Telbase
NPM · TELBASE
Deploy any web project with one command. AI-native platform with self-healing feedback.
Available components
Last scanned (19 hours ago)
Scores higher than 51% of npm servers
Category CI/CD and DevOps
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security91
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- Declares code that runs automatically (postinstall) and that we could not recognise. It may be perfectly ordinary, but we have not established what it does. View diagnostics → Partial
- 5 of 5 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency13
- Repository check failed: the declared repository URL returned HTTP 404. See how to fix → View diagnostics → Fail
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Maintenance check failed: the publisher has marked this version as deprecated on the registry, telling users to stop installing it. See how to fix → Fail
- Security-disclosure policy not yet verified: we couldn't inspect the source repository.Unverified
Schema Quality & AI Usability79
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 685 tokens (~137/item across 5 items; 5 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
- No destabilizing schema changes in the last 30 days.Pass
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety75
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- 0 of 3 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "deploy" implies "deploy" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
- An AI judge read all 5 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 31 Oct 26 +1
- Stability: 0.97 → pass security
- 30 Oct 26 −1
- Stability: pass → 0.97 functional
- 24 Oct 26 +1
- Stability: 0.97 → pass security
- 22 Oct 26 −1
- Stability: pass → 0.93 functional
- 16 Oct 26 +1
- Stability: 0.97 → pass security
- 15 Oct 26 −1
- Maintenance: pass → fail ▼ functional
- 14 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.
- 12 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 4 Nov 2026 · Analysed npm/telbase@0.14.0-beta.2
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | npm |
Background: How many MCP packages publish verified provenance →
Install scripts 1 script
| Hook | Tier | Command |
|---|---|---|
| postinstall | unreviewed | node install.js |
Background: Why install scripts are a supply-chain risk →
Dependencies 5 packages
| Packages resolved | 5 |
|---|---|
| No linked repository | 5 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
deploy ~385
Deploy an application to production. Auto-detects framework (Next.js, Vite, Django, etc.) and database (Prisma, Drizzle). Auto-selects optimal infrastructure: Vercel for frontend/Node/Python, GCP Cloud Run for Docker/Django/Go. Database auto-provisioned: PostgreSQL on Neon/Cloud SQL, SQLite on Turso. Returns JSON with url, status, and detection context (ormType, confidence, databaseProvider). On build failure, returns suggestions[] array — each has type: cli_retry (call deploy again with suggested parameters), code_change (modify source file then redeploy), or user_action (tell user what to do). On HTTP 402, user must upgrade their plan — do not retry.
| Name | Type | Req | Description |
|---|---|---|---|
| auth_emails | null|array | – | Email addresses to protect app with (Email OTP login). |
| branch | string | – | Git branch to deploy. Default main. |
| database_provider | string | – | Force database provider: neon or turso. Auto-detected from ORM if omitted. |
| directory | string | – | Path to project directory. Defaults to current working directory. |
| no_auth | boolean | – | Disable authentication. |
| no_database | boolean | – | Deploy without database provisioning or detection. Use when project has no database. |
| no_storage | boolean | – | Skip file storage provisioning. |
| provider | string | – | Force compute provider: vercel or gcp. Auto-detected if omitted. |
| repo | string | – | GitHub repository URL (e.g. https://github.com/user/repo). Omit for local file deploy. |
| root_dir | string | – | Subdirectory for monorepos containing the app. |
| storage | boolean | – | Provision file storage (R2) for uploads. |
| wait | null|boolean | – | Wait for deploy to complete and return final status. Default true. |
No output schema declared.
No examples provided.
get_deploy_logs ~91
Get build or application logs for a deploy. Use log_type=build for build output (compilation errors, dependency issues), log_type=container for runtime logs (crashes, request errors). Build logs are most useful for diagnosing deploy failures.
| Name | Type | Req | Description |
|---|---|---|---|
| deploy_id | string | yes | The deploy ID to get logs for. |
| log_type | string | – | Log type: build or container. Default build. |
No output schema declared.
No examples provided.
get_deploy_status ~84
Get current status of a deploy. Returns status (building, live, failed, cancelled), url, detection context, and on failure: errorCode, errorMessage, extractedErrors[] with actionable suggestions, and buildLogs. If status is not terminal (building), poll again after a few seconds.
| Name | Type | Req | Description |
|---|---|---|---|
| deploy_id | string | yes | The deploy ID to check status for. |
No output schema declared.
No examples provided.
list_projects ~46
List all projects in the current organization. Returns array of projects with id, name, slug, status, url, provider, and databaseProvider. Use to find project IDs for other tools.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
set_env_vars ~79
Set environment variables on a project. Use before deploying if the app needs DATABASE_URL, API keys, or external service config. Variables persist across deploys. For secrets, values are encrypted at rest.
| Name | Type | Req | Description |
|---|---|---|---|
| project_id | string | yes | The project ID to set variables on. |
| vars | object | yes | Key-value pairs of environment variables to set. |
No output schema declared.
No examples provided.
How do I install the Telbase MCP server?
Telbase runs locally as an npm package, launched with npx -y telbase. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · telbase
claude mcp add ai-telbase-deploy -- npx -y telbase
What is the Telbase MCP server?
Telbase is an MCP server listed in the public MCP registry as ai.telbase/deploy. Deploy any web project with one command. AI-native platform with self-healing feedback. This page covers its npm package (telbase).
Is the Telbase MCP server safe to use?
Telbase scores 75 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 4 November 2026. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the Telbase MCP server expose?
Telbase exposes 5 tools: deploy, get_deploy_logs, get_deploy_status, list_projects, set_env_vars. Their descriptions and schemas cost roughly 685 tokens of context every time the server is loaded.
Is the Telbase MCP server still maintained?
Telbase is still listed as active in the MCP registry. We last reached this channel on 4 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the Telbase MCP server under?
Telbase declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.