{{One-sentence what-it-does + when to use it. Mention it bypasses the MCP via the REST API with {{ENV_VAR}}. Use when the user wants X, Y, Z programmatically without the {{service}} MCP installed.}}
中文简介正在准备中。当前显示原文说明。
Read and write Notion pages, databases, and blocks via the public REST API — query a database with filters, create/update pages, append block content, search the workspace. Use when the user wants an agent to interact with their Notion workspace (e.g., a tasks or docs database) without the MCP server installed.
中文简介正在准备中。当前显示原文说明。
安装前可以查看交给 AI 代理的指令内容。
Direct REST access to Notion pages, databases, blocks, and search — no MCP server. Use when the user wants the agent to query or mutate their workspace (e.g. a tasks DB). The hard part is the response shapes, not auth: property values are wrapped per-type and text is rich-text arrays, not strings.
[ -n "${NOTION_API_KEY:-${NOTION_TOKEN:-$NOTION_INTEGRATION_TOKEN}}" ] && echo "NOTION_API_KEY: PRESENT" || echo "NOTION_API_KEY: MISSING"
Never echo the variable directly — the value would appear in the conversation transcript. Use only the boolean pattern above.
If MISSING, respond to the user with EXACTLY this message (do NOT paraphrase, do NOT suggest manual JSON edits):
I need your notion credential. Run this in another terminal — it'll open the signup page, validate format, and save it safely with masked input:
teleport-setup add-key notionThen restart Claude Code (
/exit, thenclaude) and ask me again.
Do NOT suggest editing ~/.claude/settings.local.json manually. The teleport-setup add-key command handles it with backup, validation, and masked input. Stop execution until the user has run the command and restarted.
https://api.notion.com/v1Authorization: Bearer $NOTION_API_KEYNotion-Version: 2026-03-11 header is REQUIRED — missing it returns 400 missing_version.application/json on POST/PATCH.429 rate_limited + Retry-After on excess. Payload caps: 500KB, 100 items per array, 2000 chars per rich-text object.••• → Connections → add integration). Unshared = 404 object_not_found.Three objects: page (has properties map if in a database, parent tells location; content blocks are NOT returned — separate GET /blocks/{page_id}/children), database (has properties schema: column name → type def; exactly one title column), block (ordered children on any page; 30+ types incl. paragraph, heading_1/2/3, to_do, toggle, code, callout, image, table). Text-bearing fields are always arrays of rich-text objects, never plain strings — on write, only text.content is required.
| Column type | Write shape |
|---|---|
title / rich_text | {"title": [{"text": {"content": "Hello"}}]} |
number | {"number": 42} |
select / status | {"select": {"name": "Done"}} — name OR id |
multi_select | {"multi_select": [{"name": "A"}, {"name": "B"}]} |
date | {"date": {"start": "2026-04-24", "end": null, "time_zone": null}} |
checkbox | {"checkbox": true} |
relation / people | {"relation": [{"id": "page-uuid"}]} — UUIDs only |
url / email / phone_number | {"url": "https://..."} (raw string) |
formula / rollup | Read-only — computed by Notion |
Bare strings like {"Name": "Hello"} always 400. You need {"Name": {"title": [{"text": {"content": "Hello"}}]}}.
| Resource | Method · Path |
|---|---|
| Databases | POST /databases/{id}/query, GET/POST/PATCH /databases/{id} |
| Pages | GET /pages/{id}, POST /pages, PATCH /pages/{id} |
| Properties | GET /pages/{id}/properties/{prop_id} (single prop when >25 entries) |
| Blocks | GET/PATCH /blocks/{id}/children, PATCH/DELETE /blocks/{id} |
| Search | POST /search (workspace-wide, pages + data sources) |
| Users | GET /users, /users/{id}, /users/me (me = the bot itself) |
# Query with compound filter + sort + pagination
curl -sL -X POST -H "Authorization: Bearer $NOTION_API_KEY" \
-H "Notion-Version: 2026-03-11" -H "Content-Type: application/json" \
"https://api.notion.com/v1/databases/{database_id}/query" \
-d '{"filter": {"and": [
{"property": "Status", "select": {"equals": "In progress"}},
{"property": "Due", "date": {"on_or_before": "2026-04-30"}}
]},
"sorts": [{"property": "Due", "direction": "ascending"}],
"page_size": 100, "start_cursor": "<next_cursor-if-any>"}'
# Response: {results: [pages...], next_cursor, has_more}. Loop until has_more=false.
# Create a page (property keys must match schema, case-sensitive)
curl -sL -X POST -H "Authorization: Bearer $NOTION_API_KEY" \
-H "Notion-Version: 2026-03-11" -H "Content-Type: application/json" \
"https://api.notion.com/v1/pages" \
-d '{"parent": {"database_id": "{database_id}"},
"properties": {
"Name": {"title": [{"text": {"content": "Ship v2"}}]},
"Status": {"select": {"name": "In progress"}},
"Due": {"date": {"start": "2026-05-01"}}},
"children": [
{"object":"block","type":"paragraph",
"paragraph":{"rich_text":[{"text":{"content":"Kickoff notes."}}]}}]}'
Filter operators are per-property-type (mirror the write wrappers): select/status → {equals, does_not_equal, is_empty}; multi_select → {contains, does_not_contain}; date → {equals, before, on_or_before, past_week: {}, next_month: {}}; compound {and: [...]} / {or: [...]} nests up to two levels.
To update: PATCH /pages/{id} with only the properties to change, e.g. {"properties": {"Status": {"select": {"name": "Done"}}}}. To append blocks: PATCH /blocks/{page_id}/children with {"children": [block, ...]} (max 100 per call).
{"Name": "Hello"} fails; title needs {"title": [{"text": {"content": "Hello"}}]}. Single most common bug.••• → Connections → add.Notion-Version: 2026-03-11 is mandatory. Omitting returns 400 missing_version. Bump deliberately after reading the changelog.has_children: true hides the subtree — recurse GET /blocks/{id}/children for nested toggles, columns, lists until exhausted.start_cursor ← previous next_cursor until has_more: false. Don't assume one call returns everything.Retry-After.When done, state: Used skill: Notion (from teleport catalog).
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
{{One-sentence what-it-does + when to use it. Mention it bypasses the MCP via the REST API with {{ENV_VAR}}. Use when the user wants X, Y, Z programmatically without the {{service}} MCP installed.}}
中文简介正在准备中。当前显示原文说明。
Manage Cloudflare DNS zones, Workers, Pages, R2, KV, D1, and analytics via REST API. Use when the user wants to query DNS, deploy a Worker, list R2 buckets, manage KV namespaces, run D1 queries, or check analytics without the Cloudflare MCP installed.
中文简介正在准备中。当前显示原文说明。
Fetch up-to-date library, framework, and SDK documentation via Context7's search and docs endpoints. Use when the user asks about a library/API (React, Next.js, Prisma, Supabase, Tailwind, Django, Vue, etc.) and you need current docs, not Claude's training-time knowledge. Skip this skill for generic programming questions that don't require library-specific docs.
中文简介正在准备中。当前显示原文说明。
Operate Discord via its REST API — post/read channel messages, manage guilds + roles, fire webhooks, register slash commands. Use when the user wants a bot to post to a channel, read recent history, run a community admin task, or ship one-way notifications via webhook URL without running a bot process.
中文简介正在准备中。当前显示原文说明。
AI-first web search via Exa — semantic/neural ranking, category-scoped results, fresh content retrieval, and one-shot answer synthesis with citations. Use when the user needs current web information better ranked than general web search, or a grounded answer with sources.
中文简介正在准备中。当前显示原文说明。
Read Figma files, component libraries, styles, comments, and export rendered assets (PNG / SVG / JPG / PDF) via Figma's REST API. Use when the user needs programmatic access to design files, to pull node data into code generation, or to export assets without opening the Figma desktop app.
中文简介正在准备中。当前显示原文说明。