// SCAN REPORT

A2wave

22 tools. 3 can modify or destroy data without limits.

3 write tools that can modify data. Rate limits recommended.

Last updated: 28 Sept 2026

3 can modify or destroy data

19 read-only

22 tools total

Community server · catalogue entry checked 28/09/2026

How to control A2wave ↓

TOOL MAP

What A2wave exposes to your agents

Read (19) Write / Execute (3) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous A2wave tools

Execute · High call_tool Executes arbitrary tools with user-supplied arguments; effects depend on which tool and arguments are chosen. Execute · High invoke_agent Invokes external agents to execute arbitrary tasks with inherited timeouts and reconnection capabilities, creating uncontrolled side effects. Execute · High invoke_agents_parallel Executes external agents in parallel; effects depend on agent definitions and arguments provided.

3 of A2wave's 22 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control A2wave

PolicyLayer is an MCP gateway — it sits between your AI agents and A2wave, and nothing reaches the server without passing your rules. These are the rules we recommend:

Cap read operations

{
  "get_agent": {
    "limits": [
      {
        "counter": "get_agent_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 A2wave — 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 A2WAVE →

Instant setup, no code required.

FULL CATALOGUE

All 22 A2wave tools

EXECUTE 3 tools

Execute call_tool Execute a tool in a group. Typical flow: list_tools → get_tool_schema → call_tool. toolName must come from lis Execute invoke_agent Send a message to an Agent over the A2A protocol and get its response. Long-running Tasks inherit the calling Execute invoke_agents_parallel Call several Agents in parallel: all invocations run at once and return together. Use it when sending independ

READ 19 tools

Read get_agent Get the full configuration of a specific agent, including its system prompt, skills, MCP configuration and pub Read get_agent_card Get the details of one Agent (its A2A Agent Card), including capability description and skill list. Use it to Read get_mcp_server Get the full configuration of a specific MCP Server. Read get_platform_overview Get an overview of the a2wave platform: agent count, run statistics, and the number of MCP servers, skills, pr Read get_provider Get the full configuration of a specific provider. Read get_run_detail Get the details of a run, including its execution steps, input, output and duration. Read get_run_stats Get a run statistics overview: total runs, runs today, success rate, average duration and the distribution acr Read get_settings Get the platform-wide settings, including working directory, timeouts, artifact configuration and alert webhoo Read get_skill Get the full details of a specific skill, including its instruction content and file list. Read get_tool_schema Get the full inputSchema for one or more tools. Use this after list_tools to get parameter details before call Read list_agents List the Agents available to call. Returns each Agent Read list_audit_logs List audit logs, the history of every write operation. Supports pagination. Read list_groups List all available group keys (e.g. prod, staging, dev) and their backend counts. Discovery flow: list_groups Read list_mcp_servers List all MCP Server configurations, including transport type, enabled state and command or URL. Read list_providers List all providers, including name, available models and system requirements. Read list_runs List run records, filterable by agent and paginated. Returns run status, trigger source and the associated age Read list_skills List all skills, including name, description and file information. Read list_tools List all tools in a group. Returns tool names and descriptions (lightweight, no inputSchema). Use get_tool_sch Read list_users List all users, including username, role and enabled state (passwords are never returned).

EXPLORE

Related servers

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

FAQ

Questions about A2wave

Is the A2wave MCP server safe to use without restrictions? +

The A2wave server is primarily read-only with 19 read tools. While it cannot modify data, an agent in a retry loop can make thousands of API calls per minute, exhausting rate limits and running up costs. Rate limiting is still recommended.

How many tools does the A2wave MCP server expose? +

22 tools across 2 categories: Execute, Read. 19 are read-only. 3 can modify, create, or delete data.

How do I enforce a policy on A2wave? +

Register the A2wave 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 A2wave tool call.

Deterministic rules across all 22 A2wave tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON A2WAVE →

Instant setup, no code required.

22 A2wave tools catalogued and risk-classified — across an index of 46,500+ MCP servers.

// WHERE THIS COMES FROM

These policies come from A2wave'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 →