Screenpipe MCP Server
screenpipe-mcp
npm
v0.19.4
Published by an unidentified publisher — no publish provenance and no public repository, so the publisher could not be verified and the source cannot be independently located.
MCP server for screenpipe - search your screen recordings and audio transcriptions
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 12
high Sensitive-source and external-sink co-existMTC-FLOW-004
Tools that read sensitive data ([team-records]) and tools that can send data out ([send-notification]) are exposed together. An agent can move private data to the sink.
Evidence: sources [team-records] → sinks [send-notification]
Fix: Keep secret-reading and egress capabilities on separate, separately-approved servers.
Location: flow team-records → send-notification
high Dynamic code execution in server code (dist/cli.js)MTC-SRC-001
In the server's implementation (`dist/cli.js:9832`): 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: const makeValidate = new Function(`${names_1.default.self}`, `${names_1.default.scope}`, sourceCode); const val
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.js
high Dynamic code execution in server code (dist/http-server.js)MTC-SRC-001
In the server's implementation (`dist/http-server.js:9832`): 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: const makeValidate = new Function(`${names_1.default.self}`, `${names_1.default.scope}`, sourceCode); const val
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/http-server.js
high Dynamic code execution in server code (dist/index.js)MTC-SRC-001
In the server's implementation (`dist/index.js:9832`): 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: const makeValidate = new Function(`${names_1.default.self}`, `${names_1.default.scope}`, sourceCode); const val
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 Shell/command execution in server code (dist/cli.js)MTC-SRC-002
In the server's implementation (`dist/cli.js:35545`): 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: sync = undefined; var child_process = require("child_process"); var util = require("util"); exports2.execAsync = u
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.js
high Shell/command execution in server code (dist/http-server.js)MTC-SRC-002
In the server's implementation (`dist/http-server.js:35545`): 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: sync = undefined; var child_process = require("child_process"); var util = require("util"); exports2.execAsync = u
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/http-server.js
high Shell/command execution in server code (dist/index.js)MTC-SRC-002
In the server's implementation (`dist/index.js:34560`): 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: sync = undefined; var child_process = require("child_process"); var util = require("util"); exports2.execAsync = u
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 Shell/command execution in server code (src/index.ts)MTC-SRC-002
In the server's implementation (`src/index.ts:108`): 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: File, exec } = require("child_process"); // eslint-disable-next-line @typescript-eslint/no-var-requires const { prom
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/index.ts
medium Unconstrained URL/host parameter "url" on "send-notification"MTC-CAP-007
Tool "send-notification" takes a URL/host parameter "url" with no allowlist/pattern. An outbound-request tool with an unbounded destination enables SSRF and cloud-metadata access (e.g. 169.254.169.254).
Fix: Allowlist destinations or constrain the parameter; block private/link-local addresses server-side.
Location: tool send-notification · inputSchema.properties.url
low Shell/command execution in packaging/dev tooling (scripts/assert-pack-contents.js)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/assert-pack-contents.js:36`): 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: eSync } = require("node:child_process"); const fs = require("node:fs"); const path = require("node:path"); const PKG_RO
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 scripts/assert-pack-contents.js
low Shell/command execution in packaging/dev tooling (src/self-contained-pack.test.ts)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`src/self-contained-pack.test.ts: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: ecFileSync } from "node:child_process"; import * as fs from "node:fs"; import * as os from "node:os"; import * as path 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 src/self-contained-pack.test.ts
low Shell/command execution in packaging/dev tooling (src/stdio-startup.test.ts)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`src/stdio-startup.test.ts: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: n, execFileSync } from "child_process"; import * as fs from "fs"; import { createServer } from "http"; import * as path
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/stdio-startup.test.ts
Tools 38
Each tool and what it can reach — statically extracted from the published source.
send-notificationnetwork egressteam-recordsreads sensitive dataactivity-summaryno sensitive capabilityadd-tagsno sensitive capabilitycontrol-recordingno sensitive capabilitycreate-pipeno sensitive capabilityCreating Pipesno sensitive capabilityCurrent Contextno sensitive capabilityexport-videono sensitive capabilityframe-contextno sensitive capability
Show 28 more tools ↓
get-feedbackno sensitive capabilityget-frame-elementsno sensitive capabilityget-meetingno sensitive capabilityhealth-checkno sensitive capabilitykeyword-searchno sensitive capabilitylist-audio-devicesno sensitive capabilitylist-meetingsno sensitive capabilitylist-monitorsno sensitive capabilitylist-pipesno sensitive capabilitylist-unnamed-speakersno sensitive capabilitymerge-speakersno sensitive capabilitypipe-logsno sensitive capabilityrun-pipeno sensitive capabilitysearch_contentno sensitive capabilitysearch-contentno sensitive capabilitysearch-elementsno sensitive capabilitysearch-speakersno sensitive capabilitysearch-synced-contentno sensitive capabilitystart-meetingno sensitive capabilitystop-meetingno sensitive capabilitysynced-devicesno sensitive capabilityteam-devicesno sensitive capabilityteam-frameno sensitive capabilityteam-searchno sensitive capabilityupdate-meetingno sensitive capabilityupdate-memoryno sensitive capabilityupdate-speakerno sensitive capabilityUsage Guideno sensitive capability
Toxic flows 1
Cross-tool combinations that form a data-exfiltration primitive (untrusted input → sensitive source → external sink).
What this scan could not see
- Tools were statically extracted from the published source (38 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 5
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 |
|---|---|---|---|---|
v0.19.4 latest |
A 92/100 | 12 | 1.13.0 | 2026-09-07 |
v0.19.1 |
A 92/100 | 7 | 1.13.0 | 2026-08-28 |
v0.19.0 |
A 92/100 | 7 | 1.12.1 | 2026-08-03 |
v0.18.16 |
A 92/100 | 6 | 1.12.1 | 2026-07-29 |
v0.18.15 |
A 92/100 | 4 | 1.12.1 | 2026-07-27 |
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 screenpipe-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.