@adeu/mcp-server
npm
v3.0.2
Source verified
Published by dealfluence — publish provenance cryptographically ties this package to that repository. That is proof of origin, not an official vendor package.
[](https://github.com/dealfluence/adeu) [](https://modelcontextprotocol.io/) [ — 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.
In the server's implementation (`src/test-rpc.ts:7`): 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: ildProcess } from "node:child_process"; import { resolve, join } from "node:path"; import { tmpdir } from "node:os"; imp
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 src/test-rpc.ts
In a packaging/dev/install script (shipped, but not the server runtime) (`src/mcp.schema-gaps.test.ts:23`): 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: ildProcess } from "node:child_process"; import { resolve, join } from "node:path"; import { tmpdir } from "node:os"; imp
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 src/mcp.schema-gaps.test.ts
In a packaging/dev/install script (shipped, but not the server runtime) (`src/parity_live.test.ts:120`): 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: } = await import("node:child_process"); const projectRoot = resolve(__dirname, "../../../.."); const pythonCli
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 src/parity_live.test.ts
In a packaging/dev/install script (shipped, but not the server runtime) (`src/repro.feedback.test.ts:17`): 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: ildProcess } from "node:child_process"; import { resolve, join, basename, dirname } from "node:path"; import { tmpdir }
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 src/repro.feedback.test.ts
In a packaging/dev/install script (shipped, but not the server runtime) (`src/repro.qa_2026_07_18.test.ts:10`): 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: ildProcess } from "node:child_process"; import { resolve, join } from "node:path"; import { tmpdir } from "node:os"; imp
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 src/repro.qa_2026_07_18.test.ts
In a packaging/dev/install script (shipped, but not the server runtime) (`src/repro.qa_2026_07_23.finalize.test.ts:34`): 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: ildProcess } from "node:child_process"; import { resolve } from "node:path"; import { existsSync } from "node:fs"; desc
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 src/repro.qa_2026_07_23.finalize.test.ts
In a packaging/dev/install script (shipped, but not the server runtime) (`src/repro.qa_report_v8.test.ts:17`): 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: rt { spawn } from "node:child_process"; import { existsSync } from "node:fs"; import { resolve } from "node:path"; impor
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 src/repro.qa_report_v8.test.ts
In a packaging/dev/install script (shipped, but not the server runtime) (`src/repro_qa_round3_2026_07_24.test.ts:32`): 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: ildProcess } from "node:child_process"; import { resolve, join } from "node:path"; import { tmpdir } from "node:os"; imp
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 src/repro_qa_round3_2026_07_24.test.ts
In a packaging/dev/install script (shipped, but not the server runtime) (`src/spec_2026_07_28.test.ts:3`): 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: ildProcess } from "node:child_process"; import { resolve } from "node:path"; import { fileURLToPath } from "node:url";
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 src/spec_2026_07_28.test.ts
In a packaging/dev/install script (shipped, but not the server runtime) (`tsup.config.ts:25`): 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: { execSync } from "node:child_process"; let gitSha = "unknown"; try { gitSha = execSync("git rev-parse --short HEAD",
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 tsup.config.ts
Each tool and what it can reach — statically extracted from the published source.
accept_all_changesno sensitive capabilityapply_text_revisionno sensitive capabilitydiff_docx_filesno sensitive capabilityfinalize_documentno sensitive capabilityprocess_document_batchno 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 |
|---|---|---|---|---|
v3.0.2 latest |
A 94/100 | 10 | 1.13.0 | 2026-09-07 |
v3.0.1 |
A 94/100 | 10 | 1.13.0 | 2026-08-27 |
v3.0.0 |
A 94/100 | 10 | 1.13.0 | 2026-08-25 |
v2.4.1 |
A 100/100 | 10 | 1.12.1 | 2026-08-22 |
v2.4.0 |
A 100/100 | 10 | 1.12.1 | 2026-08-18 |
v2.3.1 |
A 100/100 | 10 | 1.12.1 | 2026-08-13 |
v2.2.0 |
A 100/100 | 10 | 1.12.1 | 2026-08-12 |
v2.0.0 |
A 100/100 | 10 | 1.12.1 | 2026-08-10 |
v1.31.0 |
A 100/100 | 10 | 1.12.1 | 2026-08-07 |
v1.30.0 |
A 100/100 | 10 | 1.12.1 | 2026-08-03 |
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 @adeu/mcp-server --online
Independent packages implementing the same tool, scanned with the same engine. Compare all 2 side by side →
One key, 100+ models — chat with any LLM and generate video, images, speech. Free trial at 370.ai.
Retired compatibility stub for the AgentCanary MCP server. Daily briefs continue on X and Telegram.
A Backstage plugin that provides a chat interface for interacting with the MCP Servers.
Signal-first Bitcoin intelligence: sovereign, hiring & hashrate signals over MCP.
WhatsApp® reminders and rescheduling for Calendly. Public read-only MCP endpoint.
Open Source Generic MCP Client for testing & evaluating mcp servers and agents