// SCAN REPORT

Lens

19 tools. 10 can modify or destroy data without limits.

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

Last updated: 5 Jul 2026

10 can modify or destroy data

9 read-only

19 tools total

Verified server · catalogue entry verified 05/07/2026 · full schemas captured for 19 of 19 tools

How to control Lens ↓

TOOL MAP

What Lens exposes to your agents

Read (9) Write / Execute (8) Destructive / Financial (2)

Running more than one server? Check your whole stack →

CONTEXT-WINDOW COST

What Lens costs in tokens

3,060 tokens of tool definitions, loaded on every request

1.5% of a 200k context window

386 heaviest tool: create_workflow

Full per-tool breakdown → Model it in the token calculator →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Lens tools

Destructive · High delete_agent_session This tool irreversibly deletes data (agent conversation session). Destructive · High delete_workflow_schedule This tool irreversibly deletes a workflow schedule, which cannot be undone. Execute · High run_agent This tool triggers execution of an external agent with effects that depend entirely on what that agent does—it could perform read operations, modify data, call external APIs, or perform other side effects based on the ag Execute · High run_workflow This tool executes external workflows with user-supplied arguments, making it an Execute category risk.

10 of Lens's 19 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Lens

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

Deny destructive operations

{
  "delete_agent_session": {
    "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

{
  "create_agent": {
    "limits": [
      {
        "counter": "create_agent_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_execution_formatted_outputs": {
    "limits": [
      {
        "counter": "get_execution_formatted_outputs_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 Lens — 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 LENS →

Instant setup, no code required.

FULL CATALOGUE

All 19 Lens tools

DESTRUCTIVE 2 tools

Destructive delete_agent_session Delete an agent conversation session permanently. Destructive delete_workflow_schedule Delete a workflow schedule permanently.

EXECUTE 2 tools

Execute run_agent Execute a Lens agent directly (synchronous). Returns the full response inline. Supports session_id for multi-t Execute run_workflow Execute a Lens workflow by id or name. Provide exactly one of workflow_id or workflow_name. For input: use inp

WRITE 6 tools

Write create_agent Create a new agent in the Lens API. Required: name, type, system_prompt, user_prompt_template. Optional: descr Write create_workflow Create a new workflow in the Lens API. Specify name, type (sequential, parallel, conditional, team), and order Write create_workflow_schedule Create a recurring schedule for a workflow using cron (5 fields). Timezone is fixed server-side (default Ameri Write push_documents_to_lens_kb Upload a document (text content) to a Lens knowledge base. Use list_knowledge_bases to get the KB id. Content Write push_multimodal_content_list_to_lens_kb Push a multimodal content_list (RAG-Anything style) into a Lens knowledge base. The content_list_json must be Write update_workflow_schedule Update a workflow schedule (enable/disable, cron expression, input payload). Timezone is fixed server-side.

READ 9 tools

Read get_execution_formatted_outputs Get formatted outputs (e.g. markdown, PDF) for a workflow execution. Provide execution_id; workflow_id is opti Read get_execution_result Get the result of a workflow execution by its execution_id. Read get_session_history Get the full message history for an agent session. Returns the conversation in chronological order. Read list_agent_sessions List conversation sessions for an agent. Shows session name (first message), message count, and timestamps. Read list_agents List agents from the Lens API. Optionally filter by search (name), type, is_active, or tags. Use this to see e Read list_knowledge_bases List knowledge bases available in the Lens API (Jira, docs, etc.). Optionally filter by name with 'search'. Read list_workflow_schedules List scheduled runs configured for a workflow. Read list_workflows List workflows from the Lens API. Optionally filter by name with 'search'. If include_schedules=true, also sho Read search_knowledge_bases Search one or more knowledge bases by semantic similarity. query: natural language; knowledge_base_ids: comma-

EXPLORE

Related servers

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

FAQ

Questions about Lens

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

Yes. The Lens server exposes 2 destructive tools including delete_agent_session, delete_workflow_schedule. 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 Lens? +

The Lens server has 6 write tools including create_agent, create_workflow, create_workflow_schedule. 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 Lens.

How many tools does the Lens MCP server expose? +

19 tools across 4 categories: Destructive, Execute, Read, Write. 9 are read-only. 10 can modify, create, or delete data.

How do I enforce a policy on Lens? +

Register the Lens 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 Lens tool call.

Deterministic rules across all 19 Lens tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON LENS →

Instant setup, no code required.

19 Lens tools catalogued and risk-classified — across an index of 43,000+ MCP servers.