Mostly Right
OnlineSearch, sample and query open reproducible datasets published as immutable Parquet with schemas.
What it can do: 80 tools
search_datasetsread-onlyRanked search over every public dataset on Mostly Right: titles, summaries, readmes, table titles and column names, most relevant first. No account needed. Example: {"query": "hourly airport weather observations", "limitget_datasetread-onlyOne dataset's overview: title, summary, topics, publisher, publication and update dates, canonical page URL, star and table counts, and up to 50 tables with their id, title, license, immutable version_id, column count, clist_tablesread-onlyThe 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 {dataset_slug, main_table, tables: [{id, slug,get_table_schemaread-onlyOne public 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 sampling, keyed querying and Parquet dosample_rowsread-onlyThe publisher's materialized preview of a public table — real rows, no account, no query cost. Private workspace tables are not available here; use query_run on a successful build instead. To sample a source before anythget_download_instructionsread-onlyThe 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-4a63-4f75-9a0b-1a7d9c5b2e10"}. Bytes are neverget_access_instructionsread-onlyWhat 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' to 'querying rows'. Optionally pass {"dasearchread-onlySearch every public dataset on Mostly Right and return up to 20 matches, most relevant first, as {results: [{id, title, url, snippet, matching_table, why}]}, where `id` is the dataset slug, `url` its canonical page, andfetchread-onlyThe 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. Example: {"id": "kden-metar-hourly"} — the `iquery_tableread-onlyA 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...", "columns": ["observed_at", "air_temp_f"], "fsearch_tableread-onlyRanked search over one public table's rows, the same search its dataset page runs: words, prefixes, typos and spelling correction, served from the table's search package. NOT a catalogue search (search_datasets finds datcatalog_searchread-onlySearch 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": "county unemployment rate monthly", "limitlist_connected_datasetsread-onlyThe 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 use) and the workspace's own tables; anconnect_datasetConnects 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": "kden-metar-hourly"}. Idempotent: connectingcreate_datasetCreates 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 is the point — the page opens on it andconfigure_dataset_layoutSave ordered sections, table display titles and descriptions, collapsed sections, a separate default opening table and an optional search_table_id. search_table_id names the table the dataset's Search dialog opens on wheconfigure_table_viewSaves one versioned contextual view for this table after its first successful build. Inspect its intent, actual schema and a bounded sample first. Prefer table for wide numeric/comparison data or when a specialized templupdate_datasetmain_table_id names the table the dataset page leads with: the Data tab opens on it and the other tables keep their configured sections, or are listed as helpers when no layout is configured. Use configure_dataset_layoutgenerate_coverGenerates the dataset's branded 1200×630 cover and attaches it: the page, the Community tile and the share card all wear it. Every dataset gets exactly one, generated once its description is written. Call it only for a dset_dataset_visibilityChanges who can read a dataset: private (this workspace only), link (anyone holding an unlisted address, which this returns) or public (listed on Mostly Right for anyone). The same change as Share on the dataset's page aarchive_datasetRetires a whole dataset: every reader loses access, its public page and unlisted link are withdrawn, and its name is free for a new dataset. Nothing it built is deleted, but ONLY Mostly Right support can restore it. Thelist_my_datasetsread-onlyEvery 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: {"limit": 25}. Returns {workspace_id, dataget_my_datasetread-onlyOne 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 confirmation. Example: {"dataset_id": "…"list_dataset_eventsread-onlyThe dataset's own durable log, newest first: created, renamed or re-described, a recipe registered, each run queued, held, started, progressing and finished, a cover attached, a table's state changing, a table renamed orlist_recipesread-onlyLists immutable recipe coordinates in this workspace, optionally for one table_id from get_my_dataset. current_only defaults to true; false includes older revisions. Returns {recipes: [{recipe_id, recipe_digest, dataset_get_reciperead-onlyReads the actual immutable registered recipe, including sources, SQL and checks. Use list_recipes for current table revisions, or recipe_id from get_run for the exact executed revision. Returns {recipe_id, recipe_digest,register_recipeRegisters 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 cannot and must not state one. Identical byexplain_reciperead-onlyChecks a recipe document without registering, writing or running anything — the same evaluator that admits refreshes, plus the fast-path features the harness's `recipe explain` reports. Example: {"recipe": { …the whole rforecast_reciperead-onlySays what one full or refresh run of a registered recipe would ask of its sources, before anything is started: per-source request ceilings, runtime at the ceiling, platform spend, and the projected bytes and cost. Warnintest_recipeStarts a recipe preflight: a bounded rehearsal of a full run that fetches at most max_pages_per_source pages of each listing (default 1, max 5) and max_upstream_rows rows of each per-row source (default 25), runs the trapropose_revisionRegisters 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 inputs, which reads no upstream source and nereplay_runRuns 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 inputs must still be retained. Returns {start_runRuns 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 acquisition with an inspection checkpoint aftconfirm_runAuthorizes 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 projection. Example: {"run_id": "…", "expectedapprove_full_runCompatibility 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 their inspection checkpoint. Call it ONLYcancel_runStops 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 cancelled. A run that already finished cannot beget_runread-onlyOne 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 version it sealed, the failure code and strun_eventsread-onlyOpens 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 watch a build without polling. Example: {"list_runsread-onlyThe 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: [{run_id, status, mode, dataset_id, table_compare_runsread-onlyReads two runs and says what changed between them: status, mode, rows, bytes, truncated, covered_window, table_version_id, outcome, failure code and stage, created and completed times, and each declared check whose resul
…and 40 more.
Connect it
claude mcp add --transport http mostly-right https://mostlyright.md/api/mcpSettings → Connectors → Add custom connector
URL: https://mostlyright.md/api/mcp{
"mcpServers": {
"mostly-right": {
"url": "https://mostlyright.md/api/mcp"
}
}
}{
"servers": {
"mostly-right": {
"type": "http",
"url": "https://mostlyright.md/api/mcp"
}
}
}Questions
What does Mostly Right do?
Search, sample and query open reproducible datasets published as immutable Parquet with schemas. It exposes 80 tools to AI assistants.
What tools does Mostly Right provide?
80 tools, including search_datasets, get_dataset, list_tables, get_table_schema, sample_rows, get_download_instructions, get_access_instructions, search, fetch, query_table, search_table, catalog_search….
How do I connect Mostly Right to Claude, ChatGPT or Cursor?
Add the remote MCP endpoint https://mostlyright.md/api/mcp as a custom connector or MCP server. Copy-paste setup is on this page.
Does Mostly Right require an account or API key?
No sign-in was needed to list its tools. Individual tools may still need an account or API key.
Is Mostly Right online?
As of 2026-11-19 our probe found it online. It answered 100% of our last 3 checks.
Who publishes Mostly Right?
mostlyright.md. The official MCP Registry verified that the publisher controls this domain before accepting the listing.
Similar in Databases & Data
-
Google FirestoreOnlineOfficialPopular
Interact with your Google Cloud Firestore resources using natural language commands.
-
Google SqladminOnlineOfficialPopular
Create, manage, and query your Google Cloud SQL resources.
-
SupabaseOnline · sign-in requiredOfficialPopular
MCP server for interacting with the Supabase platform
-
STRING Database MCP ServerOnlineOfficial
Query STRING interactions, enrichment, annotations, homology, and PPI networks.
-
Horizon Brand Authority MCPOnline · sign-in requiredOfficial
Grounded Horizon Media brand Q&A for AI assistants. Authenticated MCP; brand_authority_query.
-
Idescat MCP ServerOnlineOfficial
Query official statistics of Catalonia (Idescat): tables, metadata and JSON-stat data via MCP.