Skip to main content
Glama

search

Search Notion workspaces for pages and databases using query filters to find specific content within your workspace.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryNoThe search query string
filter_object_typeNoFilter by object type
page_sizeNoNumber of results to return (max 100)

Implementation Reference

  • The main execution logic for the MCP 'search' tool: prepares params from user input, invokes NotionService.search, formats results as text content or error response.
    async ({ query, filter_object_type, page_size }) => {
      const params: any = { page_size };
      if (query) params.query = query;
      if (filter_object_type) {
        params.filter = {
          property: "object",
          value: filter_object_type,
        };
      }
    
      try {
        const results = await this.notionService.search(params);
        return {
          content: [
            {
              type: "text",
              text: JSON.stringify(results, null, 2),
            },
          ],
        };
      } catch (error) {
        console.error("Error in search tool:", error);
        return {
          content: [
            {
              type: "text",
              text: `Error: Failed to search Notion - ${
                (error as Error).message
              }`,
            },
          ],
          isError: true,
        };
      }
    }
  • Zod input validation schema for the 'search' tool parameters.
    {
      query: z.string().optional().describe("The search query string"),
      filter_object_type: z
        .enum(["page", "database"])
        .optional()
        .describe("Filter by object type"),
      page_size: z
        .number()
        .min(1)
        .max(100)
        .optional()
        .describe("Number of results to return (max 100)"),
    },
  • Full registration of the 'search' tool using this.server.tool(), including schema and handler function.
    private registerSearchTool(): void {
      this.server.tool(
        "search",
        {
          query: z.string().optional().describe("The search query string"),
          filter_object_type: z
            .enum(["page", "database"])
            .optional()
            .describe("Filter by object type"),
          page_size: z
            .number()
            .min(1)
            .max(100)
            .optional()
            .describe("Number of results to return (max 100)"),
        },
        async ({ query, filter_object_type, page_size }) => {
          const params: any = { page_size };
          if (query) params.query = query;
          if (filter_object_type) {
            params.filter = {
              property: "object",
              value: filter_object_type,
            };
          }
    
          try {
            const results = await this.notionService.search(params);
            return {
              content: [
                {
                  type: "text",
                  text: JSON.stringify(results, null, 2),
                },
              ],
            };
          } catch (error) {
            console.error("Error in search tool:", error);
            return {
              content: [
                {
                  type: "text",
                  text: `Error: Failed to search Notion - ${
                    (error as Error).message
                  }`,
                },
              ],
              isError: true,
            };
          }
        }
      );
    }
  • Helper method in NotionService that calls the underlying Notion Client search API and handles errors.
    async search(params: SearchQuery) {
      try {
        return await this.client.search(params);
      } catch (error) {
        this.handleError(error);
      }
    }
  • Zod schema and TypeScript type definition for SearchQuery parameters used by the NotionService.search helper.
    export const SearchQuerySchema = z.object({
      query: z.string().optional(),
      filter: z
        .object({
          value: z.enum(["page", "database"]),
          property: z.literal("object"),
        })
        .optional(),
      sort: z
        .object({
          direction: z.enum(["ascending", "descending"]),
          timestamp: z.enum(["last_edited_time"]),
        })
        .optional(),
      page_size: z.number().min(1).max(100).optional(),
    });
    
    export type SearchQuery = z.infer<typeof SearchQuerySchema>;
Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Tool has no description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness1/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Tool has no description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool has no description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Tool has no description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/ramidecodes/mcp-server-notion'

If you have feedback or need assistance with the MCP directory API, please join our Discord server