// SCAN REPORT

Mcp Inspector

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

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

Last updated: 5 Jul 2026

3 can modify or destroy data

7 read-only

10 tools total

Verified server · catalogue entry verified 05/07/2026 · full schemas captured for 9 of 10 tools

How to control Mcp Inspector ↓

TOOL MAP

What Mcp Inspector exposes to your agents

Read (7) Write / Execute (3) Destructive / Financial (0)

Running more than one server? Check your whole stack →

CONTEXT-WINDOW COST

What Mcp Inspector costs in tokens

1,097 tokens of tool definitions, loaded on every request

0.5% of a 200k context window

225 heaviest tool: inspector_connect

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

MOST DANGEROUS TOOLS

High Risk

The most dangerous Mcp Inspector tools

Execute · High inspector_connect This tool spawns a new process (MCP server) and establishes a connection to it. Execute · Critical inspector_call_tool This tool executes arbitrary tools on a connected MCP server. Write · Medium inspector_disconnect Close an active MCP server session by session_id.

3 of Mcp Inspector's 10 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 Inspector

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

Rate limit write operations

{
  "inspector_disconnect": {
    "limits": [
      {
        "counter": "inspector_disconnect_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "inspector_get_prompt": {
    "limits": [
      {
        "counter": "inspector_get_prompt_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 Inspector — 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 INSPECTOR →

Instant setup, no code required.

FULL CATALOGUE

All 10 Mcp Inspector tools

EXECUTE 2 tools

Execute inspector_call_tool Call a tool on the connected MCP server and return the result. Execute inspector_connect Spawn and connect to an MCP server. Returns session_id for subsequent calls.

WRITE 1 tools

Write inspector_disconnect Close an active MCP server session by session_id.

READ 7 tools

Read inspector_get_prompt Retrieve a rendered prompt with arguments from the connected MCP server. Read inspector_list_prompts List all prompts exposed by the connected MCP server. Read inspector_list_resource_templates List all resource URI templates from the connected MCP server. Read inspector_list_resources List all resources exposed by the connected MCP server. Read inspector_list_sessions List all active MCP server sessions with their IDs and targets. Read inspector_list_tools List all tools exposed by the connected MCP server. Read inspector_read_resource Read the contents of a resource by URI from the connected MCP server.

FAQ

Questions about Mcp Inspector

How do I prevent bulk modifications through Mcp Inspector? +

The Mcp Inspector server has 1 write tools including inspector_disconnect. 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 Inspector.

How many tools does the Mcp Inspector MCP server expose? +

10 tools across 2 categories: Read, Write. 7 are read-only. 3 can modify, create, or delete data.

How do I enforce a policy on Mcp Inspector? +

Register the Mcp Inspector 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 Inspector tool call.

Deterministic rules across all 10 Mcp Inspector tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON MCP INSPECTOR →

Instant setup, no code required.

10 Mcp Inspector tools catalogued and risk-classified — across an index of 43,000+ MCP servers.