Llm Bridge (npm) MCP Server
mcp-llm-bridge
npm
v0.5.1
Published by an unidentified publisher — no publish provenance and no public repository, so the publisher could not be verified and the source cannot be independently located.
MCP server that routes LLM calls through CLI subscriptions (Claude, Gemini, Codex, Copilot)
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 − 8 = 92. 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 |
| −2 | publisher verification (unlinked) — no provenance/repo link, but the shipped source was fully read |
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 4
high Shell/command execution in server code (dist/index.js)MTC-SRC-002
In the server's implementation (`dist/index.js:498`): 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: eSync, execFile } from "child_process"; // src/security/sanitize.ts var API_KEY_PATTERNS = [ // Anthropic: sk-ant-*
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 Hardcoded egress to an external endpoint (dist/chunk-2BDEDDWJ.js)MTC-SRC-003
In the server's implementation (`dist/chunk-2BDEDDWJ.js:65`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. 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 tokenRes = await fetch("https://github.com/login/oauth/access_token", { method: "POST", headers: { "Conte
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-2BDEDDWJ.js
medium Tool "vault_delete_file" can modify the filesystemMTC-CAP-002
Tool "vault_delete_file" can write, overwrite or delete files (keyword "delete_file" 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 vault_delete_file
low Mutating tool "vault_delete_file" declares no destructiveHintMTC-CAP-005
Tool "vault_delete_file" 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 vault_delete_file
Tools 25
Each tool and what it can reach — statically extracted from the published source.
conversation_get_pageingests untrusted inputvault_delete_filewrites filesvault_list_filesreads sensitive datacircuit_breaker_statsno sensitive capabilitycode_searchno sensitive capabilityconfigure_circuit_breakerno sensitive capabilityconversation_check_compactionno sensitive capabilityconversation_contextno sensitive capabilityconversation_find_relevantno sensitive capabilityconversation_infono sensitive capability
Show 15 more tools ↓
conversation_navigateno sensitive capabilityconversation_paginateno sensitive capabilitycreate_groupno sensitive capabilitydelete_groupno sensitive capabilityindex_codebaseno sensitive capabilitylist_groupsno sensitive capabilityllm_generateno sensitive capabilityllm_modelsno sensitive capabilityshared_stateno sensitive capabilityusage_queryno sensitive capabilityusage_summaryno sensitive capabilityvault_deleteno sensitive capabilityvault_listno sensitive capabilityvault_storeno sensitive capabilityvault_store_fileno sensitive capability
What this scan could not see
- Tools were statically extracted from the published source (25 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 |
|---|---|---|---|---|
v0.5.1 latest |
A 92/100 | 4 | 1.13.0 | 2026-09-08 |
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 mcp-llm-bridge --onlineOther implementations of Llm Bridge 1
Independent packages implementing the same tool, scanned with the same engine. Compare all 2 side by side →
More in AI & Agents
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