Which integrations are available for this server?

Enables GitHub Copilot in VS Code to access TensorBoard data for AI-assisted analysis.

How do I use MCP TensorBoard?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@MCP TensorBoard What's the latest training loss from run experiment_1?" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

MCP TensorBoard

by 1Kraks

Overview Schema Source Related Servers Discussions Admin

Python

Local

MCP TensorBoard

A Model Context Protocol (MCP) server that exposes TensorBoard data through a standardized API. Built with FastMCP, this server enables AI coding agents to query and analyze TensorBoard experiment data programmatically.

Features

Pure Python implementation - No subprocess or external binaries required
Multiple transports - stdio, Streamable HTTP, and SSE
Full TensorBoard support - Scalars, tensors, histograms, distributions, and images
Structured output - Pydantic models for type-safe, validated responses
AI-optimized - Compact data formats ideal for LLM consumption

Related MCP server: tb-query

Quickstart

Run directly from GitHub (no installation)

uvx --from git+https://github.com/1Kraks/mcp-tensorboard mcp-tensorboard --logdir /path/to/logs

Install with uv (recommended)

# Clone the repository
git clone https://github.com/1Kraks/mcp-tensorboard
cd mcp-tensorboard

# Create virtual environment and install
uv venv
source .venv/bin/activate  # macOS/Linux
uv sync

# Run the server
uv run mcp-tensorboard --logdir /path/to/logs

Install with pip

pip install -e .
mcp-tensorboard --logdir /path/to/logs

Usage

Command Line Options

mcp-tensorboard --logdir <path> [--transport stdio|http|sse] [--port PORT] [--host HOST] [--debug]

Option	Default	Description
`--logdir`	(required)	Path to TensorBoard logs directory
`--transport`	`stdio`	Transport protocol
`--port`	`8000`	Port for HTTP/SSE transport
`--host`	`0.0.0.0`	Host for HTTP/SSE transport
`--debug`	off	Enable debug logging

Environment Variables

TENSORBOARD_LOGDIR - Default log directory (alternative to --logdir)
TENSORBOARD_LOGS - Alternative log directory variable

Available Tools

Run Management

Tool	Description
`tensorboard_list_runs`	List all runs in the log directory

Scalars

Tool	Description
`tensorboard_list_scalar_tags`	List scalar tags for a run
`tensorboard_get_scalar_series`	Get time series for a scalar
`tensorboard_get_scalar_series_batch`	Get multiple scalars in one call
`tensorboard_get_scalar_last`	Get the most recent scalar value

Tensors

Tool	Description
`tensorboard_list_tensor_tags`	List tensor tags for a run
`tensorboard_get_tensor_series`	Get time series for scalar tensors

Histograms & Distributions

Tool	Description
`tensorboard_list_histogram_tags`	List histogram tags
`tensorboard_get_histogram_series`	Get raw histogram data
`tensorboard_list_distribution_tags`	List distribution tags (alias)
`tensorboard_get_distribution_series`	Get compressed distributions (recommended)

Images

Tool	Description
`tensorboard_list_image_tags`	List image tags
`tensorboard_get_image_series`	Get image references (blob keys)
`tensorboard_get_image`	Fetch image by blob key (returns base64)

RL Reward Analysis (Stage 4)

Tool	Description
`reward_list_experiments`	List all reward experiments with metadata
`reward_get_stats`	Get summary statistics for a reward experiment
`reward_compare`	Compare multiple reward functions side-by-side
`reward_get_trajectories`	Get training trajectories for analysis
`reward_summary_report`	Generate comprehensive analysis report

Convergence Analysis

Tool	Description
`reward_rank_by_convergence`	Rank rewards by convergence speed (steps to threshold GC)
`reward_get_convergence_summary`	Get summary statistics for convergence analysis

Convergence Metrics:

steps_to_threshold — First checkpoint where goal_completion >= threshold
gc_at_threshold — GC value at threshold step (tie-breaker for same-step convergence)
converged — Whether threshold was reached

Usage Example:

{
  "method": "tools/call",
  "params": {
    "name": "reward_rank_by_convergence",
    "arguments": {
      "reward_ids": ["reward_0001", "reward_0002", "reward_0003"],
      "threshold": 0.95
    }
  }
}

Ranking Logic:

Converged rewards ranked before non-converged
Among converged: lower steps = better (faster learning)
Tie-breaker: higher GC at threshold = better

Integration with Coding Agents

Claude Code

Option 1: Run from git (no install)

claude mcp add --transport http tensorboard-http \
  uvx --from git+https://github.com/1Kraks/mcp-tensorboard mcp-tensorboard --logdir /path/to/logs --transport http

Option 2: Local installation

# Install globally or in a shared venv
pip install -e /path/to/mcp-tensorboard

# Add to Claude Code
claude mcp add tensorboard mcp-tensorboard --logdir /path/to/logs

Option 3: Via Claude Code settings.json

Add to ~/.claude/settings.json:

{
  "mcpServers": {
    "tensorboard": {
      "command": "uvx",
      "args": [
        "--from",
        "git+https://github.com/1Kraks/mcp-tensorboard",
        "mcp-tensorboard",
        "--logdir",
        "/path/to/logs"
      ]
    }
  }
}

GitHub Copilot / VS Code

Add to VS Code settings.json:

{
  "github.copilot.chat.mcp.servers": {
    "tensorboard": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "--from",
        "git+https://github.com/1Kraks/mcp-tensorboard",
        "mcp-tensorboard",
        "--logdir",
        "/path/to/logs"
      ]
    }
  }
}

Cline (VS Code Extension)

Add to Cline's MCP settings:

{
  "mcpServers": {
    "tensorboard": {
      "command": "uvx",
      "args": [
        "--from",
        "git+https://github.com/1Kraks/mcp-tensorboard",
        "mcp-tensorboard",
        "--logdir",
        "/path/to/logs"
      ]
    }
  }
}

Cursor

Add to Cursor's MCP configuration:

{
  "mcpServers": {
    "tensorboard": {
      "command": "uvx",
      "args": [
        "--from",
        "git+https://github.com/1Kraks/mcp-tensorboard",
        "mcp-tensorboard",
        "--logdir",
        "/path/to/logs"
      ]
    }
  }
}

Generic MCP Client (Streamable HTTP)

For HTTP transport, run the server:

mcp-tensorboard --logdir /path/to/logs --transport http --port 8000

Connect to http://localhost:8000/mcp from any MCP-compatible client.

Example Usage

List all runs

{
  "method": "tools/call",
  "params": {
    "name": "tensorboard_list_runs",
    "arguments": {}
  }
}

Get scalar training loss over time

{
  "method": "tools/call",
  "params": {
    "name": "tensorboard_get_scalar_series",
    "arguments": {
      "run": ".",
      "tag": "loss",
      "max_points": 500
    }
  }
}

Compare multiple metrics

{
  "method": "tools/call",
  "params": {
    "name": "tensorboard_get_scalar_series_batch",
    "arguments": {
      "run": "experiment_1",
      "tags": ["loss", "accuracy", "val_loss", "val_accuracy"],
      "max_points": 200
    }
  }
}

Get compressed distribution (AI-friendly)

{
  "method": "tools/call",
  "params": {
    "name": "tensorboard_get_distribution_series",
    "arguments": {
      "run": ".",
      "tag": "weights",
      "max_points": 50
    }
  }
}

Development

Setup

# Clone and set up environment
git clone https://github.com/1Kraks/mcp-tensorboard
cd mcp-tensorboard
uv venv
source .venv/bin/activate
uv sync --all-extras

Run tests

pytest

Run with debug logging

mcp-tensorboard --logdir /path/to/logs --debug

Code style

# Format code
ruff format .

# Lint
ruff check .

Project Structure

mcp-tensorboard/
├── pyproject.toml              # Project configuration
├── README.md                   # This file
├── src/mcp_tensorboard/
│   ├── __init__.py             # Package init
│   ├── __main__.py             # python -m entry point
│   ├── server.py               # FastMCP server & tools
│   ├── data_reader.py          # Pure Python event file reader
│   └── types.py                # Pydantic response models
└── tests/
    └── test_server.py          # Unit tests

Troubleshooting

No runs found

Ensure --logdir points to the directory containing TensorBoard event files
Event files are typically named events.out.tfevents.*

Import errors

Run uv sync or pip install -e . to install dependencies

HTTP transport not connecting

Verify the server is running: curl http://localhost:8000/mcp
Check firewall settings for the specified port

Images not displaying

Image support requires Pillow: pip install pillow
Some TensorBoard image formats may not be supported

License

MIT License - See LICENSE file for details.

This server cannot be deployed

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Maintenance

ActivityStale

ResponsivenessNo issues

Resources

GitHub Repository

Need Help?

Related Servers

Related MCP Connectors

anotherai
dev.anotherai
MCP server for building and testing AI agents with multi-model experimentation and insights.
Agent Orchestration Autonomous Agents Testing & QA Tools
2
Foam Observability
io.github.foam-ai
Query application logs, traces, and metrics from your AI coding assistant via Foam's MCP server.
Observability Monitoring Developer Tools
2
Backtest360 A
com.backtest360
MCP server exposing the Backtest360 engine API as tools for AI agents.
Finance Research & Data
202
Agent AnalyticsOAuth
io.github.dannyshmueli
Analytics your AI agent can actually use. Track, experiment, and optimize via MCP.
Agent Orchestration Monitoring
2

Related MCP Servers

trackio-mcp
RAG Systems Monitoring Developer Tools
fcakyon
A
license
Not graded
quality
C
maintenance
An MCP server that enables AI agents to observe and interact with trackio experiment tracking, providing tools for managing ML experiments through natural language.
Updated a year ago (2025-08-03 13:39 UTC)
3
MIT
tb-query
AI & Machine Learning Monitoring
Alir3z4
A
license
A
quality
B
maintenance
MCP server for querying and analyzing TensorBoard event files, enabling AI agents to extract scalar data, statistics, and correlations without a running TensorBoard server.
Updated a year ago (2025-11-04 21:16 UTC)
6
11
GPL 3.0
AgentMark MCP Serverofficial
AI & Machine Learning Agent Orchestration
agentmark-ai
A
license
Not graded
quality
A
maintenance
MCP server for AgentMark. Exposes the full AgentMark API to AI editors: list traces and spans, manage datasets, write scores, run experiments, manage apps, deployments, environments, and annotation queues.
Updated 3 months ago (2026-07-07 01:17 UTC)
352
AGPL 3.0
@sentientui/mcp
Feature Flags Developer Tools
SentientUI
A
license
Not graded
quality
B
maintenance
MCP server for SentientUI that gives AI agents in Claude Code, Cursor, and Copilot direct access to experiment data and management actions.
Updated 13 hours ago (2026-09-23 11:48 UTC)
127 npm
MIT

MCP TensorBoard

Features

Quickstart

Run directly from GitHub (no installation)

Install with uv (recommended)

Install with pip

Usage

Command Line Options

Environment Variables

Available Tools

Run Management

Scalars

Tensors

Histograms & Distributions

Images

RL Reward Analysis (Stage 4)

Convergence Analysis

Integration with Coding Agents

Claude Code

GitHub Copilot / VS Code

Cline (VS Code Extension)

Cursor

Generic MCP Client (Streamable HTTP)

Example Usage

List all runs

Get scalar training loss over time

Compare multiple metrics

Get compressed distribution (AI-friendly)

Development

Setup

Run tests

Run with debug logging

Code style

Project Structure

Troubleshooting

License

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

trackio-mcp

tb-query

AgentMark MCP Serverofficial

@sentientui/mcp