A Notion workspace connector for an AI coding agent. It lets the agent work with Notion pages, blocks, data sources, properties, relations, and formulas through Notion’s API.

Use it to create, read, query, and extend Notion pages and structured workspace data.

It prevents common mistakes when separating page text from page metadata and when working with Notion’s newer data-source model.

mcp-notion — Skill for Claude Code and OpenCode by MichelKerkmeester

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add MichelKerkmeester/skilled-agent-harness_spec-driven-loops --skill mcp-notion

Clone the repo

git clone --depth 1 https://github.com/MichelKerkmeester/skilled-agent-harness_spec-driven-loops

Made for: Claude Code, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/mcp-notion/github.svg)](https://agentmods.dev/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/mcp-notion)

Your own site

<a href="https://agentmods.dev/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/mcp-notion"><img src="https://agentmods.dev/badge/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/mcp-notion/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/mcp-notion"><img src="https://agentmods.dev/badge/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/mcp-notion.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 101 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 6,454 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 2 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

medium MCP Rug Pull · line 71
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Fix: Pin the version: npx @scope/[email protected]
medium MCP Rug Pull · line 267
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Fix: Pin the version: npx @scope/[email protected]

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00101	$0.06454
Opus 5	$0.00051	$0.03227
Sonnet 5	$0.00020	$0.01291
Haiku 4.5	$0.00010	$0.00645

Measured 6d ago against content hash 02b6319e96b2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

mcp-notion scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.opencode/skills/mcp-tooling/mcp-notion/SKILL.md · 461 lines

How it starts

The opening of the file, as written. The whole thing — 461 lines — stays where its author put it; the contents beside it link to each section on GitHub.

mcp-notion Skill

Notion workspace operations via the official Notion MCP (@notionhq/notion-mcp-server, 24 tools) over Code Mode, plus direct Notion API calls for the five capabilities the MCP does not expose. It knows Notion's data model at the schema layer — data sources, 22 property types, relations, rollups, Formulas 2.0 — so an agent can create, query, and extend a workspace without guessing.

MARKDOWN + DATA-SOURCE CONTRACT — READ BEFORE ANY NOTION WRITE

Two shape rules cause most Notion write failures:

Page bodies vs page properties are different surfaces. A page's content is a tree of blocks (append/update via block tools, or the markdown round-trip tools). A page's metadata is properties typed by its parent data source's schema. Writing prose into a property, or a property value into a block, fails or silently truncates.
API 2.0 replaced "databases" with "data sources" (API version 2025-09-03). A database is now a container of one or more data sources; queries, schema, relations, and rollups all target a data source id, not a database id. Using a database id where a data-source id is required is the most common 400.

Markdown round-trip tools (retrieve-page-markdown / update-page-markdown) require API version 2026-03-11 and are the token-efficient path for AI. Full detail: references/database-model.md and references/mcp-tools.md.

Failure symptom: a validation_error naming data_source_id, or property writes that vanish, means a database id was used where a data-source id was required, or content was routed to the wrong surface.

1. WHEN TO USE

Activation Triggers (explicit user phrases)

"notion", "notion mcp", "notion api", "mcp-notion"
"notion page", "notion database", "notion data source", "query notion"
"create a notion page", "add a row", "notion property", "notion relation", "notion rollup", "notion formula"
"notion token", "notion integration", "ntn_", "notion search"
"upload a file to notion", "notion view", "notion async task"

Read the full file on GitHub · 461 lines

Files

What ships with it

60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

6d ago Changed 02b6319e96b2
7d ago First seen · 461 lines · 101 tokens per session scan A 5b7d9d5577ba

Subscribe to this mod's changes

mcp-notion is a skill published in the GitHub repository MichelKerkmeester/skilled-agent-harness_spec-driven-loops (35 stars, last pushed yesterday), licensed MIT. It adds 101 tokens to every session and 6,454 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Documents Productivity

orbit-notion

Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…

nexu-io/open-design · 117 tokens

mcp-notion