Coding & Development
Remote MCP Server Tester
38d agoA web-based tool for inspecting MCP servers. Connect to any MCP server, browse its Tools, Resources, and Prompts, measure fetch latency, estimate token usage, score the quality of tool definitions, and compare two servers side by side.
Tool inspectionTool inspectionResource inspectionPrompt inspectionToken countingFetch timingAuth InspectorLLM Readiness ScoreTool Poisoning RiskExport reportCompare ModeAuthenticationDynamic Client RegistrationDynamic Client RegistrationProtocol MessagesMultiple transportsConnection history
Key Capabilities
01
Tool inspection
Inspect MCP servers, including Tools, Resources, and Prompts
02
Tool inspection
Lists all tools with name, description, parameter breakdown, and input schema
03
Resource inspection
Lists all resources with URI, name, mimeType; read any resource to view its contents
04
Prompt inspection
Lists all prompts with arguments; fill in arguments and render the prompt messages
05
Token counting
Four provider options: Generic estimate (~4 chars/token), Claude API (accurate, uses count_tokens), OpenAI GPT-4o / o-series (tiktoken o200k_base), OpenAI GPT-4 / GPT-3.5 (tiktoken cl100k_base)
06
Fetch timing
Shows MCP server fetch time, roundtrip time, and a per-phase timing breakdown waterfall
07
Auth Inspector
After connecting, shows the auth method used, headers sent, decoded access token claims (exp, iss, sub, scope), and OAuth endpoints; SSO access tokens are cached and reused until expiry
08
LLM Readiness Score
Grades tool definitions A–F across 5 dimensions; highlights which tools need improvement
09
Tool Poisoning Risk
Heuristic scan for MCP tool poisoning attacks (hidden Unicode, prompt-injection phrasing, credential-exfiltration hints, hidden HTML comments) plus "rug pull" detection (tool description/schema silently changed since last connect to the same server, with a line-by-line diff and an explicit review-and-confirm step before the pinned definition is updated); optional deeper scan via the Claude API
10
Export report
Download a self-contained Markdown or JSON report (server info, timing, scores, findings) with automatic secret redaction and a built-in disclaimer — generated entirely client-side
11
Compare Mode
Connects to two servers in parallel and compares performance, tokens, quality scores, and documentation
12
Authentication
Multiple auth methods: None · Bearer Token · OAuth2 Client Credentials · SSO (Authorization Code + PKCE) · Custom Header
13
Dynamic Client Registration
Discovers OAuth endpoints from /.well-known/oauth-authorization-server and MCP WWW-Authenticate headers
14
Dynamic Client Registration
Registers an OAuth client automatically (RFC 7591) — no Client ID required
15
Protocol Messages
Collapsible history of all MCP JSON-RPC calls made during the session — initialize, tools/list, resources/list, prompts/list, tools/call, resources/read, prompts/get
16
Multiple transports
Streamable HTTP (MCP 2025) and SSE, with automatic fallback
17
Connection history
Remembers the last 8 connections in the browser
Use Cases
MCP Server InspectionInspect MCP servers to improve tool quality and securityDevelopers
MCP Server ComparisonCompare MCP server performance, tokens, quality scores, and documentationResearchers
Update History
Updated 38d ago▲ 0% mentionsProduct HuntWeb