rosclaw (ros-claw/rosclaw) is an MCP server listed on the M8ven Trust Index. It scores 74 out of 100, grade C. It declares 72 tools. No publisher has claimed this listing.

Emerging

74/100

rosclaw

Item: rosclaw
Rating: 74
Author: M8ven

Self-evolving runtime infrastructure for Physical AI and embodied agents. Ground AI agents into robot bodies with e-URDF, sandbox safety, capability routing, praxis capture, physical memory, runtime intervention, and skill evolution.

→ ros-claw/rosclaw · listed on github_code

Emerging. No concerning findings. Grades remain capped until the project builds reputation through adoption. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

Code Verified⚡ Live Monitored: not connected

Verified is a snapshot. Live keeps it current, and builds your track record.

⚡ Connect GitHub → continuous verification on every push why connect →

Who stands behind it

ros-claw

Source: github_code

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →

⚡ Connect GitHub for Live Monitored

Install from

GitHub

The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.

// key findings

✅

72 tools verified — handlers match their declared behaviour

8 read-only tools verified — handlers contain no write/delete/exec

✅

No credential exfiltration, no sensitive file access, no obfuscation

Static analysis found nothing flowing your secrets to unexpected places.

✅

Open source with a license and README

Anyone can audit the code, the license is declared, and the publisher documents what it does.

🔐

You'll be asked for 7 credentials: KIMI_API_KEY, ROSCLAW_CONTROL_TOKEN, ROSCLAW_KIMI_API_KEY, GITHUB_TOKEN, GH_TOKEN, EXP4_SUDO_PASS, ROSCLAW_RELEASE_KEY

These are read from process.env at runtime. Make sure you trust where they’ll be sent.

// tools this server exposes72 tools

These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.

rosclaw_observe

rosclaw_verify

rosclaw_memory_query

Query memory/practice/how with evidence references.

rosclaw_fail_safe

rosclaw_capabilities

rosclaw_stop_operation

Stop a running operation (ledger-first cancel, audited).

rosclaw_task_submit

rosclaw_task_observe

rosclaw_task_steer

Send a steering note to the SAME running execution session.

rosclaw_task_answer

Answer an execution's question (INPUT_REQUIRED) — same session continues.

rosclaw_task_pause

Pause a running execution (control ACK — session preserved).

rosclaw_task_resume

Resume a paused execution (same session).

rosclaw_task_cancel

Cancel an execution (audited control cancel).

rosclaw_inspect

process_start

process_status

Read an operation's authoritative state (RUNNING/SUCCEEDED/FAILED/CANCELLED + heartbeat).

process_output

Read an operation's stdout/stderr stream (newest last; bounded tail).

process_stop

Stop a running operation (ledger-first cancel — audited).

rosclaw_deliver

rosclaw_request_action

rosclaw_status

rosclaw_task_inspect

rosclaw_artifact_list

rosclaw_artifact_resolve

bash

write

Create/overwrite a file inside the project workspace (path-checked).

edit

read

Read a file inside the workspace (path-checked).

ls

List a directory inside the workspace (path-checked).

find

Find files by name substring inside the workspace (path-checked).

grep

Search file contents (literal substring) inside the workspace (path-checked).

ask_user

tool_func

ros_ping

Check if rosbridge is reachable and detect ROS version.

ros_discover

Discover topics, services, actions, nodes, and parameters.

ros_compile_manifest

Compile capabilities from the ROS graph.

ros_list_capabilities

List capabilities available through the registered ROS provider.

ros_inspect_capability

ros_validate_capability

ros_execute_capability

ros_emergency_stop

dynamic_tool_70

dynamic_tool_83

system.list_robots

List all available robots in the e-URDF-Zoo registry

system.list_providers

List all registered capability providers (llm, vlm, skill, critic, etc.)

system.run_sandbox_task

system.query_memory

Query ROSClaw Memory for past experiences, failures, or success patterns

system.explain_failure

Explain the most recent failure and get recovery suggestions from Memory/How

system.compile_asset_bundle

Compile an Asset Bundle (Skill Manifest + Provider Manifest + Tests) for a new capability

system.get_version

Get ROSClaw version and system status

ur5_get_joint_states

Get current joint positions, velocities, and efforts

ur5_move_joints

ur5_execute_trajectory

ur5_emergency_stop

ur5_get_limits

Get robot joint limits and safety parameters

ur5_validate_trajectory

Validate trajectory through Digital Twin without executing

limo.localization.get_pose

读取 LIMO 当前定位位姿（仿真观测，SIMULATED 证据域）。

limo.health

LIMO 仿真健康状态（电量/驱动/定位在线）。

limo.speaker.play_tone

播放提示音（物理动作；SIM 下为仿真执行）。

limo.localization.set_initial_pose

设置地图初始位姿（物理动作；SIM 下为仿真执行）。

ur5e.plan_cartesian_path

规划笛卡尔轨迹（COMPUTE，无副作用）：任意路径点

ur5e.execute_plan

执行已规划的轨迹（物理动作；SIM 下为仿真执行）——

ur5e.execute_cartesian_path

[deprecated——dev 兼容层] 直接执行完整轨迹对象；

ur5e.get_cartesian_trace

读取最近执行的笛卡尔轨迹 trace（时间序列 + hash + SVG，

ur5e.render_trace_preview

确定性路径预演渲染（COMPUTE）：把最近执行的 trace 渲染成

ur5e.verify_drawing

后验几何验证（COMPUTE，NOT_INDEPENDENT/非独立证据）：

ur5e.reset_simulation

重置仿真状态（CONTROL——按策略经授权链或维护通道）。

ur5e.get_joint_state

读取 UR5e 当前 6 关节角（rad，SIM 观测）。

ur5e.get_end_effector_pose

读取 UR5e 末端执行器位姿（x/y/z 米 + roll/pitch/yaw rad，SIM 观测）。

ur5e.move_joints

关节空间运动到目标关节角（物理动作；SIM 下为仿真执行）。

ur5e.move_to_pose

末端执行器移动到目标位姿（物理动作；SIM 下为仿真执行；

ur5e.stop

停止当前运动并保持状态（物理动作；SIM 下为仿真执行）。

// environment variables

To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.

🔐 secretKIMI_API_KEY

configPI_CODING_AGENT_DIR

configPI_SKIP_VERSION_CHECK

🔐 secretROSCLAW_CONTROL_TOKEN

configROSCLAW_HOMEset, otherwise $/data/practice (default ~/.rosclaw/data/practice).

🔐 secretROSCLAW_KIMI_API_KEY

configROSCLAW_PRODUCT_VERSION

configROSCLAW_TUI_UNICODE

configROSCLAW_UI_LOCALE

configROSCLAW_AGENT_CLIENT

configROSCLAW_MCP_TRANSPORT

configROSCLAW_MCP_HOST

configROSCLAW_MCP_PORT

configROSCLAW_ROBOT_ID

configROSCLAW_PROFILE

configROSCLAW_PROJECT_ROOT

configROSCLAW_LOG_LEVEL

configROSCLAW_MCP_FIXTURE

configROSCLAW_DEBUG_CONTEXT

configUR5_ROBOT_IP

configUR5_FIREWALL_MODEL

configROSCLAW_AGENT_ACTOR

configROSCLAW_AGENT_SESSION

configROSCLAW_MCP_HUB

configROSCLAW_EVOLUTION_ARENA_REPORT

configROSCLAW_PI_CLI

configROSCLAW_REQUIRE_JS_STAGE

configCANARY_RUNS

configXDG_STATE_HOME

🔐 secretGITHUB_TOKEN

🔐 secretGH_TOKEN

configREPLAY_EVENTS

🔐 secretEXP4_SUDO_PASS

configROSCLAW_PHYSICAL_GPU

configCUDA_VISIBLE_DEVICES

configROS_DISTRO

configAMENT_PREFIX_PATH

configEDITOR

configROSCLAW_SEEKDB_URL

configROSCLAW_PRACTICE_DEFAULT_PROVIDER

configROSCLAW_PRACTICE_HTTP_ADAPTER_URL

configDEEPSEEK_BASE_URL

configCOSMOS_ENDPOINT

configMINICPM_ENDPOINT

configVGGT_ENDPOINT

configROSCLAW_DEBUG

🔐 secretROSCLAW_RELEASE_KEY

configROSCLAW_AGENT_ENTRY

// quality suggestions

Tool annotations

19/72 tools have annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

72/72 tools missing one or more hints — rosclaw_observe (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); rosclaw_verify (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); rosclaw_memory_query (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +69 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.

For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.

Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.

// full audit trail

The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.

// improvement guidance — verified publishers only

We have 2 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.

// embed badge in your README

[![M8ven Score](https://m8ven.ai/badge/mcp/ros-claw/rosclaw)](https://m8ven.ai/mcp/ros-claw/rosclaw)

Shows your grade and updates automatically. Prefer no grade? Append ?variant=verified to the badge URL.

commit: cf9aeb3d58d92d041b95e81f237b88c90fec24ca

code hash: d3ff70fef3d8c1fe373b872dd6937fe888b20a427ab51cf60f101beea9ba6a41

view raw JSON →

Check MCPs from inside your assistant

Tool Check · MCP

Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.

https://m8ven.ai/api/mcp/tool-check

check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern

How to add it →Free · no account needed · works in any MCP client