| name | notion |
| description | Agent-callable Notion tools for searching pages and databases, reading and creating pages, querying data sources, appending content, and managing schemas. Use when the user mentions Notion or wants to find, read, create, or edit Notion content, even if they don't name Notion explicitly. |
| license | Elastic-2.0 |
| compatibility | Run `npm install --omit=dev` in this directory, then `node cli.js`. The TypeScript source needs Node.js 22.18+; on older Node, run `cli.js` for build-it-yourself / prebuilt / alternative-runtime options. |
| metadata | {"title":"Notion","source":"https://github.com/zapier/connectors/blob/main/apps/notion/SKILL.md","zapier-app-key":"NotionCLIAPI","api-docs":"https://developers.notion.com/reference/intro"} |
Notion
Tools for working with a Notion workspace against the Notion API (https://api.notion.com/v1/, API version 2025-09-03): find pages and data sources, read and create pages, query data-source rows, append and edit block content, manage database / data-source schemas, read and post comments. 24 scripts across search, read, write, schema, comments, and cross-workspace copy. This version uses Notion's data sources model: a database is a container that holds one or more data sources, and a data source carries the property schema + the rows (pages).
Independent, unofficial connector for Notion. Not affiliated with, endorsed by, or sponsored by Notion. "Notion" is a trademark of its owner, used only to identify the service this connector works with.
When to use this
- An agent needs to find or read content — search pages and data sources by title, then read a page, its block body, a data source's schema, or its rows.
- An agent needs to create or edit pages and content — add a page (a row in a data source or a sub-page), update properties, append blocks, or edit / delete blocks.
- An agent needs to query data sources — filter and sort the rows of a data source, or read a single page property.
- An agent needs to manage schemas — create or update databases and data sources (add / rename / retype / remove properties), read or post comments.
Setup
This is an agentskills.io skill.
If the connector has not been installed as a skill yet, install it first with npx skills add zapier/connectors --skill notion (or your harness's own skill-install mechanism), then continue here. Installing the skill copies these files, not dependencies. Before running the CLI, a local MCP server, or zapier-sdk auth commands, run npm install --omit=dev here once. Importing the published package as a dependency in your own project instead? That npm install already resolves everything — see references/use-as-sdk.md.
Want the actual repo source instead — to browse references/, run this connector's tests, or hack on it? See README.md for a scoped git clone.
The connector runs on Node.js 22.18+. Pick the reference that matches how you're running it, and load it before doing anything else:
| You have... | Load |
|---|
An MCP-aware client — tools may already be loaded (e.g. mcp__notion__<tool>), or you can register a local server yourself (or guide the user to) | references/use-as-mcp.md |
Terminal / subprocess access (you can run node) | references/use-as-cli.md |
| Only your own code, importing this package as a dependency | references/use-as-sdk.md |
| No tool access, no terminal, no ability to import this package — you write your own code that calls the Notion API directly (e.g. a code-execution sandbox) | references/use-as-recipe.md |
Scripts
All scripts use the single connection notion, except copyPage, which uses two slots (source + target) to copy a page across workspaces.
Disambiguation & refusals
Disambiguation before a write. Before writing to a page or row you looked up by name (e.g. update a page found via search, or a row found via queryDataSource), count the exact case-insensitive title matches:
- Exactly one match — act on it. Don't over-ask; a single unambiguous match is the answer.
- Two or more that tie — stop. List the tied candidates with a distinguishing field (
parent, url, or last_edited_time) and ask the user which one they mean. Don't pick arbitrarily and don't write to all of them.
Unsupported operations — say so and stop; don't fake it with another tool. This catalog deliberately does not:
- Permanently delete anything. Everything is trash / restore — pages via
updatePage in_trash, blocks via deleteBlock (reversible). There is no hard delete.
- Delete a whole database or data source. There is no tool for it. Don't substitute trashing every row to simulate it.
- Manage workspace members or permissions (inviting users, changing roles, sharing).
listUsers / getUser are read-only.
- Create or manage database views. Views aren't exposed by the API.
If asked for any of these, tell the user it's unsupported and stop — don't reach for an unrelated tool to approximate it.
Auth
Every shape passes auth as one connection selector, not the secret — a [<resolver>:]<value> string. Every connector accepts zapier:<connection-id> (Zapier-managed auth — routes through Zapier's auth, retries, and governance layer); some also accept one or more direct-token resolvers (naming and count vary per connector) — check this connector's own resolvers rather than assuming. The <resolver>: prefix is optional; a bare value goes to the first resolver that claims it — a UUID-shaped bare value always claims zapier:. Each script declares the connections it needs and the resolvers each accepts. The exact syntax for passing a connection (and how to see this connector's resolver list) differs by shape — see the reference you loaded above.
Checking what's already configured first? Don't dump environment values to do it — env or env | grep <name> prints the value along with the name, leaking a live credential into the transcript if one is set. Check names only (env | cut -d= -f1 | grep -i <name>) or test a known name directly ([ -n "$VAR_NAME" ]).
No connection yet? Pick one — and follow the reference's own flow to obtain it; never just ask the user for a connection id or token as if they already have one memorized:
Output format
Every script returns a { data, meta } envelope:
data — the script's result (the shape its outputSchema declares; see the reference you loaded above for how to inspect a script's exact schema in your shape).meta.outputDataValidation — what validating data did:
{ skipped: false, droppedPaths: null } — validated, nothing removed.{ skipped: false, droppedPaths: [...], instruction } — validated, but those paths were stripped from data: fields the script returned from the API that the outputSchema doesn't declare. If you need them, re-run with output validation skipped.{ skipped: true } — validation was bypassed; data is the raw, unchecked script output.
Reading dropped fields / skipOutputDataValidation. To receive the raw, unvalidated result, opt out of output validation (the exact syntax differs by shape — see the reference you loaded above). Input validation is never skipped.
Trimming the result / filterOutputData. To shrink a large result down to the fields you need, pass a jq expression that post-processes data (again, exact syntax per shape). The jq runs against data only, NOT the { data, meta } envelope, so write it rooted at data (run the script's --help — or your shape's equivalent — to see its output schema). The transformed value replaces data, meta is preserved, and the result is NOT re-validated against the output schema.
References
Load the matching reference file before working in that area:
| Reference | Covers | Load it when |
|---|
references/notion-api-gotchas.md | Versioning + the 2025-09-03 data-sources model, auth/sharing, the error envelope + code table, rate limits, size limits, pagination, ID/URL formats, archive/trash, search-matches-titles-only, 25-reference truncation. | Debugging an error or a 404, paginating a list, resolving an id, or reasoning about the database vs data-source split. |
references/notion-blocks.md | The typed block object, common block types, the rich_text shape, appending children (limits + nesting), why updateBlock can't change a block's type. | Building or editing page content — appendBlockChildren, createPage (children), updateBlock. |
references/notion-properties.md | The property-schema object + type list, and the per-type page property value shapes. | Defining a schema (createDatabase, createDataSource) or writing property values (createPage, updatePage). |
references/notion-query.md | The filter object (single + compound and/or), per-type conditions, the sorts array, the 10,000-result ceiling. | Calling queryDataSource with a filter or sort. |
