Xmcp MCP Server
xmcp
npm
v1.1.3
Source verified
Published by basementstudio — publish provenance cryptographically ties this package to that repository. That is proof of origin, not an official vendor package.
The MCP framework
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 − 6 = 94. 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 |
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 17
high Dynamic code execution in server code (dist/index.js)MTC-SRC-001
In the server's implementation (`dist/index.js:65`): 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: ode.process(n,e));let a=Function(`${o.default.self}`,`${o.default.scope}`,n)(this,this.scope.get());if(this.scope.value(
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
high Dynamic code execution in server code (dist/runtime/adapter-express.js)MTC-SRC-001
In the server's implementation (`dist/runtime/adapter-express.js:65`): 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: ode.process(s,e));let i=Function(`${a.default.self}`,`${a.default.scope}`,s)(this,this.scope.get());if(this.scope.value(
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/runtime/adapter-express.js
high Dynamic code execution in server code (dist/runtime/adapter-fastify.js)MTC-SRC-001
In the server's implementation (`dist/runtime/adapter-fastify.js:65`): 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: ode.process(s,e));let i=Function(`${a.default.self}`,`${a.default.scope}`,s)(this,this.scope.get());if(this.scope.value(
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/runtime/adapter-fastify.js
high Dynamic code execution in server code (dist/runtime/adapter-nestjs.js)MTC-SRC-001
In the server's implementation (`dist/runtime/adapter-nestjs.js:1`): 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: ]);return r.name=e.name,Function("fn","log","deprecate","message","site",'"use strict"\nreturn function ('+a+") {log.cal
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/runtime/adapter-nestjs.js
high Dynamic code execution in server code (dist/runtime/adapter-nextjs.js)MTC-SRC-001
In the server's implementation (`dist/runtime/adapter-nextjs.js:65`): 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: ode.process(s,e));let i=Function(`${a.default.self}`,`${a.default.scope}`,s)(this,this.scope.get());if(this.scope.value(
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/runtime/adapter-nextjs.js
high Dynamic code execution in server code (dist/runtime/http.js)MTC-SRC-001
In the server's implementation (`dist/runtime/http.js:1`): 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: ]);return i.name=e.name,Function("fn","log","deprecate","message","site",'"use strict"\nreturn function ('+a+") {log.cal
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/runtime/http.js
high Dynamic code execution in server code (dist/runtime/stdio.js)MTC-SRC-001
In the server's implementation (`dist/runtime/stdio.js:65`): 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: ode.process(s,e));let i=Function(`${a.default.self}`,`${a.default.scope}`,s)(this,this.scope.get());if(this.scope.value(
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/runtime/stdio.js
high Dynamic code execution in server code (dist/runtime/vercel.js)MTC-SRC-001
In the server's implementation (`dist/runtime/vercel.js:1`): 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: ]);return i.name=e.name,Function("fn","log","deprecate","message","site",'"use strict"\nreturn function ('+a+") {log.cal
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/runtime/vercel.js
high Shell/command execution in server code (dist/index.js)MTC-SRC-002
In the server's implementation (`dist/index.js:1`): 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: ict";e.exports=require("child_process")},6982(e){"use strict";e.exports=require("crypto")},9896(e){"use strict";e.export
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 Dynamic module load from a non-literal (dist/runtime/adapter-express.js)MTC-SRC-005
In the server's implementation (`dist/runtime/adapter-express.js:181`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. 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" }) ); await import(blobUrl); let nextId = 1; window.parent.postMessage({ jsonrpc: "2.0",
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/runtime/adapter-express.js
medium Dynamic module load from a non-literal (dist/runtime/adapter-fastify.js)MTC-SRC-005
In the server's implementation (`dist/runtime/adapter-fastify.js:181`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. 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" }) ); await import(blobUrl); let nextId = 1; window.parent.postMessage({ jsonrpc: "2.0",
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/runtime/adapter-fastify.js
medium Dynamic module load from a non-literal (dist/runtime/adapter-nestjs.js)MTC-SRC-005
In the server's implementation (`dist/runtime/adapter-nestjs.js:181`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. 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" }) ); await import(blobUrl); let nextId = 1; window.parent.postMessage({ jsonrpc: "2.0",
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/runtime/adapter-nestjs.js
medium Dynamic module load from a non-literal (dist/runtime/adapter-nextjs.js)MTC-SRC-005
In the server's implementation (`dist/runtime/adapter-nextjs.js:181`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. 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" }) ); await import(blobUrl); let nextId = 1; window.parent.postMessage({ jsonrpc: "2.0",
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/runtime/adapter-nextjs.js
medium Dynamic module load from a non-literal (dist/runtime/cloudflare-worker.js)MTC-SRC-005
In the server's implementation (`dist/runtime/cloudflare-worker.js:177`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. 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" }) ); await import(blobUrl); let nextId = 1; window.parent.postMessage({ jsonrpc: "2.0",
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/runtime/cloudflare-worker.js
medium Dynamic module load from a non-literal (dist/runtime/http.js)MTC-SRC-005
In the server's implementation (`dist/runtime/http.js:181`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. 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" }) ); await import(blobUrl); let nextId = 1; window.parent.postMessage({ jsonrpc: "2.0",
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/runtime/http.js
medium Dynamic module load from a non-literal (dist/runtime/stdio.js)MTC-SRC-005
In the server's implementation (`dist/runtime/stdio.js:165`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. 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" }) ); await import(blobUrl); let nextId = 1; window.parent.postMessage({ jsonrpc: "2.0",
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/runtime/stdio.js
medium Dynamic module load from a non-literal (dist/runtime/vercel.js)MTC-SRC-005
In the server's implementation (`dist/runtime/vercel.js:181`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. 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" }) ); await import(blobUrl); let nextId = 1; window.parent.postMessage({ jsonrpc: "2.0",
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/runtime/vercel.js
Tools 3
Each tool and what it can reach — statically extracted from the published source.
nameno sensitive capabilityresource nameno sensitive capabilityxmcp React Widgetno sensitive capability
What this scan could not see
- Tools were statically extracted from the published source (3 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 7
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 |
|---|---|---|---|---|
v1.1.3 latest |
A 94/100 | 17 | 1.13.0 | 2026-09-07 |
v1.1.2 |
A 94/100 | 15 | 1.13.0 | 2026-09-01 |
v1.1.1 |
A 94/100 | 15 | 1.13.0 | 2026-08-29 |
v1.1.0 |
A 94/100 | 14 | 1.12.1 | 2026-08-24 |
v0.8.0 |
A 94/100 | 14 | 1.12.1 | 2026-08-22 |
Show 2 more versions ↓
v0.7.1 |
A 94/100 | 15 | 1.12.1 | 2026-08-20 |
v0.6.13 |
A 94/100 | 22 | 1.12.1 | 2026-08-16 |
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 xmcp --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.