Skip to main content
Glama

mcp_inspect

Inspect remote MCP servers over Streamable HTTP to verify initialization, protocol version, capabilities, tools/list schema checks, resource and prompt counts, and latency without calling tools.

Instructions

Remote MCP server inspector (Streamable HTTP): initialize handshake, protocol version, serverInfo, capabilities, session, latency, tools/list with per-tool checks (name pattern, description, inputSchema object, undocumented or missing required params), resources/prompts counts. Read-only: never calls a tool. Costs 0.002 USDC on Base per successful call (x402). Without a payment key this tool returns the 402 challenge.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "url": "<url>"
    },
    "name": "mcp_inspect"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYesMCP endpoint URL

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.3.0

TDQS

A4/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations supplied, the description carries the full burden and does so well: it declares the side-effect profile ('Read-only: never calls a tool'), the pricing and payment rail (0.002 USDC on Base per successful call, x402), and the exact failure mode for unauthenticated callers (returns the 402 challenge rather than erroring obscurely). Cost, auth prerequisite, and mutation safety are all disclosed, which is the precise set of facts an agent needs before deciding to invoke a paid endpoint probe.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose and the checked-item list are front-loaded, followed by the safety guarantee and then the payment terms — a sensible order. The first sentence is a long comma-chained list that is dense to parse, but every clause (handshake, version, capabilities, per-tool checks) communicates a distinct return field and none is filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-parameter tool with no output schema and no annotations, the description effectively documents the return payload by enumerating the inspected fields, including per-tool verdicts (name pattern, description, inputSchema object, undocumented or missing required params). Combined with the explicit read-only and payment behavior, an agent knows both what it gets back and what it costs before calling.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% for the single required parameter, so the schema already explains 'url' as the MCP endpoint URL. The description adds only the implicit constraint that it must be a Streamable HTTP endpoint, and offers no guidance on URL form, path, or auth embedded in the URL. Baseline 3 applies when the schema does the work.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb (inspect) and resource (a remote MCP server over Streamable HTTP), then enumerates exactly what is checked: initialize handshake, protocol version, serverInfo, capabilities, session, latency, tools/list per-tool checks, resources/prompts counts. That is far more specific than a generic 'inspect' label, though it never explicitly contrasts itself with siblings such as mcp_manifest_lint, leaving the agent to infer the boundary from the endpoint-URL resource.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by the content list — you use it against a live remote endpoint, not a static manifest — and one precondition is stated explicitly: without a payment key it returns the 402 challenge. However, there is no explicit when-to-use/when-not-to-use statement and no named alternative for the case where the caller wants to lint a manifest offline instead of probing a running server.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.