Cursor Telegram MCP Server
cursor-telegram-mcp
npm
v0.9.3
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.
Manage Cursor from your phone over Telegram: an MCP server + auto-spawned local worker that notifies you, asks you questions, and (optionally) runs headless Cursor agents you text it. Local, bring-your-own-bot, runs entirely on your machine.
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 13
high Tool "run_background_job" exposes command/code executionMTC-CAP-001
Tool "run_background_job" appears to run shell commands or evaluate code (parameter "command"). Arbitrary execution driven by model input is one of the most dangerous MCP capabilities; combined with any untrusted input it becomes RCE.
Fix: Sandbox execution, allowlist commands/arguments, and never pass model output to a shell unescaped.
Location: tool run_background_job
high Shell/command execution in server code (dist/cliRunner.js)MTC-SRC-002
In the server's implementation (`dist/cliRunner.js:19`): 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 { clearRollingSession, loadRollingSession, saveRollingSession } from "./s
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/cliRunner.js
high Shell/command execution in server code (dist/doctor.js)MTC-SRC-002
In the server's implementation (`dist/doctor.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: spawnSync } from "node:child_process"; import { delimiter, join } from "node:path"; import { homedir, platform } 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/doctor.js
high Shell/command execution in server code (dist/index.js)MTC-SRC-002
In the server's implementation (`dist/index.js: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, mkdirSync, openSync } from "node:fs"; import { join } 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/index.js
high Shell/command execution in server code (dist/jobs.js)MTC-SRC-002
In the server's implementation (`dist/jobs.js:16`): 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, mkdirSync, readFileSync, rmSync, writeFileSync } from "node
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/jobs.js
high Shell/command execution in server code (dist/watchdog.js)MTC-SRC-002
In the server's implementation (`dist/watchdog.js:13`): 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 { getConfig } from "./config.js"; /** launchd label to restart; overridab
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/watchdog.js
high Shell/command execution in server code (dist/worker.js)MTC-SRC-002
In the server's implementation (`dist/worker.js:28`): 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: ync, spawn } from "node:child_process"; import { timingSafeEqual } from "node:crypto"; import { notifyAnswered, waitForA
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/worker.js
medium Hardcoded egress to an external endpoint (dist/doctor.js)MTC-SRC-003
In the server's implementation (`dist/doctor.js:17`): 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 res = await fetch(`https://api.telegram.org/bot${token}/getMe`, { method: "POST" }); const data = (a
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/doctor.js
medium Hardcoded egress to an external endpoint (dist/worker.js)MTC-SRC-003
In the server's implementation (`dist/worker.js:95`): 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 res = await fetch("https://registry.npmjs.org/cursor-telegram-mcp/latest", { signal: ctrl.signal
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/worker.js
medium Unconstrained command parameter "command" on "run_background_job"MTC-CAP-006
Tool "run_background_job" takes a command-shaped parameter "command" with no enum/pattern constraint. Free-form, model- or attacker-controlled arguments reaching a shell is the command-injection precondition.
Fix: Constrain the parameter (enum/pattern), or build the command from a fixed template with escaped args.
Location: tool run_background_job · inputSchema.properties.command
low Hardcoded egress to an external endpoint in packaging/dev tooling (dist/setup.js)MTC-SRC-003
In a packaging/dev/install script (shipped, but not the server runtime) (`dist/setup.js:16`): 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 res = await fetch(`https://api.telegram.org/bot${token}/${method}`, { method: "POST", header
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/setup.js
low Mutating tool "run_background_job" declares no destructiveHintMTC-CAP-005
Tool "run_background_job" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.
Fix: Declare accurate annotations, and gate destructive tools on user confirmation regardless.
Location: tool run_background_job
low Shell/command execution in packaging/dev tooling (dist/install.js)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`dist/install.js:13`): 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 { existsSync, mkdirSync, rmSync, writeFileSync } from "node:fs"; import {
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/install.js
Tools 7
Each tool and what it can reach — statically extracted from the published source.
run_background_jobruns code / shellask_human_and_waitno sensitive capabilityask_human_for_guidanceno sensitive capabilitycheck_background_jobno sensitive capabilitycheck_human_responseno sensitive capabilitylist_background_jobsno sensitive capabilitynotify_human_task_completeno sensitive capability
What this scan could not see
- Tools were statically extracted from the published source (7 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 1
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 |
|---|---|---|---|---|
v0.9.3 latest |
A 92/100 | 13 | 1.13.0 | 2026-09-05 |
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 cursor-telegram-mcp --onlineMore in Communication & Collaboration
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