> ## Documentation Index
> Fetch the complete documentation index at: https://docs.contexaai.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Tracing and Logs

> Track all your server and tool calls in one place

The **Traces** tab in Contexa provides complete visibility into how your MCP servers and tools are being used. Whether you're debugging a failing tool, measuring usage trends, or just validating tool call outputs - **Traces** is the place to go.

All tool calls are automatically logged with rich metadata, making it easy to inspect input/output schemas, status, timestamps, and session history.

### Overview

Click on the **Traces** tab from the sidebar to open the tracing dashboard. You'll find two main sections:

#### 🟢 Platform Logs

Shows all individual tool calls made across your deployed servers.

#### 📘 Server Session Logs

Groups calls by **chat sessions**, allowing you to trace the full flow of tool usage within a single conversation (ideal for multi-step agents or workflows).

<img src="https://mintcdn.com/contexaai-ae648e0a/6uNgbXU7OVN59NRE/images/Screenshot2025-08-07at2.17.25PM.png?fit=max&auto=format&n=6uNgbXU7OVN59NRE&q=85&s=053a08c7a5d1dd8f58dbed27abe09aad" alt="Screenshot2025 08 07at2 17 25PM Pn" width="2688" height="1422" data-path="images/Screenshot2025-08-07at2.17.25PM.png" />

#### 📜 **Tool Calls History**

* A searchable, filterable list of all tool calls
* View includes:
  * Tool name (e.g., `get-library-docs`)
  * Status (Success / Failure)
  * Timestamp
  * Source MCP server

Clicking **“View Detail”** on any entry opens the full trace.

<img src="https://mintcdn.com/contexaai-ae648e0a/6uNgbXU7OVN59NRE/images/Screenshot2025-08-07at2.18.08PM.png?fit=max&auto=format&n=6uNgbXU7OVN59NRE&q=85&s=d85215fee66e6b62aa7fb17e214a26fb" alt="Screenshot2025 08 07at2 18 08PM Pn" width="1196" height="1544" data-path="images/Screenshot2025-08-07at2.18.08PM.png" />

### Tool Call Detail View

When you inspect a tool call, you’ll see:

* **Tool Name**
* **Call Status**
* **Timestamp**
* **MCP Server Source**
* **Session ID**

Along with:

#### 🔧 Input Schema

Shows the exact arguments sent to the tool, in JSON format.

#### 📤 Output Schema

Displays the tool’s response/output, if any.

This lets you validate that tools are being called correctly and returning expected results.

### Server Session Logs

The second tab, **Server Session Logs**, groups tool call traces by session ID. This is especially useful when:

* Debugging multi-step tool interactions by an agent
* Understanding the chronological flow of calls in a single chat
* Analyzing patterns in real-world usage

### Use Cases

* ✅ Debug tool calls in real-time
* 🔎 Inspect malformed inputs or failures
* 📊 Analyze success rates and usage patterns
* 🧵 Trace tool chains within a session

<Note>
  The Tracing section is your mission control for observability—whether you're shipping APIs, orchestrating custom tools, or managing high-traffic MCP servers.
</Note>