Nerve MCP Server
nerve-mcp
npm
v0.2.2
Published by luchi0208 — 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.
MCP server for Nerve — gives AI agents runtime access to iOS apps
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 − 11 = 89. 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 |
|---|---|
| −10 | capability blast radius (critical) — 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 8
critical Completed toxic-flow trifecta across toolsMTC-FLOW-002
This server (without client built-ins) exposes a complete data-exfiltration chain: nerve_storage → nerve_tree → nerve_lldb. Untrusted input is ingested, private data is read, and it can be sent to an external sink via the agent composing the tools (→). Static analysis proves the primitive exists, not that a specific run will occur.
Fix: Remove one leg of the trifecta: isolate untrusted-input tools from secret-reading tools and from egress tools, or require human approval between them.
Location: flow nerve_storage → nerve_tree → nerve_lldb
high Tool "nerve_lldb" exposes command/code executionMTC-CAP-001
Tool "nerve_lldb" appears to run shell commands or evaluate code (parameter "command"). 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 nerve_lldb
high Tool "nerve_sequence" exposes command/code executionMTC-CAP-001
Tool "nerve_sequence" appears to run shell commands or evaluate code (parameter "command"). 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 nerve_sequence
high Shell/command execution in server code (dist/index.js)MTC-SRC-002
In the server's implementation (`dist/index.js:44`): 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: t(require("ws")); const child_process_1 = require("child_process"); const path = __importStar(require("path")); const fs
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 dist/index.js
medium Unconstrained command parameter "command" on "nerve_lldb"MTC-CAP-006
Tool "nerve_lldb" takes a command-shaped parameter "command" 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 nerve_lldb · inputSchema.properties.command
medium Unconstrained command parameter "command" on "nerve_sequence"MTC-CAP-006
Tool "nerve_sequence" takes a command-shaped parameter "command" 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 nerve_sequence · inputSchema.properties.command
low Mutating tool "nerve_lldb" declares no destructiveHintMTC-CAP-005
Tool "nerve_lldb" 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 nerve_lldb
low Mutating tool "nerve_sequence" declares no destructiveHintMTC-CAP-005
Tool "nerve_sequence" 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 nerve_sequence
Tools 40
Each tool and what it can reach — statically extracted from the published source.
nerve_lldbruns code / shellnerve_networknetwork egressnerve_sequenceruns code / shellnerve_storageingests untrusted inputnerve_treereads sensitive datanerve_actionno sensitive capabilitynerve_appearanceno sensitive capabilitynerve_backno sensitive capabilitynerve_boot_simulatorno sensitive capabilitynerve_buildno sensitive capability
Show 30 more tools ↓
nerve_consoleno sensitive capabilitynerve_context_menuno sensitive capabilitynerve_deeplinkno sensitive capabilitynerve_dismissno sensitive capabilitynerve_double_tapno sensitive capabilitynerve_drag_dropno sensitive capabilitynerve_grant_permissionsno sensitive capabilitynerve_heapno sensitive capabilitynerve_highlightno sensitive capabilitynerve_inspectno sensitive capabilitynerve_list_devicesno sensitive capabilitynerve_list_simulatorsno sensitive capabilitynerve_long_pressno sensitive capabilitynerve_mapno sensitive capabilitynerve_modifyno sensitive capabilitynerve_navigateno sensitive capabilitynerve_pinchno sensitive capabilitynerve_pull_to_refreshno sensitive capabilitynerve_runno sensitive capabilitynerve_run_deviceno sensitive capabilitynerve_screenshotno sensitive capabilitynerve_scrollno sensitive capabilitynerve_scroll_to_findno sensitive capabilitynerve_statusno sensitive capabilitynerve_swipeno sensitive capabilitynerve_tapno sensitive capabilitynerve_traceno sensitive capabilitynerve_typeno sensitive capabilitynerve_viewno sensitive capabilitynerve_wait_idleno 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 (40 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 |
|---|---|---|---|---|
v0.2.2 latest |
B 89/100 | 8 | 1.13.0 | 2026-09-07 |
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 nerve-mcp --onlineMore in Finance & Commerce
<img src="./public/logo.png" alt="1Money Logo" width="200"/>
Signed verification attestations for agent decisions: business, price, freshness, claim checks.
Actual Budget MCP server exposing API functionality
MCP server for Actual Budget - query and manage your personal finances through Claude
The Adyen Model Context Protocol server allows you to integrate with Adyen APIs through LLMs function calling utilizing various Clients. It currently supports the following tools:
Trusted agent-commerce hub: discover, trust-check, and route x402 payments with failover.