Tools at a glance
Choosing between similar tools
Four pairs look alike from the outside. The difference matters for both speed and quality of the answer:Recall
recall_context
Returns your relevant memories as prose the agent can read straight into its answer. This is the default tool for personalising a response — it is the fastest of the recall tools and needs no parsing.
string
required
What you just asked or said. Retrieval matches against this, so the agent should pass your actual words rather than an extracted keyword.
integer
default:"1200"
Budget for the returned context, between 100 and 10000. Raise it for broad questions.
string
default:"hybrid"
hybrid (recommended), semantic (meaning only), or recency (newest first — best for “what was I working on recently”).string
default:"web"
Where the conversation is happening:
web, slack, telegram, whatsapp, or unknown.search_memories
Returns matching memories individually, with their text and IDs. Use it for specific recall — “what did I decide about the vendor”, “what’s my sister’s name” — rather than general background.
Costs 1 credit per call.
string
required
A natural-language description of what you are looking for.
integer
default:"5"
How many results to return, between 1 and 20.
string
Narrow to one of
preference, fact, task, relationship, or context.number
default:"0.3"
Relevance floor between 0.0 and 1.0. Raise it to cut noise; lower it to around
0.15 if a query you expect to match returns nothing.get_user_context
A structured profile of you in relation to some text or topic: what you know, where you stand, what you have already been through, and explicit guidance on what to emphasise and avoid.
Richer and slower than recall_context — it takes several seconds. Worth it when the stakes justify the wait: drafting something under your name, advising on a decision, or prepping for a conversation.
Every claim in the profile is checked against a real memory before you see it. Anything unsupported is dropped rather than guessed at.
string
required
The material to profile you against — the message you received, the document you are reacting to, or the topic at hand.
string
What the agent is about to produce, e.g.
"reply to this email" or "prep for a negotiation". Steers what the profile emphasises.integer
default:"1200"
Budget for the memory context behind the profile, between 100 and 4000.
Knowledge
query_knowledge
Returns what you actually know about a subject, graded by expertise level and confidence, drawn from everything you have read and discussed.
Distinct from search_memories: that returns text you said, this returns knowledge extracted from it. Use it to calibrate an explanation — an agent that knows you are already expert on a topic can skip the basics.
Costs 1 credit per call.
string
Semantic query. Omit it to browse by filters alone (relevance scores are then absent).
string[]
Restrict to categories, e.g.
["technology", "finance"]. Up to 20.string[]
Restrict to any of
high, medium, low.string
user_possesses_knowledge (you know it) or user_accessed_knowledge (you merely encountered it — weaker evidence, and not to be treated as expertise).number
Only return items at or above this extraction confidence, 0.0 to 1.0.
boolean
default:"false"
Also return how your knowledge is distributed across categories — useful for “what do I know about in general”.
boolean
default:"false"
Also return your aggregate knowledge profile.
integer
default:"10"
Results per page, between 1 and 50. Page with
offset rather than maxing this out.integer
default:"0"
Page offset.
number
default:"0.3"
Relevance floor.
Voice
get_voice_card
Returns your writing-voice profile — register, sentence rhythm, punctuation and casing habits, emoji use — so the agent can write to that spec itself. Takes no arguments.
Best called before composing anything that goes out under your name.
Needs a voice card built from your writing. If you do not have one yet, build it in the dashboard at app.maximem.ai.
rewrite_as_me
Hands your draft to Vity’s voice engine and returns the same message as you would have written it.
Use this when you want the engine to do the styling; use get_voice_card when you would rather have the spec and let the agent write. Takes a few seconds, and is limited to 1,000 rewrites per day per key.
string
required
The message to rewrite. Write the full content first — the engine restyles what it is given, it does not invent what you leave out.
string
default:"generic"
Where it will be sent — e.g.
slack, email, linkedin, x. Changes the register.string
Who it is going to, e.g.
"my manager", "a close friend". Changes formality.summarize
Summarises a page or a block of text, personalised against what you already know — so it skips the familiar and flags what is new to you.
Costs 20 credits and takes several seconds. For a plain summary of text the agent already has in front of it, this is the wrong tool; use it when the personalisation or the URL fetch is the point.
string
The page to fetch and summarize. Either this or
text is required.string
Raw text to summarize instead of fetching a URL.
string
Title of the source, if known.
string
default:"tldr"
Output shape.
integer
default:"0"
For sources too large for one pass, request the next chunk by resending the same call with
segment incremented. The result says when there is more.Capture
remember
Saves one durable fact about you to long-term memory — a preference, a decision, a relationship, an ongoing project.
Stored statements are written to stand alone, because they will be read months later with none of the surrounding conversation. “Prefers async standups over daily calls”, not “yes I do”.
string
required
The statement to remember, up to 10,000 characters.
string
One of
preference, fact, task, relationship, context. Improves later recall.string
default:"medium"
low, medium, or high.capture_conversation
Saves a whole conversation so the important parts survive into later sessions. Vity decides what is worth keeping, so nothing needs filtering first.
Processing is asynchronous — the tool returns immediately and the memories become searchable a few seconds later. A search run instantly after a capture may not see them yet.
object[]
required
Up to 50 messages, each
{"role": "user" | "assistant", "content": "...", "timestamp": <unix ms>}. timestamp is optional.string
default:"web"
Where the conversation happened:
web, slack, telegram, whatsapp, unknown.string
Optional identifier for which agent held the conversation.
Deleting memories
There is no delete tool over MCP, by design — an agent cannot remove your memory on its own initiative, or as cleanup it decided was helpful. Delete memories in the dashboard at app.maximem.ai, where you can see exactly what is going before it goes.Prompts
Prompts are reusable instructions your client can offer as a slash command or template. All three chain the tools above in the right order, so you get a better result than asking for the same thing freehand.Resources
Two resources can be attached as context rather than called as tools:Not every MCP client sends your API key when reading a resource. Where that happens, the resource returns a pointer to the equivalent tool instead of failing silently. Tools are the reliable path — prefer
get_voice_card and query_knowledge if you have the choice.