Skip to main content
Glama

M8ven Score

embodied-nav-mcp

A language model that can look around a room, go to what it names, count what it sees, and stop when it is done.

The model decides what to do. The sensors decide where things are.

Tools

Tool

What it does

get_view

Four perspective faces from the 360° camera, plus pose

ground

Referring expression → pixel box → lidar metres → converter-snapped waypoint

drive_to

Publish one map-frame (x, y) and wait until arrived or settled

stop

Park so the planner stops chasing the last waypoint

parse_numerical

Split a counting question into target / anchor

count_in_view

Count this vantage only; each instance is lidar-lifted

commit_count

Cluster looks by position; publish the integer

publish_object

Lidar AABB of the last ground; publish a 3D marker

commit_count does not take a number from the model. Two views of four pillows become 4, not 8.

Geometry is the Type 3 stack from Team Xiao Hei’s feat/xiao-hei-instruction-merge: size gate, blind-cone handling, converter settle pose, park-on-exit.

Related MCP server: Webots MCP

Install

uv sync --extra dev
export ANTHROPIC_API_KEY=...
uv run pytest

Python 3.11+. Live robot/sim needs ROS Jazzy and the autonomy stack. Tests use a fake robot and need neither.

Try it

# 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."

On a robot (or in the challenge container) with the stack up:

uv run embodied-mcp-challenge
# evaluators still run: ros2 launch dummy_vlm dummy_vlm.launch

embodied-mcp --attach-ros is the same tools over stdio MCP. The challenge node calls them in-process: a robot container has no public URL for a remote MCP connector.

CMU VLN Challenge

Drop-in adapter: examples/cmu_vln/. Package name dummy_vlm is unchanged.

Type

Tools

ROS out

Numerical

parse_numerical, count_in_view, commit_count

/numerical_response

Object reference

ground, publish_object

/selected_object_marker

Instruction-following

get_view, ground, drive_to, stop

/way_point_with_heading

Allowed sensors: /camera/image, /registered_scan, /terrain_map, /terrain_map_ext, /state_estimation. Arrival is /state_estimation, not /way_point_reached. One question per process.

Configuration

Variable

Default

ANTHROPIC_API_KEY

—

required

EMBODIED_MCP_MODEL

claude-opus-5

host and pixel-grounding / counting model

EMBODIED_MCP_BUDGET_S

540

seconds from process start

XIAO_HEI_IMAGE_TOPIC

/camera/image

camera topic

License

MIT. Vendored geometry and ROS I/O from Team Xiao Hei; see NOTICE.

Available Tools

8 tools
commit_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

    A4.3/5.0

    Scored across 8 tools

    Disambiguation5/5

    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.

    Naming Consistency5/5

    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.

    Tool Count5/5

    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.

    Completeness5/5

    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.

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      D
      maintenance
      Enables controlling robots in ROS environments through natural language, supporting topics, services, actions, and GUI tools.
      24
      36
      MIT
    • F
      license
      A
      quality
      D
      maintenance
      Enables agents to identify appliances and retrieve grounded, robot-executable operation packages, reducing hallucinations from 24% to nearly 0%.
      4
      -
    • F
      license
      Not graded
      quality
      D
      maintenance
      Enables LLM agents to control robot simulations (grasping, pouring) in the Genesis physics simulator through persistent sessions, allowing multi-turn interaction with the same scene.
      -