telegram-bot-mcp-server@1.0.1
CAUTION· startup onlyPublisher claims: "Self-hosted Telegram Bot MCP server for rich text, media and interactive buttons." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Startup only; authenticated tool behavior not tested.- Tested
- server startup over stdio (initialize sent) · every file read, file written and host contacted by what ran
- Not tested
- the tool list (the server exited before answering) · what the tools do when called with real credentials
What this means for the label: Caution here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.
Before you give it your token
- It will ask for
MCP_API_KEYTELEGRAM_BOT_ENROLLMENT_AUTHTELEGRAM_BOT_TOKENTELEGRAM_DRAFT_WORKFLOW_AUTHTELEGRAM_INBOX_DEFAULT_WEBHOOK_SECRETTELEGRAM_WEBHOOK_BOTS_JSONTELEGRAM_WEBHOOK_ENABLEDTELEGRAM_WEBHOOK_RETENTION_APPROVEDConfiguration, not credentials: AWS_LAMBDA_FUNCTION_NAME, TELEGRAM_API_HASH, TELEGRAM_API_ID, TELEGRAM_AVATAR_BOTS_JSON, TELEGRAM_AVATAR_WRITE_ENABLED, TELEGRAM_BOT_ENROLLMENT_ENABLED, TELEGRAM_BOT_MANAGEMENT_ENABLED, TELEGRAM_BUSINESS_BODY_READ_ENABLED, TELEGRAM_BUSINESS_DELETE_APPLY_ENABLED, TELEGRAM_BUSINESS_NOTICE_BOTS_JSON, TELEGRAM_BUSINESS_NOTICES_ENABLED, TELEGRAM_CALLBACK_ANSWER_ENABLED, TELEGRAM_CALLBACK_SEND_ENABLED, TELEGRAM_CHAT_ID, TELEGRAM_DELIVERY_ALLOW_DEFAULT_DESTINATION, TELEGRAM_DELIVERY_ALLOW_DISPATCH, TELEGRAM_DELIVERY_ALLOWED_DESTINATIONS_JSON, TELEGRAM_DELIVERY_BACKEND, TELEGRAM_DELIVERY_DB, TELEGRAM_DELIVERY_POSTGRES_ENABLED, TELEGRAM_DRAFT_PREVIEW_ENABLED, TELEGRAM_DRAFT_PREVIEW_TARGETS_JSON, TELEGRAM_DRAFT_STOP_EVENTS_ENABLED, TELEGRAM_DRAFT_WORKFLOW_ENABLED, TELEGRAM_INBOX_ALLOW_DEFAULT_DESTINATION, TELEGRAM_INBOX_DEFAULT_ACCEPT_CALLBACKS, TELEGRAM_INBOX_DEFAULT_ACCEPT_DRAFT_STOPS, TELEGRAM_INBOX_DEFAULT_ALLOWED_CHAT_IDS_JSON, TELEGRAM_INBOX_DEFAULT_RETAIN_TEXT, TELEGRAM_INBOX_DEFAULT_RETENTION_DAYS, TELEGRAM_INBOX_MCP_ENABLED, TELEGRAM_MEDIA_ALLOWED_DESTINATIONS_JSON- Where it talks to
- no vendor host named in the codeAlso telegram.org, example.invalid, internal.invalid — not the publisher's domain; check what for before connecting.
- What the honeypot saw
- no credential files read · no network
- What we could not test
- the tool list (the server exited before answering) · what the tools do when called with real credentials
Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names telegram.org, example.invalid, internal.invalid as well as its own vendor. The guard injects MCP_API_KEY, TELEGRAM_BOT_ENROLLMENT_AUTH, TELEGRAM_BOT_TOKEN, TELEGRAM_DRAFT_WORKFLOW_AUTH, TELEGRAM_INBOX_DEFAULT_WEBHOOK_SECRET, TELEGRAM_WEBHOOK_BOTS_JSON, TELEGRAM_WEBHOOK_ENABLED, TELEGRAM_WEBHOOK_RETENTION_APPROVED only into requests to the host you bind (and its subdomains) and refuses the rest.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; startup only; authenticated tool behavior not tested) on 2026-11-09 and scored it 75/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Access to sensitive file paths; Access to sensitive file paths; Access to sensitive file paths. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 41 s · 2 scenarios · 0 deviationsStatic findings
const args=messageDraftSchema.parse(input),env=options.env??(()=>process.env),snapshot={...env()};Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.const snapshot = { ...env() };Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.const env=options.env??(()=>process.env),snapshot={...env()};Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.const initialEnv = { ...env() }, endpoint = inboxEndpoint(alias,initialEnv);Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.const snapshot={...env()},signal=AbortSignal.any([AbortSignal.timeout(30000),...(options.signal?[options.signal]:[])]);Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.response = await fetch(`https://api.telegram.org/bot${config.token}/${method}`, {Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.…<string,unknown>={})=>{ guard();const response=await(options.fetcher??fetch)(`https://api.telegram.org/bot${token}/${method}`,{method:'POST',headers:{'content-type':'application/json'},b…Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.const env=options.env??(()=>process.env),snapshot={...env()};Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.const snapshot={...env()};Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.const env=dependencies.env??(()=>process.env),snapshot={...env()};Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.…[2]; if (!command || command === "help" || command === "--help") { console.log("Telegram delivery CLI: plan | draft | enqueue | status | recover | confirm | dispatch | demo\nPass input JSON on stdin. SQLite commands use TELEGRAM_DELIVERY_D…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.console.log(JSON.stringify(planInboxRetention(input.botAlias))); return;Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.const response = await (dependencies.fetcher ?? fetch)(`https://api.telegram.org/bot${token}/getMe`, {Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.console.log(JSON.stringify(await readInboxForCli(input)));Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.…n() { if (!["list", "plan-retention"].includes(process.argv[2])) { console.log("Inbox CLI: list reads approved scope {botAlias, chatIds?, afterSequence?, limit?}; plan-retention accepts {botAlias} and prints review-only SQL without databas…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.const env=dependencies.env??(()=>process.env),snapshot={...env()};Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.||Object.keys({...snapshot,...env()}).filter(k=>k.startsWith('TELEGRAM_')).some(k=>snapshot[k]!==env()[k]))denied();Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.const env = dependencies.env ?? (() => process.env), snapshot = { ...env() };Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.…; let valid=false; try{const response=await(dependencies.fetcher??fetch)(`https://api.telegram.org/bot${token}/getMe`,{method:'POST',body:'{}',headers:{'content-type':'application/js…Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.…et storing=false; try{ guard();const response=await(options.fetcher??fetch)(`https://api.telegram.org/bot${manager.token}/getManagedBotToken`,{method:'POST',headers:{'content-type':'app…Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.…udes('-h')) { console.log('Telegram Bot MCP Server 1.0.1\nUsage: telegram-bot-mcp-server [serve|build|start] [--port 3000]\nDefault: serve (build if needed, then start on 127.0.0.1).\nSet MCP_API_KEY and your own TELEGRAM_* settings in the…Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.console.log(JSON.stringify(planReport(str(input, "text"), input.maxChunkLength as number | undefined))); return;Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.const env=options.env??(()=>process.env),snapshot={...env()},args=managedImportInput(input);Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.".env.example",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.Cost to the agent
Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.
Known vulnerabilities
No advisories in OSV for @cyuanxv/telegram-bot-mcp-server@1.0.1 as of 5d ago. This is the package itself, not its dependencies.
What would make this Verified
5 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim cyuanxv: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- Telegram Bot API URL≈ +4 on the totalReplace encoded or assembled strings with plain literals and remove undeclared network calls.
- File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.
- MCP server using network transport (SSE/HTTP)≈ +2 on the totalNamespace tool names and keep tool descriptions literal; no instructions to the agent inside them.