
Xroot MCP server
Which servers in the official MCP registry are Xroot's own, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-10-26
- Registry namedev.xroot/token-operationsverified in the MCP registry
The registry name sits under xroot.dev. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-26
- Tools18
- Server calls itselfxroot.dev
- Server version1.1.0
- Protocol version2025-06-18
On 2026-10-26 the server answered initialize and tools/list without a sign-in. First answer in 698 ms.
- Whether its tools do the product's job has not been judged yet.
- Checked on 1 of the 7 days it takes to judge reliability.
Once connected
- For "audit a token for mint or freeze authority", the likely first call is audit_token.
Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.
- INITE MCP scoreafter a weeka score needs 7 daily checks: 1 so far
- Answeredmeasuring1 of the 7 daily checks it takes to print a share
- Median first answer719 ms
- Space in an agent's context≈ 3,284 tokensthe definitions of all its tools (18), which an agent carries on every turn
- Tool definitionsA · 100 of 100
- Typed results0 of 18 toolsdeclared outputSchema: results come typed, read once
- Every tool passes all six checks.
What an agent can do with it
- not sure · read a wallet's holdings from its address alone
- can do · audit a token for mint or freeze authority
- not sure · reclaim SOL from empty Solana token accounts
Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?
Worth a look
None of the five warning signs in these definitions.
A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (30%), doing the product's job (25%), definitions (20%), context (10%) and use (15%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →
check_walletRead everything a wallet can get back, in one call: on Solana, the rent in empty token accounts, the surplus the rent cut left, wrapped SOL, failed-deploy buffers, closable programs, lookup tables, dead Meteora positions, subscriptions…
check_reclaimable_rentRead how much SOL a Solana wallet can reclaim from rent: the deposits parked in its empty token accounts, and the surplus the rent cut left in accounts it still uses. Returns counts and net figures in SOL. Nothing is closed or moved.
check_wrapped_solRead the wrapped SOL (wSOL) sitting in a Solana wallet's token accounts, and what unwrapping it back to SOL returns net of fees. Nothing is unwrapped.
check_token_delegatesList the standing token delegates and approvals on a Solana wallet — programs still allowed to move its tokens. A risk read, not money: revoking returns no SOL. Nothing is revoked.
check_failed_deploysRead the program buffer accounts left behind by a Solana wallet's failed or interrupted program deploys, and the SOL recovering them returns net of fees. Nothing is recovered.
check_closable_programsRead the upgradeable programs a Solana wallet holds the upgrade authority for, and the gross rent their bytecode accounts hold. Closing a program is permanent, so this reads only.
check_lookup_tablesRead the address lookup tables a Solana wallet owns: how many are ready to close, cooling down, or still active, and the gross rent each group holds. Nothing is deactivated or closed.
check_lp_feesCount a Solana wallet's liquidity positions with trading fees waiting to be claimed, per venue: Orca Whirlpools, Meteora, and locked Raydium liquidity. Fees are owed in many different tokens, so the answer is a count of positions, never a…
check_dlmm_positionsRead a Solana wallet's Meteora DLMM and DAMM v2 positions by status, how many can be closed now, and the gross SOL deposit those closable positions hold — what closing them returns before fees. Nothing is closed.
check_subscriptionsRead the on-chain subscriptions and recurring allowances a Solana wallet has granted, by state, plus the rent their accounts would return to this wallet (a sponsored subscription's rent goes back to its sponsor). Nothing is cancelled.
check_token_taxList the transfer-tax tokens a Solana wallet launched through the platform, with each tax rate — the tokens whose withheld tax that wallet can collect. Nothing is collected.
check_frozen_tokensRead the permissioned (Token ACL) tokens a Solana wallet holds, and which of them the holder can unlock itself under the token's published rules. Nothing is unlocked.
audit_tokenRun the free risk report on a token: who can still mint or freeze, transfer taxes and hooks, permanent delegates, liquidity status, holder concentration, and a verdict with a score. On Solana pass the mint address; on an EVM chain pass…
check_token_unlocksRead a Solana token's on-chain locks: supply vesting and locked liquidity, per locker, with the cliff, start, period and released amounts each lock reports. Use it when a user asks when a token unlocks or whether its liquidity is locked…
search_tokensFind a token by name, symbol or address in the xroot.dev token directory — the trending and newest tokens the platform has indexed on an EVM chain — with each token's pool, price and cached audit verdict where one exists. Use it to…
list_upgradesList Solana's protocol upgrades (feature gates) with their state on mainnet, testnet and devnet — pending with an activation estimate, active with its activation epoch, or not yet queued — as read from the chain. Use it when a user asks…
check_approvalsList the standing token approvals on an EVM wallet — contracts still allowed to move its tokens — ranked by risk, with unlimited allowances, expired permits and flagged spenders called out. A risk read, not money: revoking returns…
get_fee_estimateQuote the exact cost of a token operation before anything is built: the platform fee for that service on that chain plus the estimated network fee (rent, base and priority), as decimal strings in the chain's currency. Use it when a user…
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"token-operations": {
"type": "http",
"url": "https://api.xroot.dev/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http xroot https://api.xroot.dev/mcpclaude.ai, ChatGPT and other clients: add https://api.xroot.dev/mcp as a custom connector in the settings.
Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.
Cookies
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.