// SCAN REPORT

Otel

11 tools. 8 can modify or destroy data without limits.

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

Last updated: 3 Jul 2026

8 can modify or destroy data

3 read-only

11 tools total

Community server · catalogue entry verified 03/07/2026

How to control Otel ↓

TOOL MAP

What Otel exposes to your agents

Read (3) Write / Execute (6) Destructive / Financial (2)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Otel tools

Destructive · High clear_endpoints This tool irreversibly deletes all endpoints from the OpenTelemetry configuration. Destructive · Medium remove_endpoint Removing an endpoint is an irreversible deletion of a named configuration resource. Execute · Medium generate_load This tool executes a mimic profile repeatedly to generate load/traffic against OTLP endpoints. Write · Medium add_endpoint This tool creates or registers a new OTLP endpoint configuration, which is a reversible Write operation.

8 of Otel's 11 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Otel

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

Deny destructive operations

{
  "clear_endpoints": {
    "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

{
  "add_endpoint": {
    "limits": [
      {
        "counter": "add_endpoint_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "list_endpoints": {
    "limits": [
      {
        "counter": "list_endpoints_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 Otel — 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 OTEL →

Instant setup, no code required.

FULL CATALOGUE

All 11 Otel tools

DESTRUCTIVE 2 tools

Destructive clear_endpoints Remove all endpoints. Destructive remove_endpoint Remove an endpoint by name.

EXECUTE 1 tools

Execute generate_load Repeatedly run a mimic profile to simulate sustained traffic.

WRITE 5 tools

Write add_endpoint add_endpoint Write mimic_tool mimic_tool Write send_log Send one or more log records. Write send_metric Send one or more metric instruments. Write send_trace send_trace

READ 3 tools

Read list_endpoints List registered endpoints. Read list_mimic_profiles List available tool-mimicry profiles. Read status Report configured endpoints and available profiles.

EXPLORE

Related servers

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

FAQ

Questions about Otel

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

Yes. The Otel server exposes 2 destructive tools including clear_endpoints, remove_endpoint. 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 Otel? +

The Otel server has 5 write tools including add_endpoint, mimic_tool, send_log. 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 Otel.

How many tools does the Otel MCP server expose? +

11 tools across 3 categories: Destructive, Read, Write. 3 are read-only. 8 can modify, create, or delete data.

How do I enforce a policy on Otel? +

Register the Otel 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 Otel tool call.

Deterministic rules across all 11 Otel tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON OTEL →

Instant setup, no code required.

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