Chain Data for Agents (x402) MCP server
io.github.zuo305/chain-data-agentzuo305streamable-httpv0.2.0Scanned
Solana validator stats and the SOL stake unlock calendar for agents. Pay per call via x402.
7 tools: 2 do something that can't be undone, 2 change things and 3 only read.
- Reads private data · 0
- Reads text others write · 0
- Can send data out · 2
- 4 findings
Tools listed without sign-in. Remote posture
With Anlyon
2 tools here do something that can't be undone. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the Chain Data for Agents (x402) MCP server can do
The Chain Data for Agents (x402) MCP server is published by the GitHub account zuo305. It has 7 tools. It can do things that cannot be undone, such as sending, paying or publishing (solana_unlocks_get_unlock_calendar and solana_unlocks_list_unlocks) and create or change data (2 tools: solana_unlocks_get_unlock_summary and request_data), but cannot delete data. 3 tools only read.
2 tools can send data out of your system (solana_unlocks_get_unlock_calendar and solana_unlocks_list_unlocks).
The fixed checks matched 4 findings (base64-blob and annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 16, 2026, version 0.2.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
7 tools
Can't be undone 2Claude Code: ask
solana_unlocks_get_unlock_calendarGet the SOL unlock schedule by day, week or month for a date range.Can send data out1 finding
Why it is in this group
- The name "solana_unlocks_get_unlock_calendar" says "unlock": a word for a change.
- The input addresses people (input.to): what it sends cannot be taken back.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- outboundThe input takes a destination (input.to): what the tool writes goes there.
Findings
- Warn
The server marks "solana_unlocks_get_unlock_calendar" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "solana_unlocks_get_unlock_calendar" says "unlock": a word for a change.
Description, as the server wrote it Get the SOL unlock schedule by day, week or month for a date range. Dates from and to are YYYY-MM-DD, inclusive (default today and 90 days on, span up to 1,500 days). The group parameter is day (default), week (starting Monday) or month. Each period gives the SOL whose stake lockup ends then, the number of stake accounts, the delegated part (needs about one epoch to deactivate before withdrawal) and the largest single account. Periods with nothing unlocking are left out. Costs $0.002 per call, paid via x402 in USDC on Base; the first 3 paid-tool calls per day are free for MCP clients while a shared daily allowance lasts. Without x402 support, later calls return the payment requirements as an error result. Failed calls are not charged. Source: Solana mainnet-beta (stake account lockups via JSON-RPC), Public on-chain data.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- title: Get the SOL unlock schedule by day, week or month for a date range.
solana_unlocks_list_unlocksList individual SOL stake account unlocks in a date range, largest first within each time.Can send data out1 finding
Why it is in this group
- The name "solana_unlocks_list_unlocks" says "unlock": a word for a change.
- The input addresses people (input.to): what it sends cannot be taken back.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- outboundThe input takes a destination (input.to): what the tool writes goes there.
Findings
- Warn
The server marks "solana_unlocks_list_unlocks" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "solana_unlocks_list_unlocks" says "unlock": a word for a change.
Description, as the server wrote it List individual SOL stake account unlocks in a date range, largest first within each time. Dates from and to are YYYY-MM-DD, inclusive (default today and 30 days on). Filters: min_sol, withdraw_authority (whose SOL it is) and custodian (who can lift the lockup). Each row gives the stake account, SOL, unlock time, withdraw authority, custodian and the vote account it is delegated to (null if not delegated). Returns up to limit rows (default 50, max 200) and the matched count and SOL. Costs $0.002 per call, paid via x402 in USDC on Base; the first 3 paid-tool calls per day are free for MCP clients while a shared daily allowance lasts. Without x402 support, later calls return the payment requirements as an error result. Failed calls are not charged. Source: Solana mainnet-beta (stake account lockups via JSON-RPC), Public on-chain data.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- title: List individual SOL stake account unlocks in a date range, largest first within each time.
Changes things 2Claude Code: ask
request_dataRequest data that these tools do not provide yet (another chain, a dataset, a field or a filter), so the maintainers can consider it for a future release.No findings
Why it is in this group
- The name "request_data" says "request": a word for a change.
Description, as the server wrote it Request data that these tools do not provide yet (another chain, a dataset, a field or a filter), so the maintainers can consider it for a future release. Free. Describe the data and, optionally, the task it is for. Do not include personal information. Requests are stored anonymously and read by the maintainers; the result is only a confirmation.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
- title: Request data that is not covered yet
solana_unlocks_get_unlock_summaryGet how much SOL is still locked in stake account lockups and how much unlocks soon.1 finding
Why it is in this group
- The name "solana_unlocks_get_unlock_summary" says "unlock": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "solana_unlocks_get_unlock_summary" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "solana_unlocks_get_unlock_summary" says "unlock": a word for a change.
Description, as the server wrote it Get how much SOL is still locked in stake account lockups and how much unlocks soon. Returns the locked SOL total (and the delegated part), the next unlock day, the SOL unlocking in the next 7, 30, 90 and 365 days, and the last unlock date. Use solana_unlocks_get_unlock_calendar for the schedule. Free, no payment needed. Source: Solana mainnet-beta (stake account lockups via JSON-RPC), Public on-chain data.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- title: Get how much SOL is still locked in stake account lockups and how much unlocks soon.
Only reads 3Show 3 read-only tools
solana_validators_get_network_summaryGet live Solana network health: epoch progress, validator counts, stake concentration and skip rate.No findings
Why it is in this group
- The name "solana_validators_get_network_summary" says "get": a word for reading.
Description, as the server wrote it Get live Solana network health: epoch progress, validator counts, stake concentration and skip rate. Returns the current epoch and its progress, active and delinquent validator counts, total active stake in SOL, the delinquent stake share, the Nakamoto coefficient (fewest validators holding over a third of stake), median commission, cluster block production and skip rate so far this epoch, and median and best vote credits per SOL staked in the last complete epoch. Use it as the baseline when judging a single validator. Free, no payment needed. Source: Solana mainnet-beta (public chain state via JSON-RPC), Public on-chain data.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- title: Get live Solana network health: epoch progress, validator counts, stake concentration and skip rate.
solana_validators_get_validatorGet live stats for one Solana validator by vote account or identity pubkey.1 finding
Why it is in this group
- The name "solana_validators_get_validator" says "get": a word for reading.
Findings
- Warn
The input schema at properties.vote.description contains a 44-character base64 string.
What this check looks forMatched text
inputSchema.properties.vote.description: "...bkey (base58) (e.g. JDMq8hxZnad2smKLGkFbfg8zVMZHKQcMugD4tMR9u2da)"
Description, as the server wrote it Get live stats for one Solana validator by vote account or identity pubkey. Pass vote (vote account pubkey) or identity (node identity pubkey). Returns stake in SOL with share and rank, commission, delinquency, how many slots its last vote is behind the cluster, vote credits for each of the last 5 epochs per SOL staked, as a percentage of the cluster median (100 = median; approximate, as it uses today's stake), and current-epoch leader slots, blocks produced and skip rate next to the cluster's. Unknown keys return 404. Costs $0.001 per call, paid via x402 in USDC on Base; the first 3 paid-tool calls per day are free for MCP clients while a shared daily allowance lasts. Without x402 support, later calls return the payment requirements as an error result. Failed calls are not charged. Source: Solana mainnet-beta (public chain state via JSON-RPC), Public on-chain data.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- title: Get live stats for one Solana validator by vote account or identity pubkey.
solana_validators_list_validatorsList Solana validators ranked by stake, vote credits, skip rate or commission, with filters.No findings
Why it is in this group
- The name "solana_validators_list_validators" says "list": a word for reading.
Description, as the server wrote it List Solana validators ranked by stake, vote credits, skip rate or commission, with filters. For choosing where to stake or comparing validators. sort is stake (default), credits (vote credits per SOL in the last complete epoch, as % of the cluster median), skip_rate (current epoch, lowest first; validators with no leader slots yet come last) or commission (lowest first). Filters: max_commission (percent), min_stake_sol, include_delinquent (default false). Returns up to limit rows (default 20, max 50) and the number matched. Costs $0.002 per call, paid via x402 in USDC on Base; the first 3 paid-tool calls per day are free for MCP clients while a shared daily allowance lasts. Without x402 support, later calls return the payment requirements as an error result. Failed calls are not charged. Source: Solana mainnet-beta (public chain state via JSON-RPC), Public on-chain data.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- title: List Solana validators ranked by stake, vote credits, skip rate or commission, with filters.
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or untrusted-input.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write0
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out2
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 21, 2026, 19:21 UTC, unchanged since Nov 21, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 4
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 4 tools that change things (2 irreversible, 2 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://chain-data-agent.wangzuo305.workers.dev/mcp: tools/list returned 7 tools to an anonymous client, including solana_unlocks_get_unlock_calendar (irreversible), solana_unlocks_list_unlocks (irreversible), solana_unlocks_get_unlock_summary (write), request_data (write)
Posture changes
- Nov 21, 2026
- Tools that change things, listed without credentials: 1 to 4
Findings
Matches of fixed checks, with the text they matched.
The input schema at properties.vote.description contains a 44-character base64 string.
What this check looks forMatched text
inputSchema.properties.vote.description: "...bkey (base58) (e.g. JDMq8hxZnad2smKLGkFbfg8zVMZHKQcMugD4tMR9u2da)"
The server marks "solana_unlocks_get_unlock_summary" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "solana_unlocks_get_unlock_summary" says "unlock": a word for a change.
The server marks "solana_unlocks_get_unlock_calendar" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "solana_unlocks_get_unlock_calendar" says "unlock": a word for a change.
The server marks "solana_unlocks_list_unlocks" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "solana_unlocks_list_unlocks" says "unlock": a word for a change.
History
Changes to its tool definitions and to its remote endpoint, newest first.
PostureRemote posture changed. Tools that change things, listed without credentials: 1 -> 4.View diff
- Tools that change things, listed without credentials: 1 to 4
Tools3 added, 1 changed.+3 added~1 changedView diff
- Added:solana_unlocks_get_unlock_calendarCan't be undone
- Added:solana_unlocks_get_unlock_summaryChanges things
- Added:solana_unlocks_list_unlocksCan't be undone
- Changed:request_dataChanges thingsinputSchema
Install
Pinned to version 0.2.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http chain-data-agent https://chain-data-agent.wangzuo305.workers.dev/mcpclaude mcp add --transport http chain-data-agent https://chain-data-agent.wangzuo305.workers.dev/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__chain-data-agent__solana_validators_get_network_summary",
"mcp__chain-data-agent__solana_validators_get_validator",
"mcp__chain-data-agent__solana_validators_list_validators"
],
"ask": [
"mcp__chain-data-agent__solana_unlocks_get_unlock_summary",
"mcp__chain-data-agent__solana_unlocks_get_unlock_calendar",
"mcp__chain-data-agent__solana_unlocks_list_unlocks",
"mcp__chain-data-agent__request_data"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as chain-data-agent. Review it before you use it.
Capability tags behind 2 rules
- mcp__chain-data-agent__solana_unlocks_get_unlock_calendar outbound
- mcp__chain-data-agent__solana_unlocks_list_unlocks outbound
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/io.github.zuo305/chain-data-agent/verify?hash=bd1379f53dfdf2899ea1c6b209e496d2250c5030dd5ef738cdbe8b4e81bc00c4" | jq -e '.changed == false'Pinned hash bd1379f53dfd, from Nov 16, 2026, 00:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.zuo305/chain-data-agent/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.zuo305/chain-data-agent)Source: MCP Registry. Synced Nov 16, 2026, 00:18 UTC.
Chain Data for Agents (x402) MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Chain Data for Agents (x402) MCP server safe?
- No scan can promise that. What its definitions show: 7 tools, 4 of which can change, send or delete something, and 4 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the Chain Data for Agents (x402) MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Chain Data for Agents (x402) MCP server do things that cannot be undone?
- Yes. 2 tools can send, pay, publish or merge: solana_unlocks_get_unlock_calendar and solana_unlocks_list_unlocks.
What tools does the Chain Data for Agents (x402) MCP server have?
- 7 tools: 2 irreversible, 2 write, 3 read. solana_unlocks_get_unlock_calendar, solana_unlocks_list_unlocks, solana_unlocks_get_unlock_summary, request_data, solana_validators_get_network_summary, solana_validators_get_validator and solana_validators_list_validators.
Does the Chain Data for Agents (x402) MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Chain Data for Agents (x402) MCP server send data to outside services?
- 2 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): solana_unlocks_get_unlock_calendar and solana_unlocks_list_unlocks.
Has the Chain Data for Agents (x402) MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 16, 2026. Every change is on this page and in its Atom feed.