Gobby MCP Server
gobby
PyPI
v0.4.6
Published by gobbyai — 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.
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 |
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 18
high Sensitive-source and external-sink co-existMTC-FLOW-004
Tools that read sensitive data ([get_usage_report]) and tools that can send data out ([can_spawn_agent, evaluate_spawn, send_message]) are exposed together. An agent can move private data to the sink.
Evidence: sources [get_usage_report] → sinks [can_spawn_agent, evaluate_spawn, send_message]
Fix: Keep secret-reading and egress capabilities on separate, separately-approved servers.
Location: flow get_usage_report → can_spawn_agent
high Tool "can_spawn_agent" exposes command/code executionMTC-CAP-001
Tool "can_spawn_agent" appears to run shell commands or evaluate code (keyword "spawn" in tool name). 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 can_spawn_agent
high Tool "evaluate_spawn" exposes command/code executionMTC-CAP-001
Tool "evaluate_spawn" appears to run shell commands or evaluate code (keyword "spawn" in tool name). 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 evaluate_spawn
high Shell/command execution in server code (build_backend/__init__.py)MTC-SRC-002
In the server's implementation (`build_backend/__init__.py:108`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: ) result = subprocess.run( # nosec B603 B607 command, cwd=_WEB_SRC, ch
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server build_backend/__init__.py
high Shell/command execution in server code (src/gobby/adapters/codex_impl/client.py)MTC-SRC-002
In the server's implementation (`src/gobby/adapters/codex_impl/client.py:154`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: self._process = subprocess.Popen( # nosec B603 # hardcoded argument list command,
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/gobby/adapters/codex_impl/client.py
high Shell/command execution in server code (src/gobby/agents/checkpoint_manager.py)MTC-SRC-002
In the server's implementation (`src/gobby/agents/checkpoint_manager.py:140`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: y: result = subprocess.run( ["git", *args], cwd=cwd, capture
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/gobby/agents/checkpoint_manager.py
high Shell/command execution in server code (src/gobby/agents/isolation.py)MTC-SRC-002
In the server's implementation (`src/gobby/agents/isolation.py:33`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: r) -> str: result = subprocess.run( # nosec B603 B607 # fixed git argv on local isolation path. ["git", "-C
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/gobby/agents/isolation.py
high Shell/command execution in server code (src/gobby/agents/sandbox.py)MTC-SRC-002
In the server's implementation (`src/gobby/agents/sandbox.py:508`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: try: result = subprocess.run( [ "git", "-C", str(w
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/gobby/agents/sandbox.py
high Shell/command execution in server code (src/gobby/agents/spawn_executor.py)MTC-SRC-002
In the server's implementation (`src/gobby/agents/spawn_executor.py:295`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: in terminal with direct spawn (no preflight). Session linkage approach: 1. Pre-create Gobby session with parent
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/gobby/agents/spawn_executor.py
high Shell/command execution in server code (src/gobby/agents/spawners/base.py)MTC-SRC-002
In the server's implementation (`src/gobby/agents/spawners/base.py:85`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: @abstractmethod def spawn( self, command: list[str], cwd: str | Path, env: dict[str,
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/gobby/agents/spawners/base.py
high Shell/command execution in server code (src/gobby/agents/tmux/session_manager.py)MTC-SRC-002
In the server's implementation (`src/gobby/agents/tmux/session_manager.py:152`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: result = subprocess.run( ["wsl", "--exec", "which", self._config.command],
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/gobby/agents/tmux/session_manager.py
high Shell/command execution in server code (src/gobby/agents/tmux/spawner.py)MTC-SRC-002
In the server's implementation (`src/gobby/agents/tmux/spawner.py:85`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: is_available() def spawn( self, command: list[str], cwd: str | Path, env: dict[str,
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/gobby/agents/tmux/spawner.py
high Shell/command execution in server code (src/gobby/build/branch_cleanup.py)MTC-SRC-002
In the server's implementation (`src/gobby/build/branch_cleanup.py:134`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: rocess[str]: return subprocess.run( # nosec B603 # git args are fixed by callers. ["git", *args], c
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/gobby/build/branch_cleanup.py
medium Tool "unlink_identity" can modify the filesystemMTC-CAP-002
Tool "unlink_identity" can write, overwrite or delete files (keyword "unlink" in tool name). Verify it is scoped to a safe directory.
Fix: Constrain file operations to an explicit, non-sensitive root; reject path traversal.
Location: tool unlink_identity
medium Dynamic module load from a non-literal (src/gobby/cli/installers/shared.py)MTC-SRC-005
In the server's implementation (`src/gobby/cli/installers/shared.py:256`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: y: module = __import__(module_path, fromlist=[func_name]) sync_fn = getattr(module, func_name)
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/gobby/cli/installers/shared.py
low Mutating tool "can_spawn_agent" declares no destructiveHintMTC-CAP-005
Tool "can_spawn_agent" 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 can_spawn_agent
low Mutating tool "evaluate_spawn" declares no destructiveHintMTC-CAP-005
Tool "evaluate_spawn" 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 evaluate_spawn
low Mutating tool "unlink_identity" declares no destructiveHintMTC-CAP-005
Tool "unlink_identity" 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 unlink_identity
Tools 96
Each tool and what it can reach — statically extracted from the published source.
can_spawn_agentruns code / shellevaluate_spawnruns code / shellget_usage_reportreads sensitive datasend_messagenetwork egressunlink_identitywrites filesadd_channelno sensitive capabilityadd_mcp_serverno sensitive capabilityaudit_memoriesno sensitive capabilitybootstrap_session_titleno sensitive capabilitybuild_turn_and_digestno sensitive capability
Show 86 more tools ↓
call_toolno sensitive capabilitycanvas_presentno sensitive capabilitycapture_baseline_dirty_filesno sensitive capabilitycleanup_memoriesno sensitive capabilityclose_canvasno sensitive capabilitycreate_cron_jobno sensitive capabilitycreate_memoryno sensitive capabilitydelete_cron_jobno sensitive capabilitydelete_memoryno sensitive capabilityensure_defaultsno sensitive capabilityget_agent_resultno sensitive capabilityget_cron_jobno sensitive capabilityget_failing_toolsno sensitive capabilityget_machine_idno sensitive capabilityget_memoryno sensitive capabilityget_messagesno sensitive capabilityget_metrics_timeseriesno sensitive capabilityget_related_memoriesno sensitive capabilityget_retention_statsno sensitive capabilityget_rule_metricsno sensitive capabilityget_running_agentno sensitive capabilityget_session_commitsno sensitive capabilityget_session_toolsno sensitive capabilityget_skillno sensitive capabilityget_skill_metricsno sensitive capabilityget_tool_metricsno sensitive capabilityget_tool_schemano sensitive capabilityget_tool_success_rateno sensitive capabilityget_top_toolsno sensitive capabilityget_transcript_statusno sensitive capabilityget_variableno sensitive capabilityhub_statsno sensitive capabilityimport_mcp_serverno sensitive capabilityinit_projectno sensitive capabilityinstall_skillno sensitive capabilitylink_identityno sensitive capabilitylist_agent_runsno sensitive capabilitylist_channelsno sensitive capabilitylist_config_keysno sensitive capabilitylist_cron_jobsno sensitive capabilitylist_cron_runsno sensitive capabilitylist_cross_project_sessionsno sensitive capabilitylist_cross_project_tasksno sensitive capabilitylist_hubsno sensitive capabilitylist_identitiesno sensitive capabilitylist_mcp_serversno sensitive capabilitylist_memoriesno sensitive capabilitylist_toolsno sensitive capabilitymemory_statsno sensitive capabilitymerge_abortno sensitive capabilitymerge_applyno sensitive capabilitymerge_resolveno sensitive capabilitymerge_startno sensitive capabilitymerge_statusno sensitive capabilitymove_skill_to_installedno sensitive capabilitymove_skill_to_projectno sensitive capabilityprobe_branch_protectionno sensitive capabilityrebuild_crossrefsno sensitive capabilityrebuild_knowledge_graphno sensitive capabilityrecommend_toolsno sensitive capabilityreindex_embeddingsno sensitive capabilityremember_with_imageno sensitive capabilityremove_channelno sensitive capabilityremove_mcp_serverno sensitive capabilityremove_skillno sensitive capabilityrender_surfaceno sensitive capabilityreset_metricsno sensitive capabilityreset_tool_metricsno sensitive capabilityrun_cron_jobno sensitive capabilityrunning_agent_statsno sensitive capabilitysearch_hubno sensitive capabilitysearch_knowledge_graphno sensitive capabilitysearch_memoriesno sensitive capabilitysearch_messagesno sensitive capabilitysearch_toolsno sensitive capabilitysession_statsno sensitive capabilityset_configno sensitive capabilityset_variableno sensitive capabilitystop_agentno sensitive capabilitysync_exportno sensitive capabilitysync_importno sensitive capabilitytoggle_cron_jobno sensitive capabilityupdate_cron_jobno sensitive capabilityupdate_memoryno sensitive capabilityupdate_surfaceno sensitive capabilitywait_for_interactionno sensitive capability
Toxic flows 1
Cross-tool combinations that form a data-exfiltration primitive (untrusted input → sensitive source → external sink).
What this scan could not see
- Tools were statically extracted from the published source (96 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Versions 1
Scan history per published version. The engine is deterministic — the same version always yields the same score, so a changed score means the package itself changed.
| Version | Score | Findings | Engine | Scanned |
|---|---|---|---|---|
v0.4.6 latest |
A 93/100 | 18 | 1.9.0 | 2026-07-23 |
Embed this score
Show this server's live Trust Score in your README, docs or website. The badge is served straight from the registry and updates automatically after every rescan — no API key needed. It links back to this page, so anyone who sees the grade can also read the findings behind it instead of taking a number on faith.
Verify this score yourself
The score above is reproducible: the same package version always yields the same result. Run it locally or over the free API — no account, no LLM, fully deterministic.
npx mcptrustchecker scan gobby --online --registry pypiMore in Developer Tools
Security scan results for the 1stay MCP server.
Security scan results for the Adguard Home MCP server.
Security scan results for the Ado Browser MCP server.
Security scan results for the Adobe Experience Dev MCP server.
Security scan results for the Aemet MCP server.
Security scan results for the Affinity Mcp Bridge MCP server.