Model Proxy MCP Server
@agimon-ai/model-proxy-mcp
npm
v0.29.20
Published by @agimon-ai — no publish provenance and no public repository, so the publisher could not be verified and the source cannot be independently located.
Claude-compatible model proxy MCP with ChatGPT Codex upstream support
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/cli.cjs)MTC-SRC-002
In the server's implementation (`dist/cli.cjs:2`): 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: ander`),c=require(`node:child_process`),l=require(`node:util`),u=require(`@agimon-ai/foundation-port-registry`),d=requir
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/cli.cjs
high Shell/command execution in server code (dist/cli.mjs)MTC-SRC-002
In the server's implementation (`dist/cli.mjs:2`): 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: ee,spawn as b}from"node:child_process";import{promisify as x}from"node:util";import{PortRegistryService as S}from"@agimo
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/cli.mjs
medium Hardcoded egress to an external endpoint (dist/stdio-C3pqLpYB.mjs)MTC-SRC-003
In the server's implementation (`dist/stdio-C3pqLpYB.mjs:14`): 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: fresh_token:t}),r=await fetch(`https://oauth2.googleapis.com/token`,{method:`POST`,headers:{"content-type":`application/
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/stdio-C3pqLpYB.mjs
medium Hardcoded egress to an external endpoint (dist/stdio-CcaHERH8.cjs)MTC-SRC-003
In the server's implementation (`dist/stdio-CcaHERH8.cjs:14`): 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: fresh_token:t}),r=await fetch(`https://oauth2.googleapis.com/token`,{method:`POST`,headers:{"content-type":`application/
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/stdio-CcaHERH8.cjs
Tools 6
Each tool and what it can reach — statically extracted from the published source.
get_active_profileno sensitive capabilityget_current_modelno sensitive capabilityget_proxy_statusno sensitive capabilitylist_profilesno sensitive capabilityset_model_targetno sensitive capabilityupsert_profileno sensitive capability
What this scan could not see
- Tools were statically extracted from the published source (6 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 10
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 |
|---|---|---|---|---|
v0.29.20 latest |
A 92/100 | 4 | 1.13.0 | 2026-09-07 |
v0.29.19 |
A 92/100 | 4 | 1.13.0 | 2026-09-05 |
v0.29.18 |
A 92/100 | 4 | 1.13.0 | 2026-08-25 |
v0.29.17 |
A 92/100 | 4 | 1.12.1 | 2026-08-25 |
v0.29.16 |
A 92/100 | 4 | 1.12.1 | 2026-08-21 |
Show 5 more versions ↓
v0.29.13 |
A 92/100 | 4 | 1.12.1 | 2026-08-20 |
v0.29.11 |
A 92/100 | 4 | 1.12.1 | 2026-08-18 |
v0.29.7 |
A 92/100 | 4 | 1.12.1 | 2026-08-17 |
v0.29.4 |
A 92/100 | 4 | 1.12.1 | 2026-08-16 |
v0.29.3 |
A 92/100 | 4 | 1.12.1 | 2026-08-15 |
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 @agimon-ai/model-proxy-mcp --onlineMore in Data Science & ML
MCP server for 2s.io — 575+ pay-per-call tools for AI agents — ground-truth data, AI gateway, and agent infra (storage, locks, queues, watchers). x402 USDC on Base/Solana, no API keys, upto usage billing, free trials.
ArXiv preprints + Google Scholar papers, with citation counts in one query.
Add MCP servers to your favorite coding agents with a single command.
Help agents automatically write and test stories for your UI components
Model Context Protocol server for AI-Archive platform - enables AI agents to discover, submit, and review research papers
MCP server for Semantic Scholar research workflows with stdio and Streamable HTTP transports.