Rosbag MCP Server

rosbag-mcp PyPI v0.2.0

Published by cjh1995-ros — no publish provenance, so origin is unverified, but the source is public: the repository link below is self-declared yet readable, so you can inspect the code before adopting it.

View on PyPI ↗ Repository ↗ Raw report (JSON) ↗

Trust grade

93/100

Last scanned 2026-07-23

Trust

A · 93/100

Adoption risk for you: the threat score, then adjusted down for blast radius, publisher verification and how much the scan could see. Deterministic; every point is auditable.

Capability

High

Blast radius if it went rogue — what the server’s tools could reach. Independent of trust.

Coverage

Source

How much the scan could actually inspect. Shallow coverage is stated, never hidden.

A Why this grade threat 100 − adoption risk = 93/100

The grade answers one question — how safe is this server for you to adopt — so it is computed in two auditable stages. Nothing below is an opinion or an LLM's guess; every line is a real term the deterministic engine applied, and the same input always yields the same number.

1. Threat score — 100 − 0 = 100. What the published surface and source actually contain:

The deterministic scan raised no scored threat in the surface it inspected — the threat score stayed at 100. Capability observations and advisory notes are recorded but never lower it.

2. Client adoption risk — 100 − 7 = 93. Three small, subtract-only factors that reflect your risk in adopting it — a clean scan proves less on a powerful, unverified or barely-inspectable package, so the grade says so plainly:

Points	Adoption-risk factor
−6	capability blast radius (high) — client exposure if the model is manipulated
−1	publisher verification (public source) — no provenance, but the source is public and inspectable
✓	inspection depth (source) — how much of the target the scan could see

Capability observations and info notes are shown under Findings but never scored. Open any row's finding below for the file, line and evidence behind a deduction.

Findings 40

high Read-and-egress in one tool: "export_to_csv"MTC-FLOW-003

Tool "export_to_csv" can both read sensitive data and send data to an external destination. Even without an explicit untrusted-input leg, this is a single-call data-exfiltration path if the model is ever manipulated.

Fix: Separate reading from sending; require explicit user confirmation before egress of file/secret contents.

Location: flow export_to_csv

high Read-and-egress in one tool: "analyze_wheel_slip"MTC-FLOW-003

Tool "analyze_wheel_slip" can both read sensitive data and send data to an external destination. Even without an explicit untrusted-input leg, this is a single-call data-exfiltration path if the model is ever manipulated.

Fix: Separate reading from sending; require explicit user confirmation before egress of file/secret contents.

Location: flow analyze_wheel_slip

high Sensitive-source and external-sink co-existMTC-FLOW-004

Tools that read sensitive data ([set_bag_path, bag_info, get_message_at_time, get_messages_in_range, search_messages, filter_bag, analyze_mcl_divergence, analyze_trajectory, analyze_lidar_scan, analyze_logs, get_tf_tree, get_image_at_time, plot_timeseries, plot_2d, plot_lidar_scan, get_topic_schema, analyze_imu, analyze_topic_stats, compare_topics, export_to_csv, detect_events, analyze_costmap_violations, analyze_path_tracking, analyze_wheel_slip, analyze_navigation_health, analyze_lidar_timeseries, plot_comparison, analyze_pointcloud2, analyze_joint_states, analyze_diagnostics]) and tools that can send data out ([export_to_csv, analyze_wheel_slip]) are exposed together. An agent can move private data to the sink.

Evidence: sources [set_bag_path, bag_info, get_message_at_time, get_messages_in_range, search_messages, filter_bag, analyze_mcl_divergence, analyze_trajectory, analyze_li

Fix: Keep secret-reading and egress capabilities on separate, separately-approved servers.

Location: flow set_bag_path → export_to_csv

high Tool "analyze_wheel_slip" exposes command/code executionMTC-CAP-001

Tool "analyze_wheel_slip" appears to run shell commands or evaluate code (parameter "cmd"). Arbitrary execution driven by model input is one of the most dangerous MCP capabilities; combined with any untrusted input it becomes RCE.

Fix: Sandbox execution, allowlist commands/arguments, and never pass model output to a shell unescaped.

Location: tool analyze_wheel_slip

medium Unconstrained command parameter "cmd_vel_topic" on "analyze_wheel_slip"MTC-CAP-006

Tool "analyze_wheel_slip" takes a command-shaped parameter "cmd_vel_topic" with no enum/pattern constraint. Free-form, model- or attacker-controlled arguments reaching a shell is the command-injection precondition.

Fix: Constrain the parameter (enum/pattern), or build the command from a fixed template with escaped args.

Location: tool analyze_wheel_slip · inputSchema.properties.cmd_vel_topic

medium Unconstrained command parameter "cmd_vel_field" on "analyze_wheel_slip"MTC-CAP-006

Tool "analyze_wheel_slip" takes a command-shaped parameter "cmd_vel_field" with no enum/pattern constraint. Free-form, model- or attacker-controlled arguments reaching a shell is the command-injection precondition.

Fix: Constrain the parameter (enum/pattern), or build the command from a fixed template with escaped args.

Location: tool analyze_wheel_slip · inputSchema.properties.cmd_vel_field

low Mutating tool "analyze_wheel_slip" declares no destructiveHintMTC-CAP-005

Tool "analyze_wheel_slip" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.

Fix: Declare accurate annotations, and gate destructive tools on user confirmation regardless.

Location: tool analyze_wheel_slip

low Unconstrained path parameter "path" on "set_bag_path"MTC-CAP-008

Tool "set_bag_path" takes a path parameter "path" with no constraint. Without a canonicalize-and-contain check (not visible statically), this permits ../ traversal outside the intended root.