Perform a search over: - "internal": Perform a semantic search over your entire Notion workspace and connected sources (Slack, Google Drive, Github, Jira, Microsoft Teams, Sharepoint, OneDrive, or Linear). - "users": Perform a search over the Notion users in the current workspace. You can use sea...
Accepts freeform code/query input (query)
Part of the Notion MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents call search to retrieve information from Notion without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though search only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
tools:
search:
rules:
- action: allowSee the full Notion policy for all 24 tools.
Agents calling read-class tools like search have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Read risk category across the catalogue. The same policy patterns (rate-limit, allow) apply to each.
Perform a search over: - "internal": Perform a semantic search over your entire Notion workspace and connected sources (Slack, Google Drive, Github, Jira, Microsoft Teams, Sharepoint, OneDrive, or Linear). - "users": Perform a search over the Notion users in the current workspace. You can use search when you need to find information which is not already available via other tools, and you don't know where it's located. If the user doesn't have access to Notion AI features, the search will automatically fall back to a workspace search that doesn't use AI or include connected sources. This will be indicated by the "type" field in the response being "workspace_search" instead of "ai_search". Do NOT use search to get information about a Database's integrations, views, or other components. If initial results do not contain all the information you need, you can try more specific queries. After obtaining internal search results, if the user asks for the full contents of a page or database, use the "fetch" tool. This tool only shows some details like a highlight and the URL and title of each search result. To find pages under a Notion database, use this tool and supply the database's URL as the data_source_url parameter. These look like "collection://f336d0bc-b841-465b-8045-024475c079dd". You can get this URL by using the "fetch" tool to view the database and copying the URL from the <data-source url="..."> block. Keep in mind that Notion-flavored Markdown has this concept of a hierarchy of <database> blocks that contain <data-source> blocks, but users aren't familiar with the Notion "Data Source" terminology or product. Prefer to refer to both of them as "databases" in your response to humans to avoid confusion. Examples of searches: 1. Search for information across the workspace: { "query": "quarterly revenue report", "query_type": "internal" } 2. Search within a specific page and its children: { "query": "meeting notes action items", "query_type": "internal", "page_url": "https://www.notion.so/workspace/Team-Hub-1234567890abcdef" } 3. Search within a database's pages: { "query": "design review feedback", "query_type": "internal", "data_source_url": "collection://f336d0bc-b841-465b-8045-024475c079dd" } 4. Search within a specific teamspace: { "query": "project updates", "query_type": "internal", "teamspace_id": "f336d0bc-b841-465b-8045-024475c079dd" } 5. Search for users: { "query": "john@example.com", "query_type": "user" } 6. Find users by partial name: { "query": "sarah", "query_type": "user" } Common use cases: - "What does the sales team require from the product team in the next quarter?" - "Find all meeting notes that mention the new pricing strategy" - "Which pages discuss the API migration project?" - "Find all team members with email addresses ending in @design.company.com" - "What are the latest updates on the mobile app redesign?". It is categorised as a Read tool in the Notion MCP Server, which means it retrieves data without modifying state.
Add a rule in your Intercept YAML policy under the tools section for search. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Notion MCP server.
search is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the search rule in your Intercept policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the Intercept policy for search. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
search is provided by the Notion MCP server (@notion-mcp-server). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Open source. One binary. Zero dependencies.
npx -y @policylayer/intercept