Model Context Protocol server

mcp-context-inspector

Execution metrics and a full Context Window Explorer for Bedrock-based agents and Claude Code — over a real MCP server, not a mock.

Context Window Explorer · live preview

system tools reasoning tool call tool result answer

Tool call: get_service_metrics120 tok

Tool result: get_service_metrics640 tok

Final answer210 tok

Built by @sohaibsohail98

What this gives your agent

Real per-session cost, token, and tool-call metrics — 7 read-only MCP tools
The Context Window Explorer — exactly what entered the model's context window, block by block, with honest token estimates
Your own data, isolated from anyone else connected to this server — sign in below and everything you record or query is scoped to your account

What is an MCP server?

MCP (Model Context Protocol) is an open standard that lets an LLM or agent call tools over a normal HTTP connection. This server exposes read/write tools for agent execution data, and is built to support two integration paths: Bedrock-based agents calling the record_session tool directly, and Claude Code.

Why sign in with Google instead of a password?

No account to create or password to remember here — Google verifies who you are, this server just checks the signed proof and hands you a token scoped to your account. That token, not your Google identity itself, is what your agent actually uses afterward.

What does "your own data" actually mean?

Every session recorded through your token is tagged with your account. Reads are filtered the same way — you only ever see, list, or query sessions you recorded. Even guessing another person's session ID reads back as "not found," identical to one that never existed.

Sign in to get your token

One click — no password, no account to create here.