// SCAN REPORT

Mcp Test Servers

67 tools. 38 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated: 12 Aug 2026

38 can modify or destroy data

29 read-only

67 tools total

Community server · catalogue entry checked 12/08/2026

How to control Mcp Test Servers ↓

TOOL MAP

What Mcp Test Servers exposes to your agents

Read (29) Write / Execute (9) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Mcp Test Servers tools

Destructive · High delete-project Deletion operations are classified as Destructive per the schema rules, as they cannot be undone. Execute · Critical execute-sql SQL execution is an Execute category action that can trigger external database operations with effects depending on arguments. Execute · Low ping Although 'ping' is commonly a read operation, this tool's description explicitly states it 'triggers a request' (an action) and 'logs headers' (a side effect). Execute · Medium start-notification-stream This tool executes an action with side effects that runs continuously or periodically, rather than simply retrieving data.

38 of Mcp Test Servers's 67 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Mcp Test Servers

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

Deny destructive operations

{
  "delete-project": {
    "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

{
  "generate_image": {
    "limits": [
      {
        "counter": "generate_image_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "analyze_text": {
    "limits": [
      {
        "counter": "analyze_text_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 Test Servers — 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 TEST SERVERS →

Instant setup, no code required.

FULL CATALOGUE

All 67 Mcp Test Servers tools

DESTRUCTIVE 1 tools

Destructive delete-project Delete a project

EXECUTE 7 tools

Execute execute-sql execute-sql Execute long-running-task Executes a long-running task with real-time progress tracking Execute long-running-task-with-message Demonstrates a long running operation with progress updates and messages Execute long-running-task-with-no-total Executes a long-running task with real-time progress tracking Execute ping Simple ping to trigger a request and log headers Execute start-notification-stream Starts sending periodic notifications Execute toggle_dynamic_tool Toggles the availability of the dynamic_feature tool

WRITE 2 tools

Write generate_image A tool that returns an image of Sonic the Hedgehog Write terminate-session terminate-session

READ 29 tools

Read analyze_text analyze_text Read ask-favorite-color Ask the user to select their favorite color from a list (raw enum values) Read ask-name Ask the user for their name Read ask-programming-language Ask the user to select their favorite programming language with user-friendly display names Read bug-status Check if the OAuth bug has been reproduced Read debug-oauth Returns OAuth debugging information Read delayedPing delayedPing Read echo_env_var Echoes the MY_ENV_VAR environment variable Read echo_mcp_roots Echoes back the MCP roots provided by the client Read factorial factorial Read get_mixed_resources Returns both text and image content Read get-headers Returns the headers from the last request Read get-info get-info Read get-resource-list Returns a list of all available resources as resource links Read get-session-info Get session information including time until expiry Read get-time get-time Read log-to-stderr log-to-stderr Read long-running-ping long-running-ping Read makeRequest makeRequest Read multi-step-elicitation Ask for a couple of elicitations about pizza Read parse_bugsnag_error_url parse_bugsnag_error_url Read safe_header_info Safely get header information without raising errors. Read search_documentation search_documentation Read simple_ping A simple tool that returns Read sqrt sqrt Read status status Read test_all_elicitations Tests all different elicitation input types Read token-info Returns information about the current access token expiration Read whoami Returns information about the authenticated user

OTHER 28 tools

Other add add Other all_types_tool all_types_tool Other another-missing-type Another tool with missing type field Other bad-param bad-param Other crash crash Other divide divide Other dynamic_feature dynamic_feature Other echo echo Other echo_structured echo_structured Other echo_with_params echo_with_params Other env_echo env_echo Other fizzbuzz fizzbuzz Other format_data format_data Other generate_big_response generate_big_response Other long_running_progress long_running_progress Other many-resources-tool Many Resources Tool Other missing-type-tool A tool with missing type field Other multiply multiply Other number-param number-param Other optionalTool optionalTool Other power power Other root-echo root-echo Other subtract subtract Other test-anyof-integer test-anyof-integer Other test-both-params test-both-params Other test-edge-cases Test tool for edge case scenarios Other test-simple-integer test-simple-integer Other toggleTool toggleTool

EXPLORE

Related servers

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

FAQ

Questions about Mcp Test Servers

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

Yes. The Mcp Test Servers server exposes 1 destructive tools including delete-project. 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 Test Servers? +

The Mcp Test Servers server has 2 write tools including generate_image, terminate-session. 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 Test Servers.

How many tools does the Mcp Test Servers MCP server expose? +

67 tools across 4 categories: Destructive, Execute, Read, Write. 29 are read-only. 38 can modify, create, or delete data.

How do I enforce a policy on Mcp Test Servers? +

Register the Mcp Test Servers 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 Test Servers tool call.

Deterministic rules across all 67 Mcp Test Servers tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON MCP TEST SERVERS →

Instant setup, no code required.

67 Mcp Test Servers tools catalogued and risk-classified — across an index of 46,500+ MCP servers.

// WHERE THIS COMES FROM

These policies come from Mcp Test Servers's registry record.

The record behind this page: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →