// MCP TOOL REFERENCE

delete_watch

Delete one of your active webhook watches by id. Free, requires TENSORFEED_TOKEN.

Single-target operation

Part of the TensorFeed MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.

// WHEN AI AGENTS USE THIS TOOL

AI agents may call delete_watch to permanently remove or destroy resources in TensorFeed. Without a policy, an autonomous agent could delete critical data in a loop with no way to undo the damage. Intercept blocks destructive tools by default and requires explicit human approval before enabling them.

// WHY ENFORCE A POLICY ON DELETE_WATCH

Without a policy, an AI agent could call delete_watch in a loop, permanently destroying resources in TensorFeed. There is no undo for destructive operations. Intercept blocks this tool by default and only allows it when a human explicitly approves the action.

// RECOMMENDED POLICY

Destructive tools permanently remove data. Block by default. Only enable with explicit approval workflows.

tensorfeed.yaml

tools:
  delete_watch:
    rules:
      - action: deny
        reason: "Blocked by default — enable with approval"

See the full TensorFeed policy for all 42 tools.

// DETAILS

Tool Name delete_watch

Category Destructive

MCP Server TensorFeed MCP Server

Risk Level Critical

// MORE TENSORFEED TOOLS

Execute whats_new Write create_digest_watch Write create_leaderboard_rank_watch Write create_price_watch Write create_status_watch Read benchmark_series Read benchmark_series_free Read compare_models

View all 42 tools →

// WHAT CAN GO WRONG

Agents calling destructive-class tools like delete_watch have been implicated in these attack patterns. Read the full case and prevention policy for each:

Browse the full MCP Attack Database →

// OTHER DESTRUCTIVE TOOLS ACROSS MCP SERVERS

Other tools in the Destructive risk category across the catalogue. The same policy patterns (deny, require_approval) apply to each.

AbraFlexi contact_delete AbraFlexi evidence_delete AbraFlexi invoice_issued_delete AbraFlexi product_delete ACR — Agent Composition Records acknowledge_signal AdButler campaign_bulk_delete_catalog_ad_items

// IN CONTEXT OF CRITICAL RISK

delete_watch is one of the critical-risk operations in TensorFeed. For the full severity-focused view — only the critical-risk tools with their recommended policies — see the breakdown for this server, or browse all critical-risk tools across every MCP server.

// RELATED READING

// FAQ

What does the delete_watch tool do? +

Delete one of your active webhook watches by id. Free, requires TENSORFEED_TOKEN.. It is categorised as a Destructive tool in the TensorFeed MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.

How do I enforce a policy on delete_watch? +

Add a rule in your Intercept YAML policy under the tools section for delete_watch. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the TensorFeed MCP server.

What risk level is delete_watch? +

delete_watch is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.

Can I rate-limit delete_watch? +

Yes. Add a rate_limit block to the delete_watch 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.

How do I block delete_watch completely? +

Set action: deny in the Intercept policy for delete_watch. 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.

What MCP server provides delete_watch? +

delete_watch is provided by the TensorFeed MCP server (@tensorfeed/mcp-server). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.

delete_watch

Let agents act without letting them run wild.