mcp-llm-bridge (JNZader/mcp-llm-bridge) is an MCP server listed on the M8ven Trust Index. M8ven has not graded it: we have no way to read this server ourselves. No publisher has claimed this listing.

D
Caution
56/100
24 days ago

mcp-llm-bridge

MCP server that routes LLM calls through CLI subscriptions (Claude, Gemini, Codex, Copilot) — zero API tokens needed

Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

Code Verified⚡ Live Monitored: not connected

Verified is a snapshot. Live keeps it current, and builds your track record.

⚡ Connect GitHub → continuous verification on every pushwhy connect →

Who stands behind it

JNZader

Source: Glama · also listed on github_code

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →

Install from

M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.

// key findings
⚠️
Known vulnerabilities in dependencies: 3 high
Affects packages this MCP installs at runtime. Upgrade or remove the affected dependency.
No credential exfiltration, no sensitive file access, no obfuscation
Static analysis found nothing flowing your secrets to unexpected places.
Open source with a license and README
Anyone can audit the code, the license is declared, and the publisher documents what it does.
🔐
You'll be asked for 7 credentials: ADMIN_TOKEN, GITHUB_CLIENT_SECRET, GITHUB_OAUTH_SECRET, HF_TOKEN, LLM_GATEWAY_AUTH_TOKEN, LLM_GATEWAY_MASTER_KEY, OPENAI_API_KEY
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// known CVEs in dependencies3 high2 medium26 low

Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.

high@modelcontextprotocol/sdk@1.0.0GHSA-w48q-cv73-mx4w

Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default

high@opentelemetry/sdk-node@0.213.0GHSA-q7rr-3cgh-j5r3

Prometheus exporter process crash via malformed HTTP request

highhono@4.12.8GHSA-88fw-hqm2-52qc

hono: CORS Middleware reflects any Origin with credentials when `origin` defaults to the wildcard

medium@anthropic-ai/sdk@0.80.0GHSA-p7fg-763f-g4gf

Claude SDK for TypeScript has Insecure Default File Permissions in Local Filesystem Memory Tool

mediumhono@4.12.8GHSA-xf4j-xp2r-rqqx

Hono: Path traversal in toSSG() allows writing files outside the output directory

Depend on this server? Get alerted when its CVEs change.Watch this server free →
// environment variables
To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.
🔐 secretADMIN_TOKEN
configENABLE_MULTI_TENANT
configFALLBACK_STRATEGYfree-models enables free-model fallback routing
configFREE_MODEL_CATALOGtrue loads the free-model catalog at startup
configGITHUB_ALLOWED_USERS
configGITHUB_CLIENT_ID
🔐 secretGITHUB_CLIENT_SECRET
🔐 secretGITHUB_OAUTH_SECRET
🔐 secretHF_TOKENhf_xxxxxxxxxx # optional, for private repos
configLATENCY_ROUTINGtrue enables latency-based routing
configLLM_GATEWAY_AUTH_REQUIREDunset Force auth on or off explicitly
🔐 secretLLM_GATEWAY_AUTH_TOKENIf you set , add Authorization: Bearer <token> to every protected route.
configLLM_GATEWAY_CIRCUIT_BREAKER_ENABLED
configLLM_GATEWAY_CORS_ORIGINS
configLLM_GATEWAY_DB_PATH~/.llm-gateway/vault.db SQLite vault path
configLLM_GATEWAY_ENV
🔐 secretLLM_GATEWAY_MASTER_KEYyour-64-char-hex-key
configLLM_GATEWAY_OTLP_ENDPOINT
configLLM_GATEWAY_PORT3. Set environment variables such as , LLM_GATEWAY_AUTH_TOKEN, and optionally LLM_GATEWAY_MASTER_KEY.
configLLM_GATEWAY_SECURITY_PROFILElocal-dev Security profile for MCP tool exposure
configLLM_GATEWAY_TRACING_ENABLED
configLM_STUDIO_URL
configLOG_LEVEL
configMAX_COMPARISON_COST_USDcaps comparison-service spending
configMCP_DYNAMIC_SERVERSSet =true:
configMCP_SERVERS_DIRexport =./mcp-servers
configOLLAMA_URL
🔐 secretOPENAI_API_KEYFallback: if the local model fails to load, the embedder can fall back to OpenAI API (text-embedding-3-small) when is set
configTRUSTED_PROXY_IPS
// quality suggestions

Tool annotations

No tools have read-only/destructive annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

55/55 tools missing one or more hints — llm_generate (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); vault_store (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); vault_list (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +52 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.

For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.

Tool test coverage

Only 4/55 tools referenced in tests (7%)

Write tests that reference each tool by name so every tool has at least one test.

Shell command execution

25 child_process calls — runs shell commands

Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.

Production dependencies are patched

0 critical, 3 high severity in production deps — @modelcontextprotocol/sdk@1.0.0 (high), @opentelemetry/sdk-node@0.213.0 (high)

Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.

Dependency freshness

2/20 production deps stale: @xenova/transformers@2024-05-29 (2.2y), prom-client@2024-06-27 (2.1y)

Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.

// full audit trail
The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.
// improvement guidance — verified publishers only
We have 5 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.
// embed badge in your README
[![M8ven Verified](https://m8ven.ai/badge/mcp/jnzader-mcp-llm-bridge-1stypz?variant=verified)](https://m8ven.ai/mcp/jnzader-mcp-llm-bridge-1stypz)
Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.
commit: d709815f377c2ee2286e435bf1739e4e343952fb
code hash: 02101113040440558fa727d30196514096c26b8bf73fa3359055e0bec7c3ec95
verified: 8/7/2026, 4:21:36 AM
view raw JSON →
Check MCPs from inside your assistant
Tool Check · MCP

Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.

https://m8ven.ai/api/mcp/tool-check
check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern
How to add it →Free · no account needed · works in any MCP client