depwire-cli
npm
v1.19.0
Published by depwire — 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.
Dependency graph + 23 MCP tools for AI coding assistants. Impact analysis, health scoring, security scanner, agent coordination.
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 − 24.9 = 75. What the published surface and source actually contain:
| Points | What was found | Category |
|---|---|---|
| −15.4 | Assembled command execution and dynamic evaluation in the same server MTC-SRC-011 | injection |
| −9.5 | Untrusted input concatenated into a command sink ×2 MTC-SRC-009 | injection |
2. Client adoption risk — 75 − 11 = 64. 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.
In the server's implementation (`dist/chunk-5EG3JK54.js:19890`): Evaluating a runtime value as code (rather than a fixed literal) executes whatever reaches it — a direct RCE primitive, and almost never necessary in legitimate code. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: suggestedFix: "Avoid eval(parse(text=...)). Use switch statements, match.arg(), or lookup tables instead." }, {
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/chunk-5EG3JK54.js
The implementation both builds shell commands out of runtime values (`dist/chunk-FPQKWAVT.js`) and evaluates runtime values as code (`dist/chunk-5EG3JK54.js`). Each is a separate arbitrary-execution primitive; a server exposing both gives anything that reaches either one a direct path to running attacker-chosen code. These two sinks are in different files — confirm whether they are actually connected, or are unrelated code paths (e.g. a vendored bundle plus a CLI wrapper).
Fix: Remove the dynamic eval, and pass command arguments as an argv array instead of building a shell string. If both are genuinely required, constrain and validate every value that can reach them.
Location: server implementation
In the server's implementation (`dist/chunk-5EG3JK54.js:19385`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: e if user input reaches eval().", suggestedFix: "Remove eval() and use safe alternatives (JSON.parse for data, speci
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/chunk-5EG3JK54.js
In the server's implementation (`dist/chunk-5EG3JK54.js:17069`): 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: port { execSync } from "child_process"; function generateHistory(graph, projectRoot, version) { let output = ""; con
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/chunk-5EG3JK54.js
In the server's implementation (`dist/chunk-FPQKWAVT.js:617`): 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: port { execSync } from "child_process"; async function getCommitLog(dir, limit) { try { if (limit !== void 0 && (!
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/chunk-FPQKWAVT.js
In the server's implementation (`dist/index.js:1559`): 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: port { execSync } from "child_process"; function git(cmd, cwd) { return execSync(`git ${cmd}`, { cwd, encoding: "utf-8
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
In the server's implementation (`dist/chunk-FPQKWAVT.js:624`): A shell/process command assembled from concatenated or interpolated values is command injection when any part is attacker-influenced — the OWASP canonical RCE flow. Verify what reaches the interpolated value. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: ""; const output = execSync( `git log ${limitArg} --pretty=format:"%H|%aI|%s|%an"`, { cwd: dir, encodin
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/chunk-FPQKWAVT.js
In the server's implementation (`dist/index.js:1561`): A shell/process command assembled from concatenated or interpolated values is command injection when any part is attacker-influenced — the OWASP canonical RCE flow. Verify what reaches the interpolated value. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: it(cmd, cwd) { return execSync(`git ${cmd}`, { cwd, encoding: "utf-8", stdio: ["pipe", "pipe", "pipe"] }).trim(); } fu
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
Tool "list_files" takes a path parameter "directory" with no constraint. Without a canonicalize-and-contain check (not visible statically), this permits ../ traversal outside the intended root.
Fix: Resolve and verify the path stays within an allowed root; reject traversal sequences.
Location: tool list_files · inputSchema.properties.directory
Each tool and what it can reach — statically extracted from the published source.
impact_analysisingests untrusted inputlist_filesreads sensitive dataaffected_filesno sensitive capabilityclaim_filesno sensitive capabilityconnect_repono sensitive capabilityfind_dead_codeno sensitive capabilityget_active_claimsno sensitive capabilityget_architecture_summaryno sensitive capabilityget_decisionsno sensitive capabilityget_dependenciesno sensitive capabilityget_dependentsno sensitive capabilityget_file_contextno sensitive capabilityget_health_scoreno sensitive capabilityget_project_docsno sensitive capabilityget_symbol_infono sensitive capabilityget_temporal_graphno sensitive capabilityrecord_decisionno sensitive capabilityrelease_filesno sensitive capabilitysearch_symbolsno sensitive capabilitysecurity_scanno sensitive capabilitysimulate_changeno sensitive capabilityupdate_project_docsno sensitive capabilityverify_changeno sensitive capabilityvisualize_graphno sensitive capabilityScan 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 |
|---|---|---|---|---|
v1.19.0 latest |
D 64/100 | 9 | 1.13.0 | 2026-09-07 |
v1.18.0 |
D 64/100 | 9 | 1.13.0 | 2026-08-30 |
v1.16.0 |
D 64/100 | 9 | 1.13.0 | 2026-08-28 |
v1.14.2 |
D 64/100 | 9 | 1.12.1 | 2026-08-19 |
v1.14.0 |
D 64/100 | 9 | 1.12.1 | 2026-08-16 |
v1.10.0 |
D 64/100 | 9 | 1.12.1 | 2026-08-15 |
v1.9.5 |
D 64/100 | 9 | 1.12.1 | 2026-08-14 |
v1.9.4 |
D 64/100 | 9 | 1.12.1 | 2026-08-14 |
v1.9.2 |
D 64/100 | 9 | 1.12.1 | 2026-08-10 |
v1.8.7 |
D 64/100 | 9 | 1.12.1 | 2026-08-06 |
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.
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 depwire-cli --online
Authenticated MCP transport with HTTP Signatures for AAuth agents
Local-first MCP server for parallel AI coding agents to claim file ownership before edits, preventing stomping on each other in the same worktree.
Agent-agnostic intercommunication system — sessions, messaging, channels, shared state, and real-time events
MCP server for AI agent task communication and delegation with diagnostic lifecycle visibility
Programmatic add/link/unlink for MCP servers across 23 AI coding agents (Claude Code, Claude Desktop, Cursor, VS Code, Codex, Gemini CLI, Zed, Cline, OpenCode, Goose, Kiro, Windsurf, and more). Functional API with dry-run support.
MCP server layer exposing agent-mesh orchestrator as an MCP agent