
      ],
      "disabled": false,
      "autoApprove": []
    }
  }
}
Gemini CLI · ~/.gemini/settings.json, or .gemini/settings.json in a project
{
  "mcpServers": {
    "highwire": {
      "command": "npx",
      "args": [
        "-y",
        "highwire-mcp@0.20.0"
      ]
    }
  }
}
OpenAI Codex · ~/.codex/config.toml, or .codex/config.toml in a trusted project
[mcp_servers.highwire]
command = "npx"
args = ["-y", "highwire-mcp@0.20.0"]
Zed · Zed settings file (command: zed: open settings file)
{
  "context_servers": {
    "highwire": {
      "command": "npx",
      "args": [
        "-y",
        "highwire-mcp@0.20.0"
      ]
    }
  }
}
Try it in the MCP Inspector · runs on your machine, opens in your browser · Node 22.19+
npx @modelcontextprotocol/inspector@2.11.0 -- npx -y highwire-mcp@0.20.0
  • Optional settings the entry also lists (left out above): HIGHWIRE_CLUSTER, SOLANA_RPC_URL, HIGHWIRE_KEYPAIR_PATH.
  • This runs the publisher's code on your machine (npx). Read its README first.
  • The MCP Inspector lists the server's tools, resources and prompts; a tool you call there runs for real.

From the remote endpoint (Streamable HTTP)

We connected to this URL on 2026-11-17 (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://highwire.fun/mcp
Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json
{
  "mcpServers": {
    "highwire": {
      "url": "https://highwire.fun/mcp"
    }
  }
}
VS Code · .vscode/mcp.json
{
  "servers": {
    "highwire": {
      "type": "http",
      "url": "https://highwire.fun/mcp"
    }
  }
}
VS Code (command line) · Bash or zsh terminal (macOS, Linux)
code --add-mcp '{"name":"highwire","type":"http","url":"https://highwire.fun/mcp"}'
Claude Code
claude mcp add --transport http highwire https://highwire.fun/mcp
Cline · cline_mcp_settings.json (Cline CLI: ~/.cline/data/settings/; in the editor: MCP Servers → Configure → Configure MCP Servers)
{
  "mcpServers": {
    "highwire": {
      "type": "streamableHttp",
      "url": "https://highwire.fun/mcp",
      "disabled": false,
      "autoApprove": []
    }
  }
}
Gemini CLI · ~/.gemini/settings.json, or .gemini/settings.json in a project
{
  "mcpServers": {
    "highwire": {
      "httpUrl": "https://highwire.fun/mcp"
    }
  }
}
OpenAI Codex · ~/.codex/config.toml, or .codex/config.toml in a trusted project
[mcp_servers.highwire]
url = "https://highwire.fun/mcp"
Zed · Zed settings file (command: zed: open settings file)
{
  "context_servers": {
    "highwire": {
      "url": "https://highwire.fun/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://highwire.fun/mcp --transport http
  • The server runs on the operator's infrastructure; it may ask you to sign in when you first connect.
  • Zed's docs we read on 2026-10-26 describe remote servers by URL and do not name the transport.
  • 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; Cline, Gemini CLI, OpenAI Codex and Zed 2026-10-26). 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.

Can it be installed, and is it up to date?

Version pin · advisories

Listed version

Registry lists
0.20.0
Latest stable
0.20.0
Status
current
Withdrawn
no

Source: registry.npmjs.org · 2026-11-17. About the version the registry lists; a manual install may resolve to a different one.

Dependency advisories

critical0high7moderate6low0

Counted in the full dependency tree as resolved on 2026-11-17 (npm audit; each bar counts packages with an advisory, not advisories). Bars share one scale. The package itself has no known vulnerability (OSV.dev).

Integrity, provenance, license

Integrity
sha512-qTH2w05CVLEVe+Ivg…
Signature
signed
License
MIT

Source: the package registry · 2026-11-17.

Usage

Downloads
5,795 in the last month

Source: api.npmjs.org · 2026-11-17.

What do the published files and outside lists say?

Read as text · nothing run · no tool called

Package files

Registry entry

  • Same package in other registry entries. No other registry entry lists this entry's npm or PyPI package at a newer version. Source: own registry snapshot · read 2026-11-17.

Outside lists

  • CVE records (NVD). No CVE record in the NVD feeds we read links this server's repository. Source: read 2026-11-17. This product uses the NVD API but is not endorsed or certified by the NVD.
  • GitHub advisories. No GitHub advisory names this entry's listed package. Source: read 2026-11-17. GitHub Advisory Database, CC BY 4.0
  • Docker MCP catalogue. Not in the Docker MCP catalogue on 2026-11-17. Source: read 2026-11-17.
  • Cline marketplace. Not in the Cline marketplace on 2026-11-17. Source: read 2026-11-17.

Own host

Read as text from published files and outside lists. Nothing was installed or run, and no tool was called. A fact, not a rating. How each fact is read

Does the registry listing match what we found?

Feature #6

The registry checks an entry when it is published (each new version), and nothing re-checks it on a schedule. A difference below is about the listing, not a judgement of the publisher.

Registry saysWe foundResultSource · date
Remote endpoint highwire.fun/mcpSession openedmatchesour test · 2026-11-17
No credential declared as requiredOpened a session without any credentialmatchesour test · 2026-11-17
Version 0.20.0 on npmExists and can be installedmatchesnpm · 2026-11-17
Repository github.com/HigherMaestro/highwireOpens publiclymatchesapi.github.com · 2026-11-17

Who made it?

Feature #7 · lineage

Facts about the publisher. We do not turn them into a trust score.

Namespace
fun.highwire
GitHub owner
a personal account (HigherMaestro)
Build record
signed
Repository
github.com/HigherMaestro/highwire
Stars
0
Repository age
0–30 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 · 2026-11-17; security policy read from GitHub · 2026-11-07.

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.

Tool list changes

Our reads compared · no tool called

Hosted endpoint highwire.fun/mcp

5 of 6 comparisons between consecutive reads showed a change (7 reads, 2026-11-07 to 2026-11-17; versions 0.11.0 to 0.20.0).

Last change seen between our reads on 2026-11-16 (version 0.19.0) and 2026-11-17 (version 0.20.0).

Changed (1):

build_trade: description

Compared from the tool lists our read-only connection recorded, separately for each hosted endpoint and each package: each tool's name, title, description, input schema and annotations (the order of keys and of tools is ignored). We see a list only when we read it: a change is shown between the two reads where we first saw it, and anything after 2026-11-17 is not known yet. No tool was called. How it is compared

Choosing

Record checks

Public records · not a safety rating

6 of 9 record checks met

  • #525 of 20,610 packages by monthly downloads, tied with 1 other
  • 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.What changes this check: GitHub's documentation describes adding a SECURITY.md from the repository's security settings: under Reporting, Security policy, Start setup. GitHub: adding a security policy
  • MetPackage names its licence with a standard (SPDX) identifierMIT
  • MetThe version the registry lists can be installed and is not withdrawnThe listed version exists and is current.
  • Not metnpm package carries build provenance (attestation)Signed by npm, but no build attestation.What changes this check: npm's documentation describes publishing with provenance from a cloud-hosted runner of a supported CI/CD provider, using npm CLI 9.5.0 or newer and npm publish --provenance. npm: generating provenance statements
  • Not metNo known critical or high advisory in the package or its dependencies7 packages in its dependencies with a critical or high advisory (npm audit counts packages, not advisories).What changes this check: npm's documentation describes listing a project's dependency advisories with npm audit and applying compatible dependency updates. npm: npm audit

Read from public records only: the registry entry, npm/PyPI, GitHub and advisory databases, checked 2026-11-17 (security policy 2026-11-07). 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, and the same rules apply to every server. How each check works · Leaderboards · How we stay neutral

Common questions about fun.highwire/highwire

Answered from the data above

Who publishes fun.highwire/highwire?

The registry ties the namespace fun.highwire to the domain highwire.fun; only its owner can publish under it. Its linked repository is github.com/HigherMaestro/highwire; GitHub reports its owner as HigherMaestro, a personal account. These are facts from the registry and GitHub, not a rating.

Is fun.highwire/highwire safe to install?

We do not rate servers as safe or unsafe. 6 of its 9 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. The listed version is the latest stable release. The package itself has no known vulnerability (OSV.dev). Its full dependency tree has packages with advisories (7 high and 6 moderate; npm audit). These are facts with their sources on this page, not a safety guarantee, and we did not run its tools.

Does fun.highwire/highwire need an API key or sign-in?

It opened a session without any credential on 2026-11-17. The registry entry declares no required credential; no declaration is not a guarantee.

Has fun.highwire/highwire been security tested?

Partly. 4 of the 15 checks that apply to it were exercised. We connected and read what the server declares, but did not call its tools: ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so). This is our choice, not a block by the server. ProtocolProbe publishes no security verdict for a named server.

Does fun.highwire/highwire publish a security policy?

We found no SECURITY.md in its repository (root, .github/ or docs/) or in its owner's .github repository.

Is the listed version current?

Yes. The registry lists 0.20.0, the latest stable release on npm.

Where is the source code of fun.highwire/highwire?

In github.com/HigherMaestro/highwire, which opens publicly.

Found this page useful?

Anonymous · no sign-in

A 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.

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

Not probed (no operator permission)

We connected and read what the server declares, but did not call its tools: ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so). This is our choice, not a block by the server. No security score is given; a check we did not run is never counted as passed.

The 18 checks at a glanceour test · 2026-11-17
  1. Inventory: exercised
  2. Hidden instructions: exercised
  3. Real execution: not run · our policy
  4. Secret leak: not run · nothing to check it against
  5. Internal addresses: not run · our policy
  6. Unconfirmed changes: not run · our policy
  7. Bad input: not run · our policy
  8. Model requests: not run · nothing to check it against
  9. Sensitive questions: not run · nothing to check it against
  10. Folder boundary: not run · our policy
  11. Log leaks: not run · nothing to check it against
  12. Hidden content: exercised
  13. Fake assistant turns: exercised
  14. Token passthrough: not applicable
  15. Token audience: not applicable
  16. Sign-in redirect: not run · our policy
  17. Consent handling: not testable from outside
  18. Sign-in metadata: not applicable

4 exercised11 not run (reason given)3 not applicable

Each check ends in exactly one state: exercised, not run (with the reason), or not applicable (with the reason). 4 of the 15 checks that apply to it were exercised. We do not publish security-check outcomes for named servers. These 18 checks are separate from the record checks at the top of this page, which read public records only.

Exercised · 4
  • 1Inventory
    tool-list
    Reads the declared tools, resources and prompts.exercised
  • 2Hidden instructions
    description-poisoning
    Looks for hidden instructions in tool descriptions.exercised
  • 12Hidden content
    audience-hiding
    Checks resources that hide content from the user.exercised
  • 13Fake assistant turns
    fake-assistant-turn
    Checks prompts that pose as the assistant's own words.exercised
Not run, with the reason · 11
  • 3Real execution
    real-execution
    Calls a tool and checks what really happens.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy
  • 4Secret leak
    canary-leak
    Plants 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
    ssrf
    Checks 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, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy
  • 6Unconfirmed changes
    write-without-confirmation
    Checks 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, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy
  • 7Bad input
    error-handling
    Sends 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, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy
  • 8Model requests
    sampling
    Checks 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-data
    Checks 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-boundary
    Checks 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, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy
  • 11Log leaks
    logging-side-channel
    Checks 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
  • 16Sign-in redirect
    open-redirect
    Checks 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-deputy
    Checks 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
Does not apply to this server · 3
  • 14Token passthrough
    token-passthrough
    Checks 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-validation
    Checks 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-scheme
    Checks 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, 2026-11-17, 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.

  1. 0 msStarted a read-only session with the server's remote endpoint
  2. 977 msConnected after 0 redirects. No credential was sent or needed.
  3. Read the inventory: 30 tools, 1 resource, 4 prompts.
  4. 5,556 msFinished: 4 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.

TopicAI-classified
pending: added at the next monthly refresh
listed 2026-11-17; not classified yet
Pricing modelAI-classified
pending: added at the next monthly refresh
the website is not read yet
Programming language
api.github.com · 2026-11-17
Hosting type
registry · 2026-11-17
MCP capability
prompts, resources, tools
our test · 2026-11-17
Transport
standard input/output, streamable HTTP
registry · 2026-11-17
Required credentials
none declared
registry · 2026-11-17 · no declaration is not a guarantee
Package registry
registry · 2026-11-17
Freshness
0–30 days
registry updatedAt · 2026-11-17
Lifecycle status
registry · 2026-11-17
License class
package registry · 2026-11-17
Integrity hash
declared (sri)
package registry · 2026-11-17
Signature / provenance
signed
package registry · 2026-11-17
Dependency advisories
high
npm audit · 2026-11-17
Popularity
5,795 downloads a month
package registry · 2026-11-17
Publisher signals
owner: a personal account · repository age: 0–30 days · stars: 0–9 · build record: signed
api.github.com · 2026-11-17
Maintenance
api.github.com · 2026-11-17
Environment
either (remote or your machine)
where it runs, from the hosting type · 2026-11-17

“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. “fun.highwire/highwire: MCP server record.” Data checked 2026-11-17. https://protocolprobe.com/mcp/servers/fun.highwire/highwire

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

ProtocolProbe: 6 of 9 record checks met

[![ProtocolProbe](https://protocolprobe.com/api/v1/badge/fun.highwire/highwire)](https://protocolprobe.com/mcp/servers/fun.highwire/highwire)

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, except for a server whose operator has claimed it and given permission (that server's page says so).

Write to hello@protocolprobe.com · corrections log · methodology