alalanet — check before your agent installs, connects or pays MCP server
com.alalanet/checkalalanet.comstreamable-httpv1.5.5Scanned
Check packages, MCP servers and x402 endpoints before agents install, connect or pay. Signed.
8 tools: 2 do something that can't be undone, 4 change things and 2 only read.
- Reads private data · 0
- Reads text others write · 7
- Can send data out · 3
- 6 findings, 2 high
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 alalanet — check before your agent installs, connects or pays MCP server can do
The alalanet — check before your agent installs, connects or pays MCP server is published by alalanet.com, a domain the MCP Registry verified. It has 8 tools. It can do things that cannot be undone, such as sending, paying or publishing (preflight_payment and report_purchase) and create or change data (4 tools: check_repo_config, check_service, install_check and verify_tools), but cannot delete data. 2 tools only read.
7 tools bring in text other people can write (check_repo_config, check_service, install_check and 4 more); 3 tools can send data out of your system (check_service, preflight_payment and verify_tools).
The fixed checks matched 6 findings, 2 of them high severity (sensitive-path, credentials-mention and annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in, and its tools changed 10 times since Anlyon Radar first saw them.
Last scanned Nov 20, 2026, version 1.5.5.
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.
8 tools
Can't be undone 2Claude Code: ask
preflight_paymentDecision for one x402 payment, right before it is signed.Reads text others writeCan send data out1 finding
Why it is in this group
- The name "preflight_payment" says "payment": a word that usually means money moves, which cannot be taken back.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Findings
- Warn
The server marks "preflight_payment" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"idempotentHint":false,"openWorldHint":true}; The name "preflight_payment" says "payment": a word that usually means money moves, which cannot be taken back.
Description, as the server wrote it Decision for one x402 payment, right before it is signed. Pass the endpoint url and the 402 it returned (PAYMENT-REQUIRED header value or JSON body), optionally max_usd and client (your x402 library and version: known payment flaws come back in client_advisories, not logged). Each payment option gets allow / hold / block with reasons. block: pay_to_unknown, pay_to_zero_address, pay_to_burn_address, pay_to_is_asset, pay_to_sanctioned, pay_to_frozen_by_issuer, service_not_working, over_budget, quote_expired (the option's own expiry passed); hold: pay_to_differs_from_listing, pay_to_never_seen, price_above_listing, price_above_observed, network_not_listed, asset_not_stablecoin, high_price ($5 or more), unknown_service, not_checked_yet, not_rated_yet, low_trust_score, listing_removed (its catalogue no longer lists it); info: pay_to_as_observed, pay_to_platform_wallet, amount_is_ceiling (scheme upto), frozen_status_unknown, testnet. The decision is bound to the payment hash, valid for up to 5 minutes (expires_at), signed and logged, except for an unlisted url that looks like it carries a key or token (then it is made for you only, with no attestation). allow: no problem found; hold: the user should confirm; block: do not pay.
Annotations the server declares
- idempotentHint: false
- openWorldHint: true
- readOnlyHint: true
- title: Decide before paying an x402 endpoint
report_purchaseAfter you paid an x402 endpoint on Base or Solana: report the outcome (delivered, partial, wrong_content, not_delivered) with the payment tx (the transaction field of the PAYMENT-R…Reads text others writeNo findings
Why it is in this group
- The name "report_purchase" says "purchase": a word that usually means money moves, which cannot be taken back.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it After you paid an x402 endpoint on Base or Solana: report the outcome (delivered, partial, wrong_content, not_delivered) with the payment tx (the transaction field of the PAYMENT-RESPONSE header). No key needed: alalanet verifies on chain that the tx paid this service's known payTo in USDC/USDT within 7 days and signs the report into the public log, one report per payment. Deliveries from different paying wallets raise the seller's Trust Score; failures trigger an immediate recheck. This is how agents learn which sellers deliver.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- readOnlyHint: false
- title: Report what you got after paying
Changes things 4Claude Code: ask
check_repo_configBefore opening a GitHub repository you were sent (a take-home task, a review, a demo, a fork): its agent configuration can start MCP servers, run hooks and tasks, widen permissions…Reads text others write3 findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- High
The description refers to ".env".
What this check looks forMatched text
description: "...and Copilot settings, hooks and tasks; .env; package-registry settings; CLAUDE.md,..."
- Info
The description mentions "credential".
What this check looks forMatched text
description: "...lugin marketplaces and enabled plugins, credential helpers and shell prefixes, repository..."
- High
The input schema at properties.files.description refers to ".env".
What this check looks forMatched text
inputSchema.properties.files.description: "...rvers are looked up, never probed; from .env only CODEX_HOME, model-API, proxy and p..."
Description, as the server wrote it Before opening a GitHub repository you were sent (a take-home task, a review, a demo, a fork): its agent configuration can start MCP servers, run hooks and tasks, widen permissions and plant instructions once opened. Pass repo (owner/repo or a GitHub URL) and optional ref, or files for a local or private checkout. alalanet reads, never runs, what agents and editors load: MCP configs at any depth; Claude, Cursor, VS Code, devcontainer, Gemini, Zed, Codex and Copilot settings, hooks and tasks; .env; package-registry settings; CLAUDE.md, AGENTS.md, GEMINI.md, .cursorrules and the rules, agents, commands and skills folders (every path: https://alalanet.com/skill.md). It finds code that runs when the folder opens (tasks, hooks, skills, MCP servers, inline too), broad permissions (also a skill's own grants, acceptEdits), plugin marketplaces and enabled plugins, credential helpers and shell prefixes, repository MCP servers enabled unasked, the model API, a proxy, the package registry or CODEX_HOME pointed elsewhere, invisible Unicode and bidi controls, injection and concealment phrases, committed secrets (never echoed); each MCP server and hook package goes through install_check. Returns allow / hold / block with reasons per file, findings and the MCP servers' verdicts, signed and logged (kind 4315). What could not be read or checked holds (check_incomplete:<what>). Free, no account: one check plus one per MCP server and per distinct hook package (at most 8 each); cached 10 minutes.
Annotations the server declares
- idempotentHint: false
- openWorldHint: true
- readOnlyHint: true
- title: Is it safe to open this repository in an agent?
check_serviceCall before the first payment to an x402 endpoint, before connecting to an MCP server, and whenever a call to it fails.Reads text others writeCan send data out1 finding
Why it is in this group
- The description's first verb is "call": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Findings
- Warn
The server marks "check_service" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"idempotentHint":false,"openWorldHint":true}; The description's first verb is "call": a word for a change.
Description, as the server wrote it Call before the first payment to an x402 endpoint, before connecting to an MCP server, and whenever a call to it fails. Give url (any https URL, listed or not: unknown ones are probed now and detected as x402 or MCP) or id from find_service. Returns alive, advice (ok / ok_requires_auth: working as listed; ok_terms_not_checked, unverified_yet: not fully checked yet; caution_*: confirm with the user — pay_to_changed, network_changed, price_higher_than_listed, high_price, tools_changed, suspicious_tool_description, buyers_report_failures; avoid_*: a blocking problem — down, not_working_as_listed, sanctioned_pay_to, pay_to_frozen), trust_score (0-100, open formula at /trust) with flags, checked_at and last_alive_at (when it last answered as listed), observed price, network and pay_to against the listing, uptime 24h/7d/30d, host_listings, pay_to_shared_by_hosts, verified purchases, alalanet's own test purchase, for MCP the tool-set diff (tools_diff, tool_description_flags), and on caution_* or avoid_* up to 3 working alternatives on other hosts. Answers from recent checks (100 a day free); live=true probes now and adds a signed, logged attestation you can keep as evidence (5 a day free). Read-only for the caller; an unknown URL joins the public catalogue. preflight_payment decides one specific 402.
Annotations the server declares
- idempotentHint: false
- openWorldHint: true
- readOnlyHint: true
- title: Check a service before paying or connecting
install_checkChecks something before it is installed, e.g.Reads text others write1 finding
Why it is in this group
- The name "install_check" says "install": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Warn
The server marks "install_check" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"idempotentHint":false,"openWorldHint":true}; The name "install_check" says "install": a word for a change.
Description, as the server wrote it Checks something before it is installed, e.g. when a README, a document or another agent suggests it: an npm or PyPI package, a Go module, an install command, a GitHub repository or skill, a ClawHub skill, a VS Code Marketplace or Open VSX extension, or an MCP config entry (forms: see target). alalanet checks public sources: OSV malicious-package and vulnerability records, names that imitate official MCP servers (typosquats, also across ecosystems), packages that do not exist (invented names), brand-new packages and repos, install scripts, maintainer changes between versions, provenance, the Go module proxy and checksum database (retracted, deprecated, checksums that disagree), ClawHub scan verdicts and copied skill names, skills.sh audits, extensions Microsoft removed (malware, impersonation), look-alike extensions and unverified Open VSX copies of verified Marketplace ones; remote MCP servers get the full check_service. Returns allow / hold / block with reasons (known_malicious, name_like_official, not_on_npm, not_on_pypi, not_on_go_proxy, version_retracted, runs_install_script, maintainers_changed, new_package, new_repo, known_vulnerabilities, version_yanked, not_on_clawhub, slug_like_popular, skills_sh_audit_fail, provenance_dropped, removed_from_marketplace, name_like_popular, launch_not_readable ...), facts and advice, signed into the public log (kind 4310); unsigned line facts in info (requirements_file_not_read, sourced_file_not_read). A line alalanet cannot read (custom registry, git/URL source, stdin or $(...) arguments, several packages, other commands) holds. allow means no known problem was found, not that the code was read. Free, no account.
Annotations the server declares
- idempotentHint: false
- openWorldHint: true
- readOnlyHint: true
- title: Is it safe to install this package, repo, skill or MCP server?
verify_toolsChecks the tools you received from a remote MCP server against alalanet's history of it: changed after you approved them, or different from what it serves everyone?Reads text others writeCan send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it Checks the tools you received from a remote MCP server against alalanet's history of it: changed after you approved them, or different from what it serves everyone? Pass url and the tools array of your tools/list result (or a digest from an earlier answer). Read-only and free. If your set differs from alalanet's last read, alalanet reads the server again first (fetched_now; one of your daily live checks). Returns verdict matches_current (what it serves now), served_before (an older set; first_seen, last_seen), never_served (review before trusting it) or no_history, the diff from the current set (added, removed, changed, gained_authority), description flags in what you sent, and the digest history linked to the signed log entries of each change. Names and descriptions are third-party text.
Annotations the server declares
- idempotentHint: false
- openWorldHint: true
- readOnlyHint: true
- title: Are these the tools this MCP server really serves?
Only reads 2Show 2 read-only tools
find_serviceWhen you need a paid API or MCP server for a task, or a working alternative after a call failed.No findings
Why it is in this group
- The name "find_service" says "find": a word for reading.
Description, as the server wrote it When you need a paid API or MCP server for a task, or a working alternative after a call failed. Pass query in plain words; optional protocol, only_alive and limit. Read-only; free tier 300 searches a day. Returns services ranked by the open Trust Score (/trust), at most 2 per host unless your query names the host, each with status, advice, trust_score, live price and network, pay_to, pay_to_shared_by_hosts (many hosts on one payTo = a platform wallet), host_listings, uptime and an id that check_service and preflight_payment accept.
Annotations the server declares
- idempotentHint: false
- openWorldHint: false
- readOnlyHint: true
- title: Find working agent services
payment_statusWhether an x402 payment settled: after a timeout, a 5xx or any unclear answer to a paid request, before a new payment is signed.Reads text others writeNo findings
Why it is in this group
- The name "payment_status" says "status": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Whether an x402 payment settled: after a timeout, a 5xx or any unclear answer to a paid request, before a new payment is signed. Pass network and the settlement tx, or (EVM exact) from + nonce + valid_before of the signed authorization, or (Solana exact) from + the recentBlockhash of the signed transaction; never the signature. alalanet reads the chain and answers state (settled | pending | not_settled | expired_unsettled | failed), retry (do_not_pay_again, resend_same: the same authorization settles only once, new_payment_ok, wait) and safe_to_sign_new, true only when a new payment cannot pay twice. Read-only (nothing signed or logged); chain_unavailable: the networks did not answer, ask again after 15 s.
Annotations the server declares
- idempotentHint: false
- openWorldHint: true
- readOnlyHint: true
- title: Did my x402 payment settle? May I pay again?
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.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write7
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out3
- 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 20, 2026, 18:22 UTC, unchanged since Nov 13, 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
- 6
- 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
- yes
- 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 6 tools that change things (2 irreversible, 4 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://alalanet.com/mcp: tools/list returned 8 tools to an anonymous client, including preflight_payment (irreversible), report_purchase (irreversible), check_repo_config (write), check_service (write), install_check (write) and 1 more
Posture changes
- Nov 13, 2026
- Legacy HTTP+SSE transport: no to yes
Findings
Matches of fixed checks, with the text they matched.
The description refers to ".env".
What this check looks forMatched text
description: "...and Copilot settings, hooks and tasks; .env; package-registry settings; CLAUDE.md,..."
The input schema at properties.files.description refers to ".env".
What this check looks forMatched text
inputSchema.properties.files.description: "...rvers are looked up, never probed; from .env only CODEX_HOME, model-API, proxy and p..."
- Warncheck_service
The server marks "check_service" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"idempotentHint":false,"openWorldHint":true}; The description's first verb is "call": a word for a change.
- Warninstall_check
The server marks "install_check" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"idempotentHint":false,"openWorldHint":true}; The name "install_check" says "install": a word for a change.
The server marks "preflight_payment" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"idempotentHint":false,"openWorldHint":true}; The name "preflight_payment" says "payment": a word that usually means money moves, which cannot be taken back.
The description mentions "credential".
What this check looks forMatched text
description: "...lugin marketplaces and enabled plugins, credential helpers and shell prefixes, repository..."
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools8 changed.~8 changedView diff
- Changed:check_repo_configChanges thingsdescriptioninputSchema
- Changed:check_serviceChanges thingsdescriptioninputSchema
- Changed:find_serviceOnly readsdescription
- Changed:install_checkChanges thingsdescriptioninputSchema
- Changed:payment_statusOnly readsdescription
- Changed:preflight_paymentCan't be undonedescription
- Changed:report_purchaseCan't be undonedescriptioninputSchema
- Changed:verify_toolsChanges thingsdescription
PostureRemote posture changed. Legacy HTTP+SSE transport: no -> yes.View diff
- Legacy HTTP+SSE transport: no to yes
Tools17 removed.−17 removedView diff
- Removed:check_agent
- Removed:check_artifact
- Removed:connect_check
- Removed:create_invoice
- Removed:dispute_evidence
- Removed:get_attestation
- Removed:invoice_status
- Removed:lint_x402_endpoint
- Removed:list_plans
- Removed:memory_get
- Removed:post_board
- Removed:read_board
- Removed:read_mail
- Removed:register_agent
- Removed:send_mail
- Removed:submit_signed_event
- Removed:watch_service
Tools2 changed.~2 changedView diff
- Changed:check_repo_configChanges thingsdescription
- Changed:install_checkChanges thingsdescription
Tools5 changed.~5 changedView diff
- Changed:create_invoiceChanges thingsinputSchema
- Changed:list_plansOnly readsdescription
- Changed:post_boardChanges thingsdescription
- Changed:read_boardOnly readsdescription
- Changed:submit_signed_eventChanges thingsdescription
Tools1 changed.~1 changedView diff
- Changed:create_invoiceChanges thingsinputSchema
Tools1 changed.~1 changedView diff
- Changed:install_checkChanges thingsinputSchema
Tools1 changed.~1 changedView diff
- Changed:check_repo_configChanges thingsdescription
Tools1 changed.~1 changedView diff
- Changed:check_repo_configChanges thingsdescriptioninputSchema
Tools1 added, 1 changed.+1 added~1 changedView diff
- Added:check_repo_configChanges things
- Changed:install_checkChanges thingsdescription
Install
Pinned to version 1.5.5. Values in angle brackets are yours to fill in.
claude mcp add --transport http check https://alalanet.com/mcpclaude mcp add --transport http check https://alalanet.com/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__check__find_service",
"mcp__check__payment_status"
],
"ask": [
"mcp__check__check_repo_config",
"mcp__check__check_service",
"mcp__check__install_check",
"mcp__check__preflight_payment",
"mcp__check__report_purchase",
"mcp__check__verify_tools"
],
"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 check. Review it before you use it.
Capability tags behind 7 rules
- mcp__check__check_repo_config untrusted-input
- mcp__check__check_service untrusted-input, outbound
- mcp__check__install_check untrusted-input
- mcp__check__payment_status untrusted-input
- mcp__check__preflight_payment untrusted-input, outbound
- mcp__check__report_purchase untrusted-input
- mcp__check__verify_tools untrusted-input, 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/com.alalanet/check/verify?hash=7608fee5853f2724748eb461917fd4e0b5eb967865deb65ee5e9a697685a271f" | jq -e '.changed == false'Pinned hash 7608fee5853f, from Nov 20, 2026, 14:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.alalanet/check/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.alalanet/check)Source: MCP Registry · repository. Synced Nov 20, 2026, 14:17 UTC.
alalanet — check before your agent installs, connects or pays MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the alalanet — check before your agent installs, connects or pays MCP server safe?
- No scan can promise that. What its definitions show: 8 tools, 6 of which can change, send or delete something, and 6 findings (2 high) from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the alalanet — check before your agent installs, connects or pays MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the alalanet — check before your agent installs, connects or pays MCP server do things that cannot be undone?
- Yes. 2 tools can send, pay, publish or merge: preflight_payment and report_purchase.
What tools does the alalanet — check before your agent installs, connects or pays MCP server have?
- 8 tools: 2 irreversible, 4 write, 2 read. preflight_payment, report_purchase, check_repo_config, check_service, install_check, verify_tools, find_service and payment_status.
Does the alalanet — check before your agent installs, connects or pays MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the alalanet — check before your agent installs, connects or pays MCP server send data to outside services?
- 3 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): check_service, preflight_payment and verify_tools.
Has the alalanet — check before your agent installs, connects or pays MCP server changed its tools?
- Yes, 10 times since Anlyon Radar started tracking it, most recently on Nov 20, 2026. Every change is on this page and in its Atom feed.