MCP server for analyzing ROS and ROS 2 bag files with LLMs
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"rosbag-mcp","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
> **Warning** > This code is made by ai # ROSBag MCP Server The code is inspired by [ROSBag MCP Server: Analyzing Robot Data with LLMs for Agentic Embodied AI Applications](https://arxiv.org/pdf/2511.03497). An MCP (Model Context Protocol) server for analyzing ROS and ROS 2 bag files with LLMs. Enables natural language interaction with robotic datasets for debugging, performance evaluation, and extracting insights. ## Features ### Core Data Access & Management | Tool | Description | |------|-------------| | `set_bag_path` | Set path to a rosbag file or directory | | `list_bags` | List all available rosbag files in directory | | `bag_info` | Retrieve bag metadata: topics, message counts, duration, time range | | `get_topic_schema` | Inspect message structure/schema with sample data | ### Message Retrieval | Tool | Description | |------|-------------| | `get_message_at_time` | Get message from a topic at a specific timestamp | | `get_messages_in_range` | Get all messages from a topic within a time range | | `search_messages` | Search messages using conditions (regex, equals, near_position, threshold) | ### Data Filtering & Export | Tool | Description | |------|-------------| | `filter_bag` | Create a filtered copy of a bag file by topic, time, or sample rate | | `export_to_csv` | Export topic data to CSV file for external analysis | ### Domain-Specific Analysis | Tool | Description | |------|-------------| | `analyze_trajectory` | Compute trajectory metrics: total distance, mean/max speeds, position bounds | | `analyze_lidar_scan` | Analyze LiDAR scans for obstacles, gaps, and statistics | | `analyze_imu` | Analyze IMU data: acceleration, angular velocity, orientation statistics | | `analyze_logs` | Parse and analyze ROS logs; filter by level or node | | `get_tf_tree` | Get TF tree of coordinate frame relationships | | `get_image_at_time` | Extract camera image at specific time (returns base64 JPEG) | ### Navigation Analysis | Tool | Description | |------|--…
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.