About HowYouSeeMe
HowYouSeeMe is an MCP server in the Science category: world perception system combining computer vision models and systems like YOLO, SLAM, Segmentation, VLMs etc into a unified World State Summarizer Interface MCP.
Install
git clone https://github.com/AryanRai/HowYouSeeMeThis server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.
Tools (14)
cancel_navigationStop immediately `[PLANNED]`
Parameters not published.
forget_memory(name)Stop tracking
Parameters not published.
get_camera_frameLatest RGB frame as base64 JPEG for vision LLMs
Parameters not published.
get_checkpoint(id)Retrieve a specific past checkpoint frame and analysis
Parameters not published.
get_recent_eventsLast N perception events with timestamps
Parameters not published.
get_robot_contextSystem prompt context block for Ally Robot Mode
Parameters not published.
get_robot_statusNatural language status summary
Parameters not published.
navigate_to(query)Pathfind to anything in natural language `[PLANNED]`
Parameters not published.
navigate_to_posePathfind to exact 3D coordinates `[PLANNED]`
Parameters not published.
navigation_statusCurrent nav state, goal, ETA `[PLANNED]`
Parameters not published.
Show all 14 tools
query_worldFull world state — objects, people, recent events
Parameters not published.
recall_memory(name)Get a pinned object's confirmed location
Parameters not published.
remember_object(name, label)Pin an object for persistent tracking
Parameters not published.
where_is(label)Last known 3D position of anything
Parameters not published.
Ask AI
Ask AI about HowYouSeeMe
Powered by Claude · Grounded in docs
Security checks
6 checks have not been run yet.