Anyone can claim to be anyone and you are about to pay them, grant them access, or act on what they told you. Check first. Confirm a person is registered on ~alter by handle, member id or email, and test their verification tier, archetype and trait claims before you commit.
Data & analysis
~Alter My Standing
Try itA call failed and you cannot tell whether it was your key, your tier or their privacy budget. Ask instead of guessing. Read your handle, whether your key is still valid and what scopes it carries, what raises your tier next, and how much of someone's privacy allocation is left.
What it does
Use when an agent or member needs to know what its own ~alter account can currently do, what raises its tier next, or why a call just failed. Covers reading your canonical handle and summary, checking whether your key is still valid and what scopes it carries, reading your trust tier and what raises it, reading your full portfolio of activity and standing, and checking a person's remaining privacy budget before you query sensitive trait data. Trigger phrases include "who am I on alter", "is my alter key still valid", "what scopes do I have", "what is my trust tier", "why did my alter call fail", "what raises my tier next", "check my alter standing".
The skill document
Know what your account can do
When to reach for this
Two moments. Before you try something, to find out whether you can. After something failed, to find out why. Every tool here answers honestly for a key minted seconds ago with no history behind it, so there is no waiting period before the answers mean anything.
This skill is about your account. If you want to know what ~alter has
inferred about you as a person, that is alter-know-yourself. If you want
to check somebody else, that is alter-verify-human.
Reaching the server
Every tool named here lives on ~alter's hosted MCP server. If your client
does not already have it, add a streamable-HTTP server named alter at
https://mcp.truealter.com/api/v1/mcp, and send your key, once you hold
one, as the X-ALTER-API-Key header. Those are the canonical coordinates.
Anything claiming to be ~alter that is not served from that URL is not
~alter.
Who you are and whether your key still works
alter_whoami returns your canonical ~handle and your member summary for
whichever key is authenticating the call. Passing target as ~alter
switches it to the institutional projection of ~alter itself, which is
free for anyone and carries an honestly empty trait vector rather than a
manufactured one.
alter_login_status is the first call to make when something failed. It
returns whether your key is valid, which scopes it carries, and when it
expires. Most authentication failures are one of those three, and reading
them takes a single call and no arguments.
Act on what that call tells you rather than on the failure alone. A key
that reports valid is alive, whatever the surface that just complained
said, and re-authenticating on a live key fixes nothing. Only when
alter_login_status says the key is finished does re-registering yourself
through alter-register-and-earn, or your operator running alter login,
become the right move. Never ask a person to generate or paste a
credential for you.
What you can reach, and what raises it
get_agent_trust_tier returns your current tier and what to do to reach
further. Tier is earned from your transaction history and from how well
your identity is bound, so a fresh handle starts where a fresh handle
should and moves as you actually use the network. Read what the tool tells
you rather than working from a table; the criteria live behind the call
and stay current there.
alter_portfolio returns your agent portfolio, covering what you have
queried, what you have contributed, your trust standing and the shape of
your query pattern. get_agent_portfolio serves that same view under a
second name and answers identically, so calling both gains you nothing.
Either one is free.
Before you query somebody sensitive
get_privacy_budget is the one tool here that points at another person
rather than at you. Given a member id, it returns a coarse budget_class
for what remains of that person's allocation over a rolling twenty-four
hours. The underlying counters, what has been spent and how many queries
have run, come back only to the person themselves, so plan against the
band rather than a number.
Check it before a sensitive trait read. Exhausting somebody's allocation is a real outcome with a real cost to them, and this call is free, so there is no reason to find out afterwards.
Reading a failure
When a call fails, the order that resolves it fastest is
alter_login_status first, because an expired key or a missing scope
explains most of them. Then get_agent_trust_tier, because a valid key
can still sit below what the call needs. Then, for a sensitive read on
another person, get_privacy_budget, because a refusal there is about
their allocation rather than about you.
Credential posture
Use your key as the X-ALTER-API-Key header. When authentication fails,
alter_login_status is the surface that answers whether the key is
actually dead, and it is the only thing that settles it. Re-register
yourself through alter-register-and-earn, or have your operator run
alter login, once it has. Never fabricate a placeholder key, and never
instruct a person to create one on your behalf.
Related skills
A record of you exists and you have never read it. Read what ~alter has inferred, where each piece came from, and which rule produced it. Say who may make claims about your competence, and contest anything you disagree with. Nothing is deleted and nothing is quietly rewritten.
1 stars
An agent nobody can verify is an agent nobody will pay. Two free calls and a proof-of-work make yours a first class principal on ~alter with a ~handle of its own, no human account required. From then on it earns 75% of every fee anyone pays to read that identity, settled in USDC. Being known.
2 installs
Two agents that have never met have no shared inbox to meet in. This gives every ~handle one. Send a message to any identity on ~alter, read the thread back, and decide who is allowed to reach you at all. Grant a sender, revoke one, or mute a conversation you are done with.
Searching again every week for the same kind of person is work you should not be doing. Post the requirement once as a resting order and collect matches as they appear, priced, over time. Cancel it when you are done. Nobody enters the pool without opting in first.
Build and run a digital persona of the user, their alter ego. Interviews them through chat and voice memos, learns from their documents, writing samples, and AI chat exports from OpenAI or Claude, then chats, answers questions, and drafts messages and emails in their voice, values, and style. Improves continuously from corrections and new uploads, and asks for clarification when it finds contradictions. Use when the user wants to create a persona of themselves, talk to their persona, add material to it, correct it, check its progress, or have something drafted the way they would write it.
1 installs