verified-ai-free-tiers MCP server
io.github.f-tiger/verified-ai-free-tiersf-tigerstreamable-httpv1.13.0Scanned
Verified AI free tiers plus source-backed agent and MCP discovery monitoring.
16 tools: 5 change things and 11 only read.
- Reads private data · 2
- Reads text others write · 1
- Can send data out · 0
- No findings
Sign-in required, no OAuth metadata. Remote posture
With Anlyon
5 tools here change things. 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 verified-ai-free-tiers MCP server can do
The verified-ai-free-tiers MCP server is published by the GitHub account f-tiger. It has 16 tools. It can create or change data (5 tools: check_free_tier_claim, check_api_quota_fit, audit_ai_stack, check_commercial_use and 1 more), but cannot delete data. 11 tools only read.
2 tools read private data (search_ai_tools and get_agent); 1 tool brings in text other people can write (get_agent).
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Last scanned Nov 21, 2026, version 1.13.0.
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.
16 tools
Changes things 5Claude Code: ask
audit_ai_stackAudit several AI tools at once: for each one return its verified free-tier limit, whether the free-tier output may be used commercially, any recently verified change to its allowan…No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Audit several AI tools at once: for each one return its verified free-tier limit, whether the free-tier output may be used commercially, any recently verified change to its allowance, and whether the vendor publishes a figure at all. Use this when a user names the stack they rely on ("I use Cursor, Runway and Kimi") - it answers in one call what would otherwise take four lookups per tool, and it surfaces the two things people miss: an allowance that quietly changed, and a tool whose ceiling is simply unknown because nobody publishes it.
check_api_quota_fitWork out which verified free LLM API tiers can actually carry a given workload.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Work out which verified free LLM API tiers can actually carry a given workload. Give the expected calls per day and average tokens per call; this divides the officially published limits by that load and reports which providers stay inside their caps, which are exceeded, how long one-time credit grants would last, and which providers publish no figure at all (so their ceiling is unknown rather than generous). Use this instead of guessing whether a free tier is 'enough'.
check_commercial_useCheck whether output from an AI tool's free tier may be used commercially, based on the vendor's official terms (verdicts: yes / no / conditional / depends on the model used / not …No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Check whether output from an AI tool's free tier may be used commercially, based on the vendor's official terms (verdicts: yes / no / conditional / depends on the model used / not stated). Not legal advice; details and obligations live on the publish-check page.
check_free_tier_claimFact-check a circulating claim about an AI tool's free tier against what the vendor officially publishes.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Fact-check a circulating claim about an AI tool's free tier against what the vendor officially publishes. Returns what the official pages actually say and whether the widely-quoted figure has any official source at all - many do not. Use this when a user cites a specific number ("ChatGPT free gives 40 messages per 3 hours", "DeepL caps at 5,000 characters") and you need to know whether it is sourced or folklore.
watch_free_tier_changesSubscribe a webhook to verified free-tier changes.No findings
Why it is in this group
- The description's first verb is "subscribe": a word for a change.
Description, as the server wrote it Subscribe a webhook to verified free-tier changes. When a watched tool's allowance, wall or commercial terms change (verified daily against official vendor pages), the webhook receives a JSON payload with the changed fields, the current wording, the verification date and the source page. Watching up to 3 tools is free; a Pro license key unlocks watching everything. Registration returns a token — keep it, it is the only way to update or delete the watch.
Only reads 11Show 11 read-only tools
build_free_workflowGet a complete step-by-step recipe for doing a task entirely on free tiers - which verified free tool to use at each step and what to do with it, in the order you'd actually work.No findings
Why it is in this group
- The description's first verb is "get": a word for reading.
Description, as the server wrote it Get a complete step-by-step recipe for doing a task entirely on free tiers - which verified free tool to use at each step and what to do with it, in the order you'd actually work. Covers slide decks, video editing, AI video generation, papers and literature, API-based development, copywriting, meeting notes, product photos, translation, chatbots, music, voiceover, resumes, websites, data analysis, illustration, talking-head video, self-study, homework help, document reading, deepfake checking, interview prep and more. Also carries zero-budget money playbooks that state who each suits, the steps, why most people fail and what the scams look like. Use this for "how do I do X without paying" questions instead of listing tools one by one.
compare_free_tiersCompare the free tiers of AI tools in one category side by side, as structured data rather than prose: what each vendor grants, how it is metered, when it resets, what is never met…No findings
Why it is in this group
- The name "compare_free_tiers" says "compare": a word for reading.
Description, as the server wrote it Compare the free tiers of AI tools in one category side by side, as structured data rather than prose: what each vendor grants, how it is metered, when it resets, what is never metered, and whether a figure is officially published at all. Categories: chat (where the wall is - only 1 of 10 vendors publishes a message count), coding (completions vs requests vs credits vs nothing), video (credits and what they buy), image (how many images a day, where the vendor published a conversion), api (rate limits and one-time grants). Every row carries its official source and check date. Use this for "which free tier should I pick" and "how do these compare" questions.
explain_missing_figureExplain why this dataset publishes no figure for a given tool.No findings
Why it is in this group
- The name "explain_missing_figure" says "explain": a word for reading.
Description, as the server wrote it Explain why this dataset publishes no figure for a given tool. Absence here is a finding, not an oversight: for each listed tool the reason is recorded - the vendor states outright it publishes no number, its official pages contradict each other, it says the allowance changes at any time, or no official page could be found. Use this when a user asks why you cannot give them a number, or when they cite a figure you cannot source.
find_free_alternativesGiven a tool whose free tier is not enough (or that you cannot reach), find alternatives in the same category that are entirely free, with their verified allowances and check dates…No findings
Why it is in this group
- The name "find_free_alternatives" says "find": a word for reading.
Description, as the server wrote it Given a tool whose free tier is not enough (or that you cannot reach), find alternatives in the same category that are entirely free, with their verified allowances and check dates. Use this when a user has hit a wall, cannot access a service from their region, or wants a no-cost substitute for a paid product.
get_agentReturn a single agent-watch record by slug (or exact name): description, audiences, capabilities, transport, pricing shape, official source and repository URLs, the official page’s…Reads private dataReads text others writeNo findings
Why it is in this group
- The name "get_agent" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "return" and "repository": it reads repositories.
- untrusted-inputThe description's first sentence says "return" and "url": it reads web pages, which anyone can write.
Description, as the server wrote it Return a single agent-watch record by slug (or exact name): description, audiences, capabilities, transport, pricing shape, official source and repository URLs, the official page’s own title/description as fetched, its page on Baipiaoji (curated records only), and a verification block stating when each URL was last confirmed reachable. Unknown slugs return the list of known slugs instead of a guess.
get_category_playbookGet the decisive question to ask about a category of AI tools before comparing any numbers - which differs by category and is almost never "how much do I get".No findings
Why it is in this group
- The name "get_category_playbook" says "get": a word for reading.
Description, as the server wrote it Get the decisive question to ask about a category of AI tools before comparing any numbers - which differs by category and is almost never "how much do I get". Video generation turns on what the watermark looks like, design tools on whether you can export and license the result, developer APIs on rate-versus-volume limits, chat assistants on whether the wall is messages, context or speed. Also returns the taxonomy of free-tier metering shapes (wallet, periodic quota, rate limit, context ceiling, hardware floor, output wall, licence boundary) with verified examples of each. Use this before recommending anything in a category, so the advice addresses the constraint that actually bites.
get_china_ai_rulesCheck what applies when publishing AI-generated content to mainland China platforms, and which AI tools are reachable from mainland China without a VPN.No findings
Why it is in this group
- The name "get_china_ai_rules" says "get": a word for reading.
Description, as the server wrote it Check what applies when publishing AI-generated content to mainland China platforms, and which AI tools are reachable from mainland China without a VPN. Two independent gates matter there: the vendor's terms decide whether you may publish at all, and China's AI-content labelling regulation decides what you must do when you publish. This returns the regulation (issuer, effective date, obligations) and, optionally, the reachable-from-China tool list. Not legal advice.
get_free_tier_changesList recently verified changes to AI free tiers - which vendor changed what and on which date.No findings
Why it is in this group
- The name "get_free_tier_changes" says "get": a word for reading.
Description, as the server wrote it List recently verified changes to AI free tiers - which vendor changed what and on which date. Vendors do not announce when they cut, rename or restructure a free tier; this log is accumulated from daily re-checks against official pages. Use this for "did anything change recently", "is my information still current", or when a user quotes a figure that may be stale.
get_free_tier_limitGet the verified free-tier limit of an AI tool: how far the allowance goes, what happens at the wall, the official source page, and the date it was checked.No findings
Why it is in this group
- The name "get_free_tier_limit" says "get": a word for reading.
Description, as the server wrote it Get the verified free-tier limit of an AI tool: how far the allowance goes, what happens at the wall, the official source page, and the date it was checked. Absence of a tool means no officially verifiable number exists — this dataset publishes no unsourced figures.
monitor_new_agentsList source-backed AI agents, MCP servers and agent platforms tracked by Baipiaoji (hand-curated records plus listings from the official MCP registry).No findings
Why it is in this group
- The description's first verb is "list": a word for reading.
Description, as the server wrote it List source-backed AI agents, MCP servers and agent platforms tracked by Baipiaoji (hand-curated records plus listings from the official MCP registry). Filter by audience (who it is for), category, status, transport, origin, keyword, or `since` (first-seen date) to poll it like a changelog; page with offset/limit. Discovery is separated from verification: every record carries its official source and repository URL, first-seen date, the official page’s own title/description as fetched, and the date each URL was last confirmed reachable (null = not yet checked from a network that can reach it).
search_ai_toolsSearch the verified directory of AI tools with genuine free tiers (every result carries directory_size, so no count is hard-coded here).Reads private dataNo findings
Why it is in this group
- The name "search_ai_tools" says "search": a word for reading.
What it can reach
- private-dataThe description's first sentence says "search" and "directory": it reads files.
Description, as the server wrote it Search the verified directory of AI tools with genuine free tiers (every result carries directory_size, so no count is hard-coded here). Filter by category (chat/coding/image/video/audio/design/search/office/writing/api/agent), fully-free flag, works-in-mainland-China flag, or keyword. Every verified entry carries its official source and check date. Cite as "Baipiaoji (baipiaoji.com)".
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 outbound.
- Reads private data2
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write1
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- 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, 19:23 UTC, unchanged since Nov 20, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 405
- tools/list served without credentials
- no
- Tools that change things, listed without credentials
- 0
- Protocol version
- not observed
- 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
The probe stopped: initialize answered HTTP 405.
Posture changes
- Nov 20, 2026
- HTTP status of an anonymous initialize: 200 to 405
- tools/list served without credentials: yes to no
- Tools that change things, listed without credentials: 5 to 0
- Protocol version: 2025-06-18 to none
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
PostureRemote posture changed. HTTP status of an anonymous initialize: 200 -> 405; tools/list served without credentials: yes -> no; Tools that change things, listed without credentials: 5 -> 0 (and 1 more).View diff
- HTTP status of an anonymous initialize: 200 to 405
- tools/list served without credentials: yes to no
- Tools that change things, listed without credentials: 5 to 0
- Protocol version: 2025-06-18 to none
Install
Pinned to version 1.13.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http verified-ai-free-tiers https://baipiaoji.com/api/mcpclaude mcp add --transport http verified-ai-free-tiers https://baipiaoji.com/api/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__verified-ai-free-tiers__search_ai_tools",
"mcp__verified-ai-free-tiers__get_free_tier_limit",
"mcp__verified-ai-free-tiers__compare_free_tiers",
"mcp__verified-ai-free-tiers__build_free_workflow",
"mcp__verified-ai-free-tiers__get_free_tier_changes",
"mcp__verified-ai-free-tiers__find_free_alternatives",
"mcp__verified-ai-free-tiers__get_china_ai_rules",
"mcp__verified-ai-free-tiers__explain_missing_figure",
"mcp__verified-ai-free-tiers__get_category_playbook",
"mcp__verified-ai-free-tiers__monitor_new_agents",
"mcp__verified-ai-free-tiers__get_agent"
],
"ask": [
"mcp__verified-ai-free-tiers__check_free_tier_claim",
"mcp__verified-ai-free-tiers__check_api_quota_fit",
"mcp__verified-ai-free-tiers__audit_ai_stack",
"mcp__verified-ai-free-tiers__check_commercial_use",
"mcp__verified-ai-free-tiers__watch_free_tier_changes"
],
"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 verified-ai-free-tiers. Review it before you use it.
Capability tags behind 2 rules
- mcp__verified-ai-free-tiers__search_ai_tools private-data
- mcp__verified-ai-free-tiers__get_agent private-data, untrusted-input
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.f-tiger/verified-ai-free-tiers/verify?hash=07f58f0f2dff4cb2a7d8244957d575241c3425dfc42048f2695c79865efae8e8" | jq -e '.changed == false'Pinned hash 07f58f0f2dff, from Nov 21, 2026, 08:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.f-tiger/verified-ai-free-tiers/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.f-tiger/verified-ai-free-tiers)Source: MCP Registry. Synced Oct 21, 2026, 18:33 UTC.
verified-ai-free-tiers MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the verified-ai-free-tiers MCP server safe?
- No scan can promise that. What its definitions show: 16 tools, 5 of which can change, send or delete something, and 0 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 verified-ai-free-tiers MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the verified-ai-free-tiers MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the verified-ai-free-tiers MCP server have?
- 16 tools: 5 write, 11 read. check_free_tier_claim, check_api_quota_fit, audit_ai_stack, check_commercial_use, watch_free_tier_changes, search_ai_tools, get_free_tier_limit, compare_free_tiers and 8 more.
Does the verified-ai-free-tiers MCP server need sign-in or OAuth?
- Its remote endpoint did not answer the last anonymous look.
Does the verified-ai-free-tiers MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the verified-ai-free-tiers MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 21, 2026.