MCP servers › io.github.t0ll-xyz › toll
MCP server · registry snapshot 2026-11-12 · last tested 2026-11-12
toll MCP server
Registry name io.github.t0ll-xyz/toll
by t0ll-xyz · GitHub account (the registry's namespace rule)repository: same ownerSource ↗npm ↗Website ↗
Robinhood Chain checks for agents: coins, devs, ERC-8004 agents, pre-sign check, Stock Token data. — the publisher's description
Summary
io.github.t0ll-xyz/toll is a remote and local MCP server listed in the official MCP registry at version 0.6.1, under the namespace of the GitHub account t0ll-xyz. Its linked repository, github.com/t0ll-xyz/toll-plugins, belongs to the same GitHub account. On 2026-11-12 ProtocolProbe connected to it in read-only mode and read its inventory: 28 tools, 0 resources and 0 prompts.
Record checks
- 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- met: The version the registry lists can be installed and is not withdrawn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)
- met: No known critical or high advisory in the package or its dependencies
- #1,140 of 20,610 packages by monthly downloads
- 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
- no known high or critical advisories
- Repository
- public
- Tools
- 28
- Last tested
- 2026-11-12
Tool list size
14,044 tokens on Claude Opus 5.5
Added to every request that loads this server's tools (28 tools). Counted with Anthropic's token counter on 2026-11-12, from the tool list we read on 2026-11-12. 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 2026-11-12 (t0ll.xyz), 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 (0.6.1).
Observed fact
This server accepted a session without any credential and lists 2 tools whose name or declaration suggests they change data (unwatch_coin, unwatch_wallet). That is our reading of the names; we did not call them. Source: our connection, 2026-11-12.
How fresh this is
- Live-tested
- yes, a real session (not a text-only review)
- Last tested
- 2026-11-12
- Mode
- read-only (no tool calls)
- Latest version
- 0.6.1, published 2026-11-11 (registry, as of the 2026-11-12 snapshot)
- First listed version
- 2026-11-06 (earliest version still in the registry; older removed versions would be earlier)
- Version history
- 6 versions listed, 2026-11-06 to 2026-11-11; 6 in the 90 days before the 2026-11-12 snapshot.(versions still listed in the registry only)
Most recent 6 versions
0.6.1· 2026-11-110.6.0· 2026-11-100.5.0· 2026-11-090.4.1· 2026-11-080.4.0· 2026-11-070.3.0· 2026-11-06
- Registry data
- snapshot 2026-11-12
- Package and repository
- checked 2026-11-12
- 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 0.5.0 (published 2026-11-09) → 0.6.1 (published 2026-11-11), between the registry lists of 2026-11-09 and 2026-11-12.
The publisher published no GitHub release note for this version: its repository publishes no GitHub releases.
Source: the official MCP Registry list on 2026-11-09 and on 2026-11-12; release notes from the GitHub Releases API, checked 2026-11-12.
What it is
What does this server offer?
Observed inventoryNone of its 28 tools are described as changing anything. For 28 the reading was uncertain, so no mark is shown.
- check_coinon 5 other servers
“Use it when someone asks "is this a rug?", "who made this coin?", "was it sniped or bundled?" or "can the dev pull the liquidity?" about a token address.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
2 inputs, 1 required
addressstringrequired“The token contract address: 0x followed by 40 hex characters”chainstring“Which chain: rh = Robinhood Chain (4663).”
- pre_buy_checkon 1 other server
“Use it when someone is about to buy a coin and asks "should I buy this?" or "should I ape this?": Toll answers with facts, not advice.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
1 input, 1 required
addressstringrequired“The token contract address you are about to buy on Robinhood Chain: 0x followed by 40 hex characters”
- check_coinson 1 other server
“Up to 20 Robinhood Chain coins in one call, answered only from checks Toll already holds (read in the last 24 h): for each coin the verdict word (AGAINST / CAREFUL / CLEAR / INCOMPLETE) with its tall…”
Publisher declares: read-only yes · destructive no · idempotent no · open-world yes
1 input, 1 required
addressesarrayrequired“Token contract addresses on Robinhood Chain, 1 to 20 (0x followed by 40 hex characters each)”
- larp_checkon 1 other server
“LARP check: is there a real product behind a coin on Robinhood Chain?”
Publisher declares: read-only yes · destructive no · idempotent no · open-world yes
2 inputs, 1 required
tokenstringrequired“The coin: its token contract on Robinhood Chain: 0x followed by 40 hex characters”chainstring“Which chain: rh = Robinhood Chain.”
- dev_recordon 1 other server
“Every coin one wallet launched on Robinhood Chain.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
2 inputs, 1 required
walletstringrequired“The deployer (dev) wallet address: 0x followed by 40 hex characters”chainstring“Which chain: rh = Robinhood Chain (4663).”
- wallet_privacyon 1 other server
“What anyone can learn about a wallet from Robinhood Chain alone: a privacy grade (A to F), a score out of 100, and each leak found (who funded it, linked wallets, holdings, active hours, launches, tr…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
1 input, 1 required
walletstringrequired“The wallet address on Robinhood Chain: 0x followed by 40 hex characters”
- wallet_approvalson 3 other servers
“A wallet's live token approvals on Robinhood Chain: ERC-20 allowances, NFT approval-for-all and Permit2 allowances, newest first (at most 200, with how many more).”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
1 input, 1 required
walletstringrequired“The wallet address on Robinhood Chain: 0x followed by 40 hex characters”
- fresh_launcheson 1 other server
“The newest coins launched on Robinhood Chain, newest first, from Toll's live engine: launchpad, age, pair, and the engine's short notes on each (dev record, first buyers, buyers, curve), with a link …”
Publisher declares: read-only yes · destructive no · idempotent no · open-world yes
1 input
limitinteger“How many coins, 1 to 20 (default 10)”
- chain_pulseon 1 other server
“How busy Robinhood Chain is right now, as Toll's live engine counts it: launches in the last 5 minutes and hour, graduations, launches by launchpad, new pools, trades a minute and volume.”
Publisher declares: read-only yes · destructive no · idempotent no · open-world yes
Takes no inputs.
- launch_recordon 2 other servers
“The call Toll made a few minutes after a Robinhood Chain coin launched, frozen and never edited: against / careful / clear (or launch facts only), the findings tallied, why, the dev's and funder's ot…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
1 input, 1 required
addressstringrequired“The token contract address on Robinhood Chain: 0x followed by 40 hex characters”
- check_agenton 10 other servers
“One ERC-8004 agent registered on Robinhood Chain (identity registry 0x8004A169FB4a3325136EB29fA0ceB6D2e539a432), by its agent id: whether its registration card loads and from which host, its class (r…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
1 input, 1 required
idinteger or stringrequired“The agent id: its ERC-8004 token id in the Robinhood Chain identity registry, a whole number from 0 to 1000000000 (for example 20030)”
- find_paid_apion 4 other servers
“Paid APIs (x402) an agent can buy on Robinhood Chain, by what you need (for example "weather", "stock quotes", "BV-7X", or empty for all): each with its resource URL, price, payTo, whether that payTo…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
2 inputs
querystring“What you want to buy, in a few words (for example "weather" or "stock quotes"); empty lists every operator's best endpoint”limitinteger“How many rows, 1 to 20 (default 10)”
Show 16 more tools
- check_hookon 1 other server
“One Uniswap v4 hook on Robinhood Chain, by its contract address: its name and where the name was read (the contract's own getter, Blockscout or Sourcify), whether it is a launchpad's shared hook, its…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
1 input, 1 required
addressstringrequired“The hook contract's address on Robinhood Chain: 0x followed by 40 hex characters”
- check_txon 3 other servers
“Pre-sign check, before an agent signs anything on Robinhood Chain (chain id 4663): send the transaction (to, data, value, and from), a message to sign (message: {kind: personal_sign | eth_sign, data,…”
Publisher declares: read-only yes · destructive no · idempotent no · open-world yes
19 inputs
chainIdinteger or string“The chain id: 4663 (Robinhood Chain), the only one read; leave it out for 4663”fromstring“The signer's address (0x + 40 hex): a swap paying out to anyone else is flagged”tostring“The transaction's to: the contract or wallet it is sent to (0x + 40 hex)”datastring“The calldata, hex (0x for a plain send)”value“Wei sent with it, decimal or 0x hex (default 0)”authorizationListarray“A type-4 (EIP-7702) transaction's authorizationList, or a signAuthorization alone (no to, no data): [{chainId, address, nonce, yParity, r, s}].”authorization_listarray“The same list under its snake_case name”typedDataobject“An EIP-712 signature request: {domain, types, primaryType, message}.”messageobject“A message to sign: {kind: "personal_sign" | "eth_sign", data (0x hex or text), origin?”originstring“The site or app asking for the signature (https://...), checked against a Sign-In with Ethereum domain”rpcobject“The wallet request as the agent would send it: {method, params}.”userOpobject“An ERC-4337 user operation (v0.6, v0.7 packed or unpacked, v0.8): sender, nonce, callData, gas fields, paymaster, signature.”entryPointstring“The userOp's EntryPoint address (0x + 40 hex); an EntryPoint Toll does not know is a warning”x402object“An x402 payment: the PaymentRequired the 402 sent (with accepts), or one accepts entry; optional payment (the signed payload) and resource (the URL)”agentId“The x402 seller's ERC-8004 agent id, when known”registrystring“The identity registry agentId is in, CAIP-10 (default eip155:4663:0x8004A169FB4a3325136EB29fA0ceB6D2e539a432, Robinhood Chain; Base: eip155:8453:0x8004A169FB4a…”intentobject“Optional: what the agent means to do, compared with what the transaction does in the simulation.”ticketboolean or object“Optional: ask for a single-use ALLOW ticket a contract can require: true, or {consumer?”strictboolean“Strict payee policy: an x402 payment whose payTo is not verified as the seller's (ERC-8478 verified-wallet or verified-delegation) is BLOCK instead of a warnin…”
- presign_risk_reporton 1 other server
“Agent Pre-Sign Risk Report (ERC draft, ethereum/ERCs PR #2134): send a PresignRequest {version: "erc-presign/1", subject: {type: "calls", chainId: "eip155:4663", from: "eip155:4663:0x...", calls: [{t…”
Publisher declares: read-only yes · destructive no · idempotent no · open-world yes
4 inputs, 2 required
versionstringrequired“Always "erc-presign/1"”subjectobjectrequired“{type: "calls", chainId: "eip155:4663", from: "eip155:4663:0x<signer>", calls: [{to, value (wei, decimal string), data}], typedData?, authorizationList?”contextobject“Optional: {payment: {requirements (the x402 accepts entry chosen), resource?, payee?: {registry, agentId}}, texts: [{field, ref?, text}], tokens: [CAIP-10]}”kindsarray“Optional: only these finding kinds”
- stock_tokenon 1 other server
“One Robinhood Stock Token (a tokenized security: debt issued by Robinhood Assets (Jersey) Ltd, not a share) on Robinhood Chain, by its ticker (NVDA, AAPL) or its token contract: Robinhood's listing (…”
Publisher declares: read-only yes · destructive no · idempotent no · open-world yes
1 input, 1 required
idstringrequired“A stock ticker as Robinhood lists it (NVDA, AAPL, BRK.B) or the Stock Token's contract on Robinhood Chain (0x + 40 hex)”
- stock_tokenson 2 other servers
“The Stock Tokens Robinhood lists on Robinhood Chain (about 200): ticker, issuer's name, contract, Chainlink's reference price (or no feed) and its status, with how many have a feed, how many have SEC…”
Publisher declares: read-only yes · destructive no · idempotent no · open-world yes
2 inputs
querystring“Only tokens whose ticker or company contains this (NVDA, nvidia)”limitinteger“How many tokens, 1 to 250 (default 25)”
- fundamentalson 3 other servers
“The company numbers behind one Robinhood Stock Token on Robinhood Chain, from SEC EDGAR XBRL filings, by ticker (AAPL) or token contract: revenue, gross profit, operating income, net income, EPS (dil…”
Publisher declares: read-only yes · destructive no · idempotent no · open-world yes
2 inputs, 1 required
idstringrequired“A stock ticker as Robinhood lists it (AAPL, NVDA, BRK.B) or the Stock Token's contract on Robinhood Chain (0x + 40 hex)”periodstring“ttm (default): the last four quarters; annual: the last 4 fiscal years; quarterly: the last 8 quarters”
- insider_tradeson 12 other servers
“Insider trades at the company behind one Robinhood Stock Token on Robinhood Chain, from SEC Form 4 filings of the last 90 days (the newest 40 at most; the window covered is stated): who (owner and re…”
Publisher declares: read-only yes · destructive no · idempotent no · open-world yes
2 inputs, 1 required
idstringrequired“A stock ticker as Robinhood lists it (AAPL, NVDA, BRK.B) or the Stock Token's contract on Robinhood Chain (0x + 40 hex)”limitinteger“How many trade rows to list, 1 to 100 (default 15)”
- institutionson 1 other server
“Institutional holders of the company behind one Robinhood Stock Token on Robinhood Chain, from SEC's quarterly Form 13F data sets, by ticker (NVDA) or token contract: the top investment managers by s…”
Publisher declares: read-only yes · destructive no · idempotent no · open-world yes
2 inputs, 1 required
idstringrequired“A stock ticker as Robinhood lists it (AAPL, NVDA, BRK.B) or the Stock Token's contract on Robinhood Chain (0x + 40 hex)”limitinteger“How many holders to list, 1 to 20 (default 10)”
- guidanceon 1 other server
“What the company behind one Robinhood Stock Token on Robinhood Chain said in its last 4 earnings releases (SEC 8-K Item 2.02, the press release exhibit), by ticker (NVDA) or token contract, AI-extrac…”
Publisher declares: read-only yes · destructive no · idempotent no · open-world yes
2 inputs, 1 required
idstringrequired“A stock ticker as Robinhood lists it (AAPL, NVDA, BRK.B) or the Stock Token's contract on Robinhood Chain (0x + 40 hex)”limitinteger“How many values to list per release, 1 to 60 (default 25)”
- macroon 5 other servers
“US macro figures for agents reading Robinhood Stock Tokens on Robinhood Chain, from public primary sources, each with its date: the Treasury daily par yield curve (1 month to 30 years), the New York …”
Publisher declares: read-only yes · destructive no · idempotent no · open-world yes
Takes no inputs.
- stock_eventson 1 other server
“What changed on Robinhood's Stock Tokens on Robinhood Chain, oldest first: listed / delisted, multiplier_scheduled / multiplier_applied, corporate_action (status changes), feed_stale / feed_paused / …”
Publisher declares: read-only yes · destructive no · idempotent no · open-world yes
3 inputs
sinceinteger“The next of the last answer (an event id): only newer events.”kindstring“Only this kind: listed, delisted, multiplier_scheduled, multiplier_applied, corporate_action, feed_stale, feed_paused, feed_resumed, filing”limitinteger“How many events, 1 to 100 (default 25; the keyless preview is always the last 10)”
- watch_coinon 1 other server
“Watch one Robinhood Chain coin for your agent: Toll re-reads it about every 10 minutes, and sooner after a trade or liquidity change (with more watched coins it takes longer), and POSTs a signed JSON…”
Publisher declares: read-only no · destructive no · idempotent yes · open-world yes
2 inputs, 2 required
addressstringrequired“The token contract address to watch on Robinhood Chain: 0x followed by 40 hex characters”urlstringrequired“Your webhook: a public https URL on the default port”
- my_watcheson 2 other servers
“The coins and the wallets your Toll key's wallet watches on Robinhood Chain: for each watch its id, token or address, url, paused (after 5 failed deliveries), fails, last read; never the secret.”
Publisher declares: read-only yes · destructive no · idempotent no · open-world yes
Takes no inputs.
- unwatch_coinon 1 other server
“Remove one of your coin watches on Robinhood Chain by its id (from my_watches).”
Publisher declares: read-only no · destructive yes · idempotent yes · open-world no
1 input, 1 required
idstringrequired“The watch id (a uuid) from my_watches”
- watch_walleton 3 other servers
“Watch one Robinhood Chain wallet for your agent (its own wallet, or one it trades with): Toll POSTs a signed JSON event to your https url when the wallet gives a new token approval (ERC-20, NFT appro…”
Publisher declares: read-only no · destructive no · idempotent yes · open-world yes
2 inputs, 2 required
addressstringrequired“The wallet address to watch on Robinhood Chain: 0x followed by 40 hex characters”urlstringrequired“Your webhook: a public https URL on the default port”
- unwatch_walleton 2 other servers
“Remove one of your wallet watches on Robinhood Chain by its id (from my_watches).”
Publisher declares: read-only no · destructive yes · idempotent yes · open-world no
1 input, 1 required
idstringrequired“The wallet watch id (a uuid) from my_watches”
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 2026-11-12.
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
- 100% of 59
- Tools with a description
- 100% of 28
- Typical description length
- 675 characters
The tool set
Counted from the listing
- Tools
- 28
- Size of the list
- about 10,019 tokens for an agent to load (characters ÷ 4)
- Naming
- 24 of 28 names use snake_case
AI reading: easy to mix up
No pair found.
The AI items cover 0 of 28 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 @tollxyz/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": {
"toll": {
"command": "npx",
"args": [
"-y",
"@tollxyz/mcp@0.6.1"
]
}
}
}Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json
{
"mcpServers": {
"toll": {
"command": "npx",
"args": [
"-y",
"@tollxyz/mcp@0.6.1"
]
}
}
}VS Code · .vscode/mcp.json
{
"servers": {
"toll": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@tollxyz/mcp@0.6.1"
]
}
}
}VS Code (command line) · Bash or zsh terminal (macOS, Linux)
code --add-mcp '{"name":"toll","type":"stdio","command":"npx","args":["-y","@tollxyz/mcp@0.6.1"]}'Claude Code
claude mcp add --transport stdio toll -- npx -y @tollxyz/mcp@0.6.1
Cline · cline_mcp_settings.json (Cline CLI: ~/.cline/data/settings/; in the editor: MCP Servers → Configure → Configure MCP Servers)
{
"mcpServers": {
"toll": {
"command": "npx",
"args": [
"-y",
"@tollxyz/mcp@0.6.1"
],
"disabled": false,
"autoApprove": []
}
}
}Gemini CLI · ~/.gemini/settings.json, or .gemini/settings.json in a project
{
"mcpServers": {
"toll": {
"command": "npx",
"args": [
"-y",
"@tollxyz/mcp@0.6.1"
]
}
}
}OpenAI Codex · ~/.codex/config.toml, or .codex/config.toml in a trusted project
[mcp_servers.toll] command = "npx" args = ["-y", "@tollxyz/mcp@0.6.1"]
Zed · Zed settings file (command: zed: open settings file)
{
"context_servers": {
"toll": {
"command": "npx",
"args": [
"-y",
"@tollxyz/mcp@0.6.1"
]
}
}
}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 @tollxyz/mcp@0.6.1
- Optional settings the entry also lists (left out above): TOLL_BASE_URL.
- 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 2026-11-12 (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://t0ll.xyz/mcp
Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json
{
"mcpServers": {
"toll": {
"url": "https://t0ll.xyz/mcp"
}
}
}VS Code · .vscode/mcp.json
{
"servers": {
"toll": {
"type": "http",
"url": "https://t0ll.xyz/mcp"
}
}
}VS Code (command line) · Bash or zsh terminal (macOS, Linux)
code --add-mcp '{"name":"toll","type":"http","url":"https://t0ll.xyz/mcp"}'Claude Code
claude mcp add --transport http toll https://t0ll.xyz/mcp
Cline · cline_mcp_settings.json (Cline CLI: ~/.cline/data/settings/; in the editor: MCP Servers → Configure → Configure MCP Servers)
{
"mcpServers": {
"toll": {
"type": "streamableHttp",
"url": "https://t0ll.xyz/mcp",
"disabled": false,
"autoApprove": []
}
}
}Gemini CLI · ~/.gemini/settings.json, or .gemini/settings.json in a project
{
"mcpServers": {
"toll": {
"httpUrl": "https://t0ll.xyz/mcp"
}
}
}OpenAI Codex · ~/.codex/config.toml, or .codex/config.toml in a trusted project
[mcp_servers.toll] url = "https://t0ll.xyz/mcp"
Zed · Zed settings file (command: zed: open settings file)
{
"context_servers": {
"toll": {
"url": "https://t0ll.xyz/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://t0ll.xyz/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
- 0.6.1
- Latest stable
- 0.6.1
- Status
- current
- Withdrawn
- no
Source: registry.npmjs.org · 2026-11-12. About the version the registry lists; a manual install may resolve to a different one.
Dependency advisories
Counted in the full dependency tree as resolved on 2026-11-12 (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
- sha512-4q0LkiNL8DxY1H+aI…
- Signature
- signed
- License
- MIT
Source: the package registry · 2026-11-12.
Usage
- Downloads
- 2,915 in the last month
Source: api.npmjs.org · 2026-11-12.
What do the published files and outside lists say?
Read as text · nothing run · no tool called
Package files
- Install-time script (npm). No install-time script in the published package.json (version 0.6.1). Source: read 2026-11-12.
- Operating systems and processors (npm). The npm package sets no os or cpu limit (package.json). Source: read 2026-11-12.
- Node.js version (npm). Needs Node 20 or later (engines.node
>=20.19). Source: read 2026-11-12. - MCP SDK in the package files. Lists
@modelcontextprotocol/sdkas a dependency (package.json). Source: read 2026-11-12. - Build workflow. No build provenance published for this version. Source: read 2026-11-12.
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 2026-11-12.
Outside lists
- CVE records (NVD). No CVE record in the NVD feeds we read links this server's repository. Source: read 2026-11-12. 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 2026-11-12. GitHub Advisory Database, CC BY 4.0
- Docker MCP catalogue. Not in the Docker MCP catalogue on 2026-11-12. Source: read 2026-11-12.
- Cline marketplace. Not in the Cline marketplace on 2026-11-12. Source: read 2026-11-12.
Own host
- security.txt. No security.txt at https://t0ll.xyz/.well-known/ (HTTP 404, 2026-11-12). Source: t0ll.xyz/.well-known/security.txt · read 2026-11-12.
- A2A agent card. An A2A agent card is published at https://t0ll.xyz/.well-known/agent-card.json (name, skills, url). Source: t0ll.xyz/.well-known/agent-card.json · read 2026-11-12.
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 #6The 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 says | We found | Result | Source · date |
|---|---|---|---|
| Remote endpoint t0ll.xyz/mcp | Session opened | matches | our test · 2026-11-12 |
| No credential declared as required | Opened a session without any credential | matches | our test · 2026-11-12 |
| Version 0.6.1 on npm | Exists and can be installed | matches | npm · 2026-11-12 |
| Repository github.com/t0ll-xyz/toll-plugins | Opens publicly | matches | api.github.com · 2026-11-12 |
Who made it?
Feature #7 · lineage
Facts about the publisher. We do not turn them into a trust score.
- Namespace
- io.github.t0ll-xyz
- GitHub owner
- an organization (t0ll-xyz)
- Build record
- signed
- Repository
- github.com/t0ll-xyz/toll-plugins
- 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 · 2026-11-12; 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 calledHosted endpoint t0ll.xyz/mcp
3 of 3 comparisons between consecutive reads showed a change (4 reads, 2026-11-07 to 2026-11-12; versions 0.4.0 to 0.6.1).
Last change seen between our reads on 2026-11-09 (version 0.5.0) and 2026-11-12 (version 0.6.1).
Added (1):
find_paid_apiChanged (1):
check_tx: descriptionCompared 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 2026-11-12 is not known yet. No tool was called. How it is compared
Choosing
Record checks
Public records · not a safety rating7 of 9 record checks met
- #1,140 of 20,610 packages by monthly downloads
- 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
- MetNo known critical or high advisory in the package or its dependenciesNone known in the package or its dependency tree.
Read from public records only: the registry entry, npm/PyPI, GitHub and advisory databases, checked 2026-11-12 (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 io.github.t0ll-xyz/toll
Answered from the data aboveWho publishes io.github.t0ll-xyz/toll?
The registry ties the namespace io.github.t0ll-xyz to the GitHub account t0ll-xyz; only its owner can publish under it. Its linked repository, github.com/t0ll-xyz/toll-plugins, belongs to the same GitHub account. These are facts from the registry and GitHub, not a rating.
Is io.github.t0ll-xyz/toll safe to install?
We do not rate servers as safe or unsafe. 7 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 no known advisory. These are facts with their sources on this page, not a safety guarantee, and we did not run its tools.
Does io.github.t0ll-xyz/toll need an API key or sign-in?
It opened a session without any credential on 2026-11-12. The registry entry declares no required credential; no declaration is not a guarantee.
Has io.github.t0ll-xyz/toll 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. ProtocolProbe publishes no security verdict for a named server.
Does io.github.t0ll-xyz/toll 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 0.6.1, the latest stable release on npm.
Where is the source code of io.github.t0ll-xyz/toll?
In github.com/t0ll-xyz/toll-plugins, 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.
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. These 18 checks are separate from the record checks at the top of this page, which read public records only.
- 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, 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-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, 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-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, 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-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, 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
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, 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-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, 2026-11-12, 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
- 850 msConnected after 0 redirects. No credential was sent or needed.
- Read the inventory: 28 tools, 0 resources, 0 prompts.
- 3,946 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.
“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.t0ll-xyz/toll: MCP server record.” Data checked 2026-11-12. https://protocolprobe.com/mcp/servers/io.github.t0ll-xyz/toll
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.t0ll-xyz/toll)
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