// SCAN REPORT

Mcp Taskade

57 tools. 32 can modify or destroy data without limits.

7 destructive tools with no built-in limits. Policy required.

Last updated: 11 Jun 2026

32 can modify or destroy data

25 read-only

57 tools total

Community server · catalogue entry verified 11/06/2026

How to control Mcp Taskade ↓

TOOL MAP

Read (25) Write / Execute (25) Destructive / Financial (7)

MOST DANGEROUS TOOLS

Critical Risk

Destructive · High agentKnowledgeMediaRemove The tool performs an irreversible deletion operation ('Remove') on knowledge media assets. Destructive · High agentKnowledgeProjectRemove The 'Remove' action on a knowledge project constitutes an irreversible deletion of data. Destructive · High deleteAgent Deleting an agent cannot be undone and permanently removes data/configuration. Destructive · High mediaDelete The tool performs an irreversible delete operation on media objects.

32 of Mcp Taskade's 57 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

HOW TO CONTROL MCP TASKADE

PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Taskade, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "agentKnowledgeMediaRemove": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "taskDeleteAssignees": {
    "limits": [
      {
        "counter": "taskdeleteassignees_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "agentConvoGet": {
    "limits": [
      {
        "counter": "agentconvoget_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Mcp Taskade — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON MCP TASKADE →

Free to start. No card required.

ALL 57 MCP TASKADE TOOLS

DESTRUCTIVE 7 tools

Destructive agentKnowledgeMediaRemove Remove a knowledge media Destructive agentKnowledgeProjectRemove Remove a knowledge project Destructive deleteAgent Delete an agent Destructive mediaDelete Delete a media Destructive taskDelete Delete a task in a project Destructive taskFieldValueDelete Delete the field value of a task Destructive taskNoteDelete Delete the note of a task

WRITE 25 tools

Write taskDeleteAssignees Remove assignee from a task Write taskDeleteDate Delete date of a task Write agentKnowledgeMediaCreate Create a knowledge media Write agentKnowledgeProjectCreate Create a knowledge project Write agentPublicAccessEnable Enable public access in the agent Write agentPublicUpdate Update public agent Write agentUpdate Update agent Write folderAgentGenerate Generate agent based on input text prompts Write folderCreateAgent Create an agent in a team or workspace. Write projectComplete Mark the project as completed Write projectCopy Copy a project to a folder Write projectCreate Create a project in a team Write projectFromTemplate Create a project from a custom template Write projectRestore Restore project Write projectShareLinkEnable Enable share link in the project Write taskComplete Complete a task in a project Write taskCreate Create one or more tasks in a project Write taskFieldValuePut Update/create the field value of a task Write taskMove Move a task within the project Write taskNotePut Add/update a note to the task Write taskPut Update task. Write taskPutAssignees Task assignment Write taskPutDate Create or update date for a task Write taskUncomplete Mark a task as incomplete in a project Write workspaceCreateProject Create a project in a workspace

READ 25 tools

Read agentConvoGet Get agent conversation by id Read agentConvosGet Get agent conversations Read agentGet Get agent with id Read agentPublicGet Get public agent Read folderAgentGet Get agents in a folder. Read folderProjectsGet Get all projects in a team, or in the home team of a workspace. Read folderProjectTemplatesGet Get projects templates in a folder. Read mediaGet Get media with id Read mediasGet Get medias in a folder Read meProjectsGet Get all projects of mine Read projectBlocksGet Get all blocks for a project Read projectFieldsGet Get all fields for a project Read projectGet Get project Read projectMembersGet Get members of a project Read projectShareLinkGet Get share link for the project Read projectTasksGet Get all tasks for a project Read publicAgentGet Get public agent by public agent ID Read taskAssigneesGet Get the assignees of a task Read taskFieldsValueGet Get all field values for a task Read taskFieldValueGet Get the field value of a task Read taskGet Get task with id Read taskGetDate Get the date of a task Read taskNoteGet Get the note of a task Read workspaceFoldersGet Get all folders for a workspace Read workspacesGet Get all workspaces for a user

RELATED SERVERS

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Can an AI agent delete data through the Mcp Taskade MCP server? +

Yes. The Mcp Taskade server exposes 7 destructive tools including agentKnowledgeMediaRemove, agentKnowledgeProjectRemove, deleteAgent. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Mcp Taskade? +

The Mcp Taskade server has 25 write tools including taskDeleteAssignees, taskDeleteDate, agentKnowledgeMediaCreate. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Mcp Taskade.

How many tools does the Mcp Taskade MCP server expose? +

57 tools across 3 categories: Destructive, Read, Write. 25 are read-only. 32 can modify, create, or delete data.

How do I enforce a policy on Mcp Taskade? +

Register the Mcp Taskade MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Mcp Taskade tool call.

Deterministic rules across all 57 Mcp Taskade tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON MCP TASKADE →

Free to start. No card required.

57 Mcp Taskade tools catalogued and risk-classified — across an index of 42,500+ MCP servers.

Mcp Taskade

// TOOL MAP

// MOST DANGEROUS TOOLS

// HOW TO CONTROL MCP TASKADE

// ALL 57 MCP TASKADE TOOLS

// RELATED SERVERS

// FAQ