MCP servermd.mostlyright/datasets
Search, sample and query open reproducible datasets published as immutable Parquet with schemas.
Overview
Score?
UNRATED 0.685
of what a free look can see, on 21 looks
Looks
24
last 4 hr ago
Tools
38
changed 4 days ago
More info
URL
mostlyright.md/api/mcp
streamable-http
Says it is
mostlyright 2.0.0
protocol 2025-06-18
In the record since
22 days ago
Among servers18,413 with a card
0median 0.606 · this server 0.685 · highest on record 0.8561
Toolsfrom sha256:27d33d1e5c…a8fedc · +0 −0 4 days ago
| Tool | Schema |
|---|---|
| approve_full_run Compatibility for an existing legacy full run paired with a bounded preview, in awaiting_sample_approval. New full builds use progressive acquisition and never need this tool for t |
input · no output |
| cancel_run Stops a run that is queued, held at the confirmation gate, or running. A run cancelled at the gate never ran. Example: {"run_id": "…"}. Returns the run receipt with status cancelle |
input · no output |
| catalog_search Search a sealed snapshot of public data sources for feeds that might answer a question — the first move when you need a source and do not already know one. Example: {"question": "c |
input · no output |
| confirm_run Authorizes a held run and starts it. The numbers are the ones already stored on the run — you cannot restate them, which is the point: what is authorized is the server's own projec |
input · no output |
| connect_dataset Connects one public dataset to the authenticated workspace so its tables become queryable and downloadable. This is the gate every keyed read passes. Example: {"dataset_slug": "kde |
input · no output |
| create_dataset Creates an empty dataset in your workspace and returns its ids. A dataset is the container a recipe binds to; it exists before it has a description, a recipe or a single row, which |
input · no output |
| diagnose_table Reads one table's current promotion pointers and latest recorded failure. When that failure names a run, it also reads that run and its declared recipe sources, so the diagnosis st |
input · no output |
| fetch The full public document for one dataset as Markdown: summary, facts, access instructions, and every table with its columns, types, descriptions and units. No account needed. Examp |
input · no output |
| get_access_instructions What this server does anonymously, what needs an account, the two API key classes and what each unlocks, the OAuth option, the signup URL, and the numbered steps from 'no account' |
input · no output |
| get_artifact_download Mints a short-lived signed URL for one sealed artifact. Fetch it yourself with a plain GET and no headers; it expires. Example: {"run_id": "…", "artifact_id": "…"}. Returns {url, e |
input · no output |
| get_dataset One dataset's overview: title, summary, topics, publisher, publication and update dates, canonical page URL, star and table counts, and every table with its id, title, license, imm |
input · no output |
| get_download_instructions The exact URL, HTTP method and header for downloading one table's current immutable Parquet snapshot, plus whether the publisher enabled it. Example: {"table_id": "0f2f6bfa-4a63-4f |
input · no output |
| get_my_dataset One workspace dataset in build terms: name, description, status, each table with its build state, promotion state and live version, the latest run, and any run held waiting for a c |
input · no output |
| get_run One run's current state: status, mode, the clamps it ran under, rows delivered and whether a clamp truncated them, how many pages a many-page source reached, the table and table ve |
input · no output |
| get_source_inspection Reads one source inspection by session_id and probe_id. Returns bounded evidence with status queued, complete, truncated or failed. A missing legacy endpoint is reported as capabil |
input · no output |
| get_table One table as the builder sees it: whether it is promoted, which version is live, the refresh schedule and what the platform has learned about its rhythm, when it last refreshed and |
input · no output |
| get_table_schema One table's columns (name, type, and any published profile such as null counts, distinct counts or ranges), its immutable version_id, and its capabilities: whether anonymous sampli |
input · no output |
| list_connected_datasets The public datasets the authenticated workspace has used so far. Takes no arguments. query_table is not limited to this list: a key reads any public dataset (connecting it on first |
input · no output |
| list_my_datasets Every dataset this workspace owns, most recently updated first — not the public catalog. Use it to find the dataset_id for a dataset you or a colleague created earlier. Example: {" |
input · no output |
| list_runs The workspace's own runs, newest first, optionally narrowed to one dataset, one status or one mode. Example: {"dataset_id": "…", "status": "failed", "limit": 20}. Returns {runs: [{ |
input · no output |
| list_source_credentials The NAMES of the API keys and passwords this workspace has stored for its sources, with their status and when they were added. Never a value — no secret ever crosses this server. T |
input · no output |
| list_tables The tables in one dataset, without the full column schemas — the cheap call when you only need table ids and titles. Example: {"dataset_slug": "kden-metar-hourly"}. Returns {datase |
input · no output |
| normalize_reader_options Resolves the certified Reader family and version and returns default-filled canonical decode options. Validates options only; it does not acquire or decode bytes. Returns family_id |
input · no output |
| promote_table Promotion makes the table's newest passing version the version everyone reads, and starts the recurring refresh that keeps it current. Example: {"table_id": "…", "confirm": true}. |
input · no output |
| propose_revision Registers a proposed revision and returns its immutable recipe coordinates plus a review link. It then starts EXACTLY ONE run: a replay of the named successful run's retained input |
input · no output |
| query_run Runs one read-only SQL statement over the parquet a run sealed, and waits for the answer. THIS IS HOW YOU CHECK THE DATA IS RIGHT before promoting anything: count the rows, look at |
input · no output |
| query_table A bounded, structured query over one table's current version. NO SQL: send columns, filters, order_by, aggregates, group_by and limit as JSON. Example: {"table_id": "0f2f...", "col |
input · no output |
| register_recipe Registers the JSON recipe that says where the data comes from, how it is shaped and what must be true of it. The server canonicalizes the document and computes its digest — you can |
input · no output |
| replay_run Runs a registered recipe revision against the retained raw inputs of a named successful run of the same table. No upstream acquisition is performed. Replay must be enabled and the |
input · no output |
| run_artifacts The files a run sealed: the parquet, the column profile, the receipt, the preview. Works on a running, succeeded or failed run — a failed run's partial output is listed too. Exampl |
input · no output |
| run_events Opens the run's event stream, collects up to max_events, and returns as soon as the run reaches a terminal event or wait_seconds elapses — whichever comes first. This is how you wa |
input · no output |
| sample_rows The publisher's materialized preview of a table — real rows, no account, no query cost. 20 rows by default, 100 at most, and they are always the same rows: this is a sample for und |
input · no output |
| search Search every public dataset on Mostly Right and return up to 20 matches as {results: [{id, title, url}]}, where `id` is the dataset slug and `url` its canonical page. No account ne |
input · no output |
| search_datasets Full-text search over every public dataset on Mostly Right. No account needed. Example: {"query": "hourly airport weather observations", "limit": 10}. Returns {datasets: [{id, slug |
input · no output |
| start_run Runs a registered recipe. THIS IS THE TOOL THAT DOES THE REAL WORK: it reads the sources and can run for a long time. Start builds in full mode: full runs use one progressive acqui |
input · no output |
| start_source_inspection Prepares an HTTPS source, opens a bounded research session and queues a source_inspect probe. Returns session_id, probe_id, source_id and limits; it does not write a recipe. If unc |
input · no output |
| update_dataset A changed nonblank description generates a factual dataset name and topic tags, except a name or tags someone chose in an earlier update, which stay. The name given at create_datas |
input · no output |
| write_note Appends one cell to a run's or a dataset's decision record — why a source was chosen, what a check found, what you changed and why. The record is append-only and is what a reader s |
input · no output |
Verify it yourself
npx teppi-check https://mostlyright.md/api/mcpcurl -s https://api.teppi.xyz/v1/trust/mcp/mcs_01M29XADA0K5ZHTBJ2D3C9668E