Scrivener (writerslogic) MCP Server
scrivener-mcp
npm
v0.12.0
Source verified
Published by writerslogic — publish provenance cryptographically ties this package to that repository. That is proof of origin, not an official vendor package.
MCP server for Scrivener - Read, write, analyze, and search manuscripts with semantic search, character/plot tracking, writing analysis, and content enhancement. Works with Claude, ChatGPT, and other AI assistants.
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 − 1.2 = 99. What the published surface and source actually contain:
| Points | What was found | Category |
|---|---|---|
| −1.2 | Package runs install-time scripts MTC-SUP-010 | supply-chain |
2. Client adoption risk — 99 − 6 = 93. 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 12
high Shell/command execution in server code (dist/handlers/database/auto-installer.js)MTC-SRC-002
In the server's implementation (`dist/handlers/database/auto-installer.js:5`): 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: execFile, spawn } from 'child_process'; import { createWriteStream } from 'fs'; import * as fs from 'fs/promises'; 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 dist/handlers/database/auto-installer.js
high Shell/command execution in server code (dist/handlers/database/database-setup.js)MTC-SRC-002
In the server's implementation (`dist/handlers/database/database-setup.js:5`): 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: / import { exec } from 'child_process'; import * as fs from 'fs/promises'; import * as path from 'path'; import { promis
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/handlers/database/database-setup.js
high Shell/command execution in server code (dist/services/auto-setup/ai-config-wizard.js)MTC-SRC-002
In the server's implementation (`dist/services/auto-setup/ai-config-wizard.js: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: { execFileSync } from 'child_process'; import { getLogger } from '../../core/logger.js'; import { writeJSON, getEnv } f
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/services/auto-setup/ai-config-wizard.js
high Shell/command execution in server code (dist/services/auto-setup/keydb-installer.js)MTC-SRC-002
In the server's implementation (`dist/services/auto-setup/keydb-installer.js:6`): 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: ; import { exec } from 'child_process'; import { promisify } from 'util'; import { getLogger } from '../../core/logger.j
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/services/auto-setup/keydb-installer.js
high Shell/command execution in server code (dist/utils/adaptive-timeout.js)MTC-SRC-002
In the server's implementation (`dist/utils/adaptive-timeout.js:435`): 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: cFile } = await import('child_process'); const { promisify } = await import('util');
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/utils/adaptive-timeout.js
high Shell/command execution in server code (dist/utils/condition-waiter.js)MTC-SRC-002
In the server's implementation (`dist/utils/condition-waiter.js:208`): 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: cFile } = await import('child_process'); const { promisify } = await import('util'); const execF
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/utils/condition-waiter.js
high Shell/command execution in server code (dist/utils/env-config.js)MTC-SRC-002
In the server's implementation (`dist/utils/env-config.js:8`): 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: { execFileSync } from 'child_process'; import { getLogger } from '../core/logger.js'; import { ValidationUtils, FileUti
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/utils/env-config.js
high Shell/command execution in server code (dist/utils/permission-manager.js)MTC-SRC-002
In the server's implementation (`dist/utils/permission-manager.js:5`): 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: / import { exec } from 'child_process'; import { promisify } from 'util'; import { ApplicationError, ErrorCode } from '.
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/utils/permission-manager.js
high Shell/command execution in server code (dist/utils/scrivener-app.js)MTC-SRC-002
In the server's implementation (`dist/utils/scrivener-app.js:14`): 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: port { execFile } from 'child_process'; import * as path from 'path'; import { promisify } from 'util'; const execFileAs
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/utils/scrivener-app.js
high Shell/command execution in server code (dist/utils/shared-patterns.js)MTC-SRC-002
In the server's implementation (`dist/utils/shared-patterns.js:9`): 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: exec, execFile } from 'child_process'; const execAsync = promisify(exec); const execFileAsync = promisify(execFile); co
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/utils/shared-patterns.js
medium Hardcoded egress to an external endpoint (dist/services/auto-setup/ai-config-wizard.js)MTC-SRC-003
In the server's implementation (`dist/services/auto-setup/ai-config-wizard.js:97`): 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 response = await fetch('https://api.openai.com/v1/models', { headers: { Autho
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/services/auto-setup/ai-config-wizard.js
low Package runs install-time scripts (postinstall)MTC-SUP-010
"scrivener-mcp" executes postinstall script(s) at install time. An install hook runs at install time; most are routine build/setup, but review what it does before trusting it.
Evidence: node scripts/postinstall.cjs
Fix: Review the scripts; install with --ignore-scripts where possible and vet what they do.
Location: package scrivener-mcp
What this scan could not see
- No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, scan the running server: --command "npx -y <package>".
Versions 4
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 |
|---|---|---|---|---|
v0.12.0 latest |
A 93/100 | 12 | 1.13.0 | 2026-09-07 |
v0.11.0 |
A 93/100 | 12 | 1.10.0 | 2026-07-25 |
v0.10.0 |
A 93/100 | 12 | 1.9.0 | 2026-07-24 |
v0.9.3 |
B 88/100 | 12 | 1.8.0 | 2026-07-23 |
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 scrivener-mcp --onlineOther implementations of Scrivener 1
Independent packages implementing the same tool, scanned with the same engine. Compare all 2 side by side →
More in Web, Search & Scraping
Agent IP: MCP server with patents search tools
MCP server for searching the Agent Almanac — the public catalog of 9,000+ Model Context Protocol servers. Find, install, and discover MCP servers from inside Claude Desktop, Cursor, Continue, Zed, or any MCP-aware agent.
Search agents & MCP servers by capability, with daily-observed pricing, liveness and market data.
Verified merchants accepting agentic payments on Lightning/L402/BOLT12/USDT — search, verify, pay.
Airframe MCP Client - Connect agents to Airframe's product intelligence
Amazon product search demand over time, with growth for any keyword. Free key at trendsmcp.ai