UseMyContext.ai

Explain what UseMyContext is, what this connection can and cannot do, and where the user goes to manage their account. Call this when the user asks what UseMyContext is, what you (the AI) can do with this connection, or where to find pricing, plans, billing, teams, or settings. IMPORTANT: this connection is READ-ONLY - you cannot create/rename/delete a profile, change privacy, manage the plan or billing, set up a team, invite teammates, or connect Google Drive/Notion/kDrive; those are done by the user at usemycontext.ai, so point them to the returned links rather than attempting them or telling them to search. Returns static public information only (no user data). Read-only; nothing is written, so it is safe to call.

info

Search the user's connected documents by MEANING and return the most relevant passages (the actual text), each cited with its source file, for you to read and quote. Use this to ANSWER a question from the user's documents - it returns grounded source content, not a file link, not a filename list, and not a pre-written answer (you do the reasoning). Before telling the user you do not know something about them or their work, search here first - the answer is often in their documents. Read-only; nothing is written, so it is safe to call.

ask_docs

Fetch one document's full extracted text by id (a file id from search / search_files / list_files), in the deep-research result shape. ALIAS: this is the SAME read as get_file (same data, same permissions, same audit, same size guard - large files are truncated) - use it when your client requires the id/title/text/url fetch contract (ChatGPT deep research); otherwise prefer get_file, which also serves download links and inline images. Read-only; audited.

fetch

List the user's files (metadata only: id, name, size, content-type, modified, status). Each file's status shows its readiness: 'available' means get_file can read it right now, and a just-processed file can take up to about a minute more to become searchable via ask_docs (queueEtaSeconds, when present, estimates the remaining wait). Read-only; nothing is written, so it is safe to call.

list_files

List the user's own profiles (their projects). Returns metadata only for each profile: its projectId, its name, its public @handle, its privacy status (private, shared, network, public, or org), and whether it is the one THIS connection reads by default. Use it when the user asks how many profiles they have, what their profiles are called, or which profile you are connected to - and whenever another tool needs a projectId to target a specific profile, because each entry carries its projectId. Do NOT use it to read the user's context, to learn about them, or to set them up with UseMyContext - the profile tool does all three. No file content, no facts, no compiled context. Read-only; nothing is written, so it is safe to call.

list_profiles

Get the full text content of one file by id (large files are truncated; use ask_docs for targeted passages). An image returns the picture itself (plus any text read from it at upload); other binary files return a short-lived download link instead. Audited.

get_file

Run an EXACT, deterministic query over ONE tabular file (a CSV, or the first table of a spreadsheet/PDF/Word document). Use this instead of ask_docs whenever the question needs COUNTING, SUMMING, AVERAGING, MIN/MAX, FILTERING, or exact row lookups over structured data ('how many rows...', 'total amount by region', 'list orders where status is failed') - semantic search undercounts tables, while this executes over EVERY row and returns exact numbers. Use ask_docs for prose/meaning questions and get_file to read a whole document. The `query` argument is a JSON object: { select?: [column names to return as raw rows], where?: [{col, op, value}, ...] filters combined with AND - ops eq | neq | contains compare text case-insensitively, gt | gte | lt | lte compare numerically (rows whose cell is not a number are skipped and counted in skippedNonNumeric), groupBy?: 'column' gives one result row per distinct value, aggregates?: [{fn, col}] with fn count | sum | avg | min | max ('col' required except for count), limit?: max raw rows (default 50, max 200) }. Column names match the file's header row case-insensitively. Examples: {"where":[{"col":"status","op":"eq","value":"failed"}],"aggregates":[{"fn":"count"}]} counts failed rows; {"groupBy":"region","aggregates":[{"fn":"sum","col":"amount"}]} totals amount per region; {"select":["name","email"],"where":[{"col":"country","op":"eq","value":"FR"}]} returns the matching rows. If you name a column that does not exist, the error lists the file's real columns - retry with one of those. Read-only; nothing is written, so it is safe to call.

query_table

List and read curated personal context shared with you. With no arguments, lists who shared what (names + ids only, no content). With a `from` selector (a grantId from that list), returns that person's shared profile text. SAVED BY NAME: if the user has saved a context under a short name, pass `saved` (that exact name) to pull it - the service resolves the name to the real source (a share, a teammate, a @handle, or one of the user's own projects) and re-checks access live every time. If that access is gone (revoked, expired, left the team, or closed), it returns a calm "no longer available" note instead of an error. NETWORK: if you already know a member's project @handle, pass `handle` to pull the context they have opened to the UseMyContext network - their live composite, read-only. Each @handle addresses ONE specific project, so the handle alone identifies what to read. ORGANISATION: if you and another person are members of the same UseMyContext team/organisation on an active team plan, pass `org` (the organisation id) and `member` (that teammate's member id) to read their live composite - their curated context only, never their files or facts. Profiles whose owners set them to public visibility are browsable anonymously at https://usemycontext.ai/directory; for private, shared, network, or team contexts you must already know the saved name / handle / org + member ids. Read-only; nothing is written, so it is safe to call. You only ever see what was shared with you, saved by you, opened to the network, or a teammate's context within your own organisation.

shared_context

Search the user's files by filename and return matching documents in the deep-research result shape. ALIAS: this is the SAME search as search_files (same data, same permissions) - use it when your client requires the id/title/url search contract (ChatGPT deep research); otherwise prefer search_files for richer file metadata. Each result's id can be passed to fetch (or get_file) to read that document. Read-only; nothing is written, so it is safe to call.

search

Search the user's files by filename. Returns matching file metadata (including each file's processing status), ranked by name match. Read-only; nothing is written, so it is safe to call.

search_files