embodied-mcp
embodied-nav-mcp
Ein Sprachmodell, das sich in einem Raum umsehen, zu dem gehen kann, was es benennt, zählen kann, was es sieht, und anhalten kann, wenn es fertig ist.
Das Modell entscheidet, was zu tun ist. Die Sensoren entscheiden, wo die Dinge sind.
Werkzeuge
Werkzeug | Funktion |
| Vier perspektivische Ansichten der 360°-Kamera, plus Pose |
| Referenzausdruck → Pixelbox → Lidar-Meter → vom Konverter eingerasteter Wegpunkt |
| Einen |
| Parken, damit der Planer aufhört, dem letzten Wegpunkt zu folgen |
| Eine Zählfrage in Ziel / Anker aufteilen |
| Nur diese Perspektive zählen; jede Instanz wird per Lidar positioniert |
| Blicke nach Position gruppieren; die Ganzzahl veröffentlichen |
| Lidar-AABB des letzten |
commit_count übernimmt keine Zahl vom Modell. Zwei Ansichten von vier Kissen ergeben 4, nicht 8.
Die Geometrie ist der Type-3-Stack von Team Xiao Heis feat/xiao-hei-instruction-merge: Größen-Gate, Blindkegel-Behandlung, Konverter-Settle-Pose, Parken beim Verlassen.
Related MCP server: Webots MCP
Installation
uv sync --extra dev
export ANTHROPIC_API_KEY=...
uv run pytestPython 3.11+. Live-Roboter/Simulation benötigt ROS Jazzy und den Autonomie-Stack. Tests verwenden einen simulierten Roboter und benötigen keines von beiden.
Ausprobieren
# Dry run, no ROS
uv run embodied-mcp-agent --fake "How many blue chairs are between the table and the wall?"
uv run embodied-mcp-agent --fake "Find the potted plant on the kitchen island closest to the fridge."
uv run embodied-mcp-agent --fake "Take the path near the window to the fridge."Auf einem Roboter (oder im Challenge-Container) mit laufendem Stack:
uv run embodied-mcp-challenge
# evaluators still run: ros2 launch dummy_vlm dummy_vlm.launchembodied-mcp --attach-ros sind dieselben Werkzeuge über stdio MCP. Der Challenge-Knoten ruft sie prozessintern auf: Ein Robotercontainer hat keine öffentliche URL für einen entfernten MCP-Connector.
CMU-VLN-Challenge
Drop-in-Adapter: examples/cmu_vln/. Der Paketname dummy_vlm ist unverändert.
Typ | Werkzeuge | ROS-Ausgabe |
Numerisch |
|
|
Objektreferenz |
|
|
Anweisungsbefolgung |
|
|
Zulässige Sensoren: /camera/image, /registered_scan, /terrain_map, /terrain_map_ext, /state_estimation. Die Ankunft wird über /state_estimation gemeldet, nicht über /way_point_reached. Eine Frage pro Prozess.
Konfiguration
Variable | Standard | |
| — | erforderlich |
|
| Host- und Pixel-Grounding-/Zählmodell |
|
| Sekunden ab Prozessstart |
|
| Kamera-Topic |
Lizenz
MIT. Eingebettete Geometrie und ROS-I/O von Team Xiao Hei; siehe NOTICE.
Available Tools
8 toolscommit_countA
Cluster every count_in_view look by lidar position and publish one integer on /numerical_response. Two views of the same four pillows become 4, not 8. You do not pass the number — geometry does.
Inputs: no named parameters. Returns: result
count_in_viewA
Count matching instances from the current vantage point only. The call is never told the running total — do not add previous looks yourself. Each instance is boxed and lifted with lidar so later looks can be de-duplicated. If sufficient is false, drive as next_view suggests (or ground the anchor) and count_in_view again. When you are done looking, call commit_count — that publishes the clustered integer.
Inputs: target (required), question (required), anchor. Returns: result
drive_toA
Publish one waypoint (map-frame x, y) and wait until the vehicle arrives or settles. Arrival is decided from /state_estimation, not from a 'waypoint reached' topic. Prefer publish_xy from ground() over coordinates you invent.
Inputs: x (required), y (required), timeout_s. Returns: result
get_viewA
Capture the robot's current 360° camera, split into four perspective faces (front, right, back, left), and return them with the current pose. Call this when you need to see the room. Do not guess what is around you.
Inputs: no named parameters. Returns: result
groundA
Ground a referring expression in the live camera + lidar. Pass the object or place to go to, in the instruction's own words (e.g. 'the lantern closest to the fan decoration'). The tool asks a pixel-grounding model for a box, lifts metres from the registered scan, size-checks the range, and snaps the waypoint to where the platform converter will actually settle. Use publish_xy as the argument to drive_to. If committed is false, this is a step to a better viewpoint — drive there and ground again. If visible is false, drive to suggested_xy and look again.
Inputs: query (required). Returns: result
parse_numericalA
Split a counting question into target, attribute, relation, and anchor. Use this first on numerical questions so you know what to ground and what to pass to count_in_view.
Inputs: question (required). Returns: result
publish_objectA
Publish a 3D cube marker on /selected_object_marker for the object you last grounded. Call ground() on the unique referred object first. The box centre and size come from the lidar cluster, not from a guess.
Inputs: label (required). Returns: result
stopA
Park at the current pose so the local planner stops chasing the last waypoint. Call this when the instruction is finished, or after you have published a numerical or object-reference answer.
Inputs: no named parameters. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 8 tools
Each tool serves a distinct function: perception (get_view), grounding (ground), navigation (drive_to, stop), numerical parsing (parse_numerical), counting (count_in_view), finalizing counts (commit_count), and object publication (publish_object). There is no overlap or ambiguous boundaries between them.
All tool names follow a consistent verb_phrase pattern with snake_case (e.g., get_view, drive_to, commit_count). The verbs are imperative and descriptive, making the intent of each tool predictable from its name alone.
With 8 tools, the server is well-scoped for embodied navigation and counting tasks. Each tool covers a necessary step in the workflow without redundancy or excessive granularity, fitting within the ideal 3-15 tool range.
The tool surface fully covers the lifecycle of the domain: perceiving the environment, grounding references, moving, stopping, parsing questions, counting from multiple views, committing aggregated results, and publishing object markers. There are no obvious gaps or dead ends for the intended tasks.
Maintenance
Related MCP Connectors
Persistent workspace and visual memory for humans and autonomous agents.
Video scene understanding for AI agents via the Primate Vision API.
E2LLM gives your AI eyes and hands in a real browser: structured perception (SiFR) plus action.
Task and planning workspace for humans collaborating with AI agents
Related MCP Servers
- AlicenseAqualityDmaintenanceEnables controlling robots in ROS environments through natural language, supporting topics, services, actions, and GUI tools.2436MIT
- AlicenseNot gradedqualityDmaintenanceBridges AI agents with Webots robotics simulation, enabling natural language control of Nao robots and visual perception.MIT
- FlicenseAqualityDmaintenanceEnables agents to identify appliances and retrieve grounded, robot-executable operation packages, reducing hallucinations from 24% to nearly 0%.4-
- FlicenseNot gradedqualityDmaintenanceEnables LLM agents to control robot simulations (grasping, pouring) in the Genesis physics simulator through persistent sessions, allowing multi-turn interaction with the same scene.-