Skip to main content
Glama
peakmojo

Zoom Recordings No-Auth

by peakmojo

zoom_list_recordings

Retrieve paginated Zoom cloud recordings for a user by specifying start and end dates, page size, and number. Uses an OAuth2 token for secure access to the Zoom account.

Instructions

List Zoom cloud recordings from a user's Zoom account with pagination support

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
from_dateNoStart date for Zoom recording search in 'YYYY-MM-DD' format
page_numberNoPage number of Zoom recordings to return (default: 1)
page_sizeNoNumber of Zoom recordings to return per page (default: 30, max: 300)
to_dateNoEnd date for Zoom recording search in 'YYYY-MM-DD' format
zoom_access_tokenYesZoom OAuth2 access token

Implementation Reference

  • Core handler function in ZoomClient class that fetches and returns list of cloud recordings using Zoom API endpoint /users/me/recordings with support for date filtering and pagination.
    def list_recordings(self, from_date: Optional[str] = None, to_date: Optional[str] = None, 
                        page_size: int = 30, page_number: int = 1) -> str:
        """List cloud recordings from Zoom
        
        Args:
            from_date: Start date for recording search in 'YYYY-MM-DD' format
            to_date: End date for recording search in 'YYYY-MM-DD' format
            page_size: Number of records to return per page (default: 30, max: 300)
            page_number: Page number to return (default: 1)
            
        Returns:
            JSON string with recordings data
        """
        try:
            # Define the operation
            def _operation():
                logger.debug(f"Fetching recordings with page_size={page_size}, page_number={page_number}")
                
                # Prepare query parameters
                params = {
                    "page_size": min(page_size, 300),  # Zoom API limits to 300 max
                    "page_number": page_number
                }
                
                if from_date:
                    params["from"] = from_date
                if to_date:
                    params["to"] = to_date
                
                # Get user's recordings (me = current authenticated user)
                response = requests.get(
                    f"{self.base_url}/users/me/recordings",
                    headers=self._get_headers(),
                    params=params
                )
                
                if response.status_code != 200:
                    return json.dumps({
                        "error": f"Failed to retrieve recordings. Status code: {response.status_code}",
                        "details": response.text,
                        "status": "error"
                    })
                
                recordings_data = response.json()
                
                # Process and return recordings
                return json.dumps(convert_datetime_fields(recordings_data))
            
            # Execute the operation with token refresh handling
            return self._handle_token_refresh(_operation)
                
        except Exception as e:
            logger.error(f"Exception in list_recordings: {str(e)}", exc_info=True)
            return json.dumps({"error": str(e)})
  • Tool registration in MCP server's list_tools method, defining name, description, and input schema for zoom_list_recordings.
    types.Tool(
        name="zoom_list_recordings",
        description="List Zoom cloud recordings from a user's Zoom account with pagination support",
        inputSchema={
            "type": "object",
            "properties": {
                "zoom_access_token": {"type": "string", "description": "Zoom OAuth2 access token"},
                "from_date": {"type": "string", "description": "Start date for Zoom recording search in 'YYYY-MM-DD' format"},
                "to_date": {"type": "string", "description": "End date for Zoom recording search in 'YYYY-MM-DD' format"},
                "page_size": {"type": "integer", "description": "Number of Zoom recordings to return per page (default: 30, max: 300)"},
                "page_number": {"type": "integer", "description": "Page number of Zoom recordings to return (default: 1)"}
            },
            "required": ["zoom_access_token"]
        },
    ),
  • Dispatch handler within the MCP call_tool function that parses arguments, initializes ZoomClient, and calls list_recordings for the zoom_list_recordings tool.
    if name == "zoom_list_recordings":
        # Initialize Zoom client with just access token
        logger.debug(f"Initializing Zoom client for list_recordings with access token: {access_token[:10]}...")
        try:
            zoom = ZoomClient(
                access_token=access_token
            )
            logger.debug("Zoom client initialized successfully")
            
            from_date = arguments.get("from_date")
            to_date = arguments.get("to_date")
            page_size = int(arguments.get("page_size", 30))
            page_number = int(arguments.get("page_number", 1))
            
            logger.debug(f"Calling list_recordings with from_date={from_date}, to_date={to_date}, page_size={page_size}, page_number={page_number}")
            results = zoom.list_recordings(from_date=from_date, to_date=to_date, 
                                           page_size=page_size, page_number=page_number)
            logger.debug(f"list_recordings result (first 200 chars): {results[:200]}...")
            return [types.TextContent(type="text", text=results)]
        except Exception as e:
            logger.error(f"Exception in zoom_list_recordings handler: {str(e)}", exc_info=True)
            return [types.TextContent(type="text", text=f"Error: {str(e)}")]
  • JavaScript implementation of the listRecordings method in ZoomClient class that fetches Zoom cloud recordings using the API.
    async listRecordings({ from_date, to_date, page_size = 30, page_number = 1 } = {}) {
      try {
        const operation = async () => {
          logger.debug(`Fetching recordings with page_size=${page_size}, page_number=${page_number}`);
          
          const params = {
            page_size: Math.min(page_size, 300),
            page_number: page_number
          };
          
          if (from_date) params.from = from_date;
          if (to_date) params.to = to_date;
          
          const response = await axios.get(
            `${this.baseUrl}/users/me/recordings`,
            {
              headers: this._getHeaders(),
              params
            }
          );
          
          if (response.status !== 200) {
            return JSON.stringify({
              error: `Failed to retrieve recordings. Status code: ${response.status}`,
              details: response.data,
              status: "error"
            });
          }
          
          return JSON.stringify(response.data);
        };
        
        return await this._handleTokenRefresh(operation);
      } catch (error) {
        logger.error(`Exception in listRecordings: ${error.message}`);
        return JSON.stringify({ error: error.message });
      }
    }
  • server.js:332-356 (registration)
    JavaScript MCP server.tool registration for zoom_list_recordings, including Zod schema and inline handler function.
    server.tool(
      'zoom_list_recordings',
      'List Zoom cloud recordings from a user\'s Zoom account with pagination support',
      {
        zoom_access_token: z.string().describe('Zoom OAuth2 access token'),
        from_date: z.string().optional().describe('Start date for Zoom recording search in \'YYYY-MM-DD\' format'),
        to_date: z.string().optional().describe('End date for Zoom recording search in \'YYYY-MM-DD\' format'),
        page_size: z.number().optional().describe('Number of Zoom recordings to return per page (default: 30, max: 300)'),
        page_number: z.number().optional().describe('Page number of Zoom recordings to return (default: 1)')
      },
      async ({ zoom_access_token, from_date, to_date, page_size = 30, page_number = 1 }) => {
        try {
          const zoom = new ZoomClient({ accessToken: zoom_access_token });
          logger.error(`listing recordings with from_date=${from_date}, to_date=${to_date}, page_size=${page_size}, page_number=${page_number}`);
          const result = await zoom.listRecordings({ from_date, to_date, page_size, page_number });
          return {
            content: [{ type: 'text', text: result }]
          };
        } catch (error) {
          return {
            content: [{ type: 'text', text: `Error: ${error.message}` }]
          };
        }
      }
    );
Behavior2/5

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions 'pagination support' which is a useful behavioral trait, but fails to disclose critical aspects such as authentication requirements (though implied by the zoom_access_token parameter), rate limits, error handling, or what the output format looks like (e.g., list structure, fields included). For a tool with 5 parameters and no annotations, this leaves significant gaps in understanding how it behaves.

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

Conciseness5/5

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

The description is a single, efficient sentence that front-loads the core purpose ('List Zoom cloud recordings') and includes key features ('from a user's Zoom account with pagination support'). There is zero waste—every word contributes to understanding the tool's function without redundancy or unnecessary elaboration.

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

Completeness2/5

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

Given the complexity (5 parameters, no annotations, no output schema), the description is incomplete. It lacks details on authentication (beyond the token parameter), output format, error cases, or usage constraints. While it mentions pagination, it doesn't describe how pagination works in practice (e.g., total pages, next token). For a tool that likely returns structured data, this leaves the agent with insufficient context to use it effectively.

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

Parameters3/5

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

Schema description coverage is 100%, meaning all parameters are well-documented in the input schema itself (e.g., date formats, defaults, max values). The description adds no additional parameter semantics beyond what's in the schema—it doesn't explain relationships between parameters (e.g., how from_date and to_date interact) or provide usage examples. With high schema coverage, the baseline is 3, as the description doesn't compensate but also doesn't detract.

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

Purpose4/5

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

The description clearly states the verb ('List') and resource ('Zoom cloud recordings') with the scope ('from a user's Zoom account') and mentions pagination support. It distinguishes from siblings like zoom_get_recording_details (which gets details of a specific recording) and zoom_get_meeting_transcript (which gets transcripts), but doesn't explicitly differentiate from zoom_refresh_token (which is unrelated). The purpose is specific but could be slightly more precise about what 'list' entails.

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

Usage Guidelines3/5

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

The description implies usage for retrieving recordings with date filtering and pagination, but provides no explicit guidance on when to use this tool versus alternatives like zoom_get_recording_details for specific recordings or zoom_refresh_token for token management. It mentions pagination support, which hints at usage for large datasets, but lacks clear when/when-not scenarios or prerequisites beyond the implied need for a Zoom account.

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

Related 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/peakmojo/mcp-server-zoom-noauth'

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