flixconomy.ai: humans and Ari for agents MCP server
io.github.flixconomy/flixconomyflixconomystreamable-httpv0.2.0Scanned
Real humans for AI agents: ask a question or rent a human for a task. Prepaid in EUR.
16 tools: 2 can delete or cancel things, 1 do something that can't be undone, 8 change things and 5 only read.
- Reads private data · 1
- Reads text others write · 6
- Can send data out · 3
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
2 tools here can delete or cancel things and 1 does 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 flixconomy.ai: humans and Ari for agents MCP server can do
The flixconomy.ai: humans and Ari for agents MCP server is published by the GitHub account flixconomy. It has 16 tools. It can delete or cancel things (2 tools: cancel_task and delete_api_key), do things that cannot be undone, such as sending, paying or publishing (message_task_human) and create or change data (8 tools: ask_a_human, rent_a_human, create_account, create_api_key and 4 more). 5 tools only read.
1 tool reads private data (get_task); 6 tools bring in text other people can write (ask_a_human, rent_a_human, get_task and 3 more); 3 tools can send data out of your system (rent_a_human, message_task_human and subscribe_updates). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 19, 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.
16 tools
Deletes or cancels 2Claude Code: deny
cancel_taskCancel a task from rent_a_human.No findings
Why it is in this group
- The name "cancel_task" says "cancel": a word for removing or ending something.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Cancel a task from rent_a_human. Before a human accepts it, the full price returns to your credit.
Annotations the server declares
- destructiveHint: true
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: false
delete_api_keyDelete an API key of your account (key_id from get_account).No findings
Why it is in this group
- The name "delete_api_key" says "delete": a word for removing or ending something.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Delete an API key of your account (key_id from get_account). It stops working within a few minutes.
Annotations the server declares
- destructiveHint: true
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: false
Can't be undone 1Claude Code: ask
message_task_humanSend a message to the human on a task (answer their question, add details).Reads text others writeCan send data outNo findings
Why it is in this group
- The description's first verb is "send": a word for sending, and what is sent cannot be taken back.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe description's first verb is "send": it sends or publishes something to other people.
Description, as the server wrote it Send a message to the human on a task (answer their question, add details). Works while the task is open or accepted.
Annotations the server declares
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
- readOnlyHint: false
Changes things 8Claude Code: ask
ari_coachingComing soon.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.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Coming soon. Coaching by Agent: Ari, an AI with its own experience, helps your agent with a hard decision.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
ari_supportComing soon.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.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Coming soon. Support by Agent: hand a support question your agent can't settle to Ari.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
ask_a_humanAsk a real human a short question.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
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 Ask a real human a short question. Returns an id, the price and the due time at once; collect the answer with get_human_answer. answer_within_minutes (required): by when a human must answer, 15 to 10080. Shorter is more expensive: from 24 h 1 EUR, from 4 h 2 EUR, from 1 h 4 EUR, from 15 min 8 EUR (incl. VAT), taken from your account credit. Not answered in time: status expired and the full price returns to your credit. question: one short, self-contained question a person can answer in under a minute (taste, judgement, approval, sanity check). options: optional 2 to 10 answer choices; the human picks one and may add a comment. context: optional background (links, the two variants, what it is for). Shown to the human. api_key: optional, your API key if you cannot set the Authorization header.
Annotations the server declares
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
- readOnlyHint: false
create_accountCreate a flixconomy.ai account for yourself.Reads text others writeNo findings
Why it is in this group
- The name "create_account" says "create": a word for a change.
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 Create a flixconomy.ai account for yourself. No key needed. Returns an account key (keep it secret; it manages the account but cannot call services) and a top-up link for your human (card payment via Stripe, from 10 EUR). The email your human enters at the first payment receives invoices and signs in at www.flixconomy.ai/account. After the payment, call create_api_key.
Annotations the server declares
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
- readOnlyHint: false
create_api_keyCreate an API key for all flixconomy.ai services (shown once).No findings
Why it is in this group
- The name "create_api_key" says "create": a word for a change.
Description, as the server wrote it Create an API key for all flixconomy.ai services (shown once). Needs credit on the account. name: a label, e.g. 'research agent'.
Annotations the server declares
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
- readOnlyHint: false
rent_a_humanPost a paid task for a real human (online or physical, on site).Reads text others writeCan send data outNo findings
Why it is in this group
- The description's first verb is "post": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe description's first verb is "post": it sends or publishes something to other people.
Description, as the server wrote it Post a paid task for a real human (online or physical, on site). Returns a task id, the price and the due time. deadline (required): ISO 8601, at least 4 hours ahead, e.g. 2026-10-20T18:00:00+02:00. price_eur = budget plus a fee that depends on the deadline: from 72 h 20 %, from 24 h 30 %, from 4 h 50 % (all incl. VAT); taken from your account credit, the task is visible to humans at once. Returned in full if you cancel before a human accepts or if it is not done by the deadline (status expired). title: short summary. description: what exactly should be done and what counts as done. budget: what the human gets, in EUR (10 to 500). location: city or address if the task is on site. api_key: optional, your API key if you cannot set the Authorization header.
Annotations the server declares
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
- readOnlyHint: false
subscribe_updatesGet notified when Ari's services launch (Coaching, Support, Test your AGI) and about news of Ask/Rent a human.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "subscribe_updates" says "subscribe": a word for a change.
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.webhook_url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it Get notified when Ari's services launch (Coaching, Support, Test your AGI) and about news of Ask/Rent a human. No key needed. email: optional, your human's address; they get a confirmation link and receive updates only after confirming (double opt-in). agent_card_url / mcp_url / webhook_url: optional public https contacts for you as an agent (A2A agent card, MCP server, webhook); stored as a contact, nothing is sent yet. name: optional label. interests: any of ask, rent, coaching, support, agi, human.
Annotations the server declares
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
- readOnlyHint: false
test_your_agiComing soon.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.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Coming soon. Test your AGI: Ari talks with your agent and checks it for own vision, drive without an assignment, steadfastness with reasons and morality as part of the reasoning.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
Only reads 5Show 5 read-only tools
get_accountYour account: credit, usage, API keys, payments and the top-up link.No findings
Why it is in this group
- The name "get_account" says "get": a word for reading.
Description, as the server wrote it Your account: credit, usage, API keys, payments and the top-up link. account_key: the fxa_... key from create_account (or send it as the Authorization header).
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
get_creditShow the credit left on the account of your API key (EUR), what was used, and where your human can top it up.No findings
Why it is in this group
- The name "get_credit" says "get": a word for reading.
Description, as the server wrote it Show the credit left on the account of your API key (EUR), what was used, and where your human can top it up.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
get_human_answerGet the status and answer for a question id from ask_a_human.No findings
Why it is in this group
- The name "get_human_answer" says "get": a word for reading.
Description, as the server wrote it Get the status and answer for a question id from ask_a_human. Waits up to wait_seconds (0 to 45) for an answer. status is open (call again), answered (with answer and, if options were given, choice) or expired (refunded_eur shows the credit returned). Only the API key that asked can read it.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
get_pricePrice before you ask, nothing is charged.No findings
Why it is in this group
- The name "get_price" says "get": a word for reading.
Description, as the server wrote it Price before you ask, nothing is charged. kind 'ask' with answer_within_minutes, or kind 'task' with budget (EUR) and deadline (ISO 8601). Returns price_eur and due_at.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
get_taskGet the status of a task from rent_a_human (open, accepted, done, cancelled, expired) and all messages with the human.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "get_task" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "get" and "message": it reads messages.
- untrusted-inputThe description's first sentence says "get" and "message": it reads messages, which other people can write.
Description, as the server wrote it Get the status of a task from rent_a_human (open, accepted, done, cancelled, expired) and all messages with the human.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
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.
18 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 private-data tool breaks every one.
- Reads private data1
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write6
- 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.
{
"permissions": {
"deny": [
"mcp__flixconomy__get_task"
]
}
}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, 19:04 UTC, unchanged since Oct 22, 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
- 11
- 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 11 tools that change things (2 destructive, 1 irreversible, 8 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://api.flixconomy.ai/mcp: tools/list returned 16 tools to an anonymous client, including cancel_task (destructive), delete_api_key (destructive), message_task_human (irreversible), ask_a_human (write), rent_a_human (write) and 6 more
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.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 0.2.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http flixconomy https://api.flixconomy.ai/mcpclaude mcp add --transport http flixconomy https://api.flixconomy.ai/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__flixconomy__get_human_answer",
"mcp__flixconomy__get_task",
"mcp__flixconomy__get_price",
"mcp__flixconomy__get_credit",
"mcp__flixconomy__get_account"
],
"ask": [
"mcp__flixconomy__ask_a_human",
"mcp__flixconomy__rent_a_human",
"mcp__flixconomy__message_task_human",
"mcp__flixconomy__create_account",
"mcp__flixconomy__create_api_key",
"mcp__flixconomy__ari_coaching",
"mcp__flixconomy__ari_support",
"mcp__flixconomy__test_your_agi",
"mcp__flixconomy__subscribe_updates"
],
"deny": [
"mcp__flixconomy__cancel_task",
"mcp__flixconomy__delete_api_key"
]
}
}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 flixconomy. Review it before you use it.
Capability tags behind 6 rules
- mcp__flixconomy__ask_a_human untrusted-input
- mcp__flixconomy__rent_a_human untrusted-input, outbound
- mcp__flixconomy__get_task private-data, untrusted-input
- mcp__flixconomy__message_task_human untrusted-input, outbound
- mcp__flixconomy__create_account untrusted-input
- mcp__flixconomy__subscribe_updates 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/io.github.flixconomy/flixconomy/verify?hash=2672022ec2503bb199324c512c176f18cf98cc3857c8d80a918c81e1dffcf40a" | jq -e '.changed == false'Pinned hash 2672022ec250, from Nov 19, 2026, 17:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.flixconomy/flixconomy/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.flixconomy/flixconomy)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:34 UTC.
flixconomy.ai: humans and Ari for agents MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the flixconomy.ai: humans and Ari for agents MCP server safe?
- No scan can promise that. What its definitions show: 16 tools, 11 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 flixconomy.ai: humans and Ari for agents MCP server delete data?
- Yes. 2 tools can delete, cancel or revoke something: cancel_task and delete_api_key.
Can the flixconomy.ai: humans and Ari for agents MCP server do things that cannot be undone?
- Yes. 1 tool can send, pay, publish or merge: message_task_human.
What tools does the flixconomy.ai: humans and Ari for agents MCP server have?
- 16 tools: 2 destructive, 1 irreversible, 8 write, 5 read. cancel_task, delete_api_key, message_task_human, ask_a_human, rent_a_human, create_account, create_api_key, ari_coaching and 8 more.
Does the flixconomy.ai: humans and Ari for agents MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the flixconomy.ai: humans and Ari for agents 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): rent_a_human, message_task_human and subscribe_updates.
Has the flixconomy.ai: humans and Ari for agents MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 19, 2026.