tsdevstack/cli-mcp (tsdevstack/cli-mcp) is an MCP server listed on the M8ven Trust Index. It scores 60 out of 100, grade C. It declares 54 tools. No publisher has claimed this listing.

C
Caution
60/100

tsdevstack/cli-mcp

MCP server plugin for the tsdevstack CLI, enabling AI agents to manage infrastructure, deployment, and project state with 54 tools and 12 resources.

Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

Code Verified⚡ Live Monitored: not connected

Verified is a snapshot. Live keeps it current, and builds your track record.

⚡ Connect GitHub → continuous verification on every pushwhy connect →

Who stands behind it

tsdevstack

Source: Glama

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →

Install from

The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.

// key findings
⚠️
Known vulnerabilities in dependencies: 3 high
Affects packages this MCP installs at runtime. Upgrade or remove the affected dependency.
54 tools verified — handlers match their declared behaviour
14 read-only tools verified — handlers contain no write/delete/exec
No credential exfiltration, no sensitive file access, no obfuscation
Static analysis found nothing flowing your secrets to unexpected places.
Open source with a license and README
Anyone can audit the code, the license is declared, and the publisher documents what it does.
// tools this server exposes54 tools

These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.

add_bucket_storage

Add an object storage bucket to the project. What it does locally: - Adds bucket to storage.buckets in config.json - Regenerates docker-compose.yml with MinIO (S3-compatible) container + minio-init job that auto-creates the bucket - Regenerates secrets with STORAGE_ENDPOINT, STORAGE_ACCESS_KEY, STO

add_messaging_topic

Add an async messaging topic to the project. What it does: - Adds topic to messaging.topics in config.json with publishers and subscribers - Validates name (kebab-case, no duplicates, not reserved) - Validates publisher/subscriber service names exist and are NestJS type - Runs sync Service selecti

add_service

Add a new service (nestjs, nextjs, or spa). After this, run sync to regenerate all config. Types: nestjs (backend API), nextjs (SSR frontend), spa (Rsbuild SPA).

cloud_init

Initialize cloud provider credentials for a specific provider (gcp, aws, azure). One-time setup per provider. Provider must be passed as flag to skip interactive prompt.

cloud_secrets_push

Push secrets to cloud. Generates framework secrets, prompts for DOMAIN/RESEND_API_KEY/EMAIL_FROM, auto-derives the rest. Run once per environment during initial setup.

cloud_secrets_remove

Remove a secret from cloud secret manager. Verify the secret is unused before removing.

cloud_secrets_set

Set or update a single secret in cloud. Use for overrides or adding new third-party API keys.

deploy_kong

Rebuild and deploy Kong gateway. Run after changing routes (adding endpoints, changing auth decorators).

deploy_lb

Deploy/update the load balancer. Run after changing domains or adding frontend apps. Outputs DNS records and SSL validation info.

deploy_scheduler

Deploy a single scheduled job. Alternative to batch deploy_schedulers.

deploy_schedulers

Deploy all scheduled jobs (cron tasks) to cloud.

deploy_service

Build, push, deploy a single service (full workflow). Alternative to deploy_services --service. Supports optional tag override.

deploy_services

Deploy code changes to existing services only. Faster than full deploy. Use for code updates when no infrastructure changes are needed. Supports optional service filter.

generate_client

Generate TypeScript HTTP client + DTOs from a service's OpenAPI spec. Other services import this for type-safe API calls.

generate_docker_compose

Regenerate docker-compose.yml from current config. Run after adding services or storage buckets. When storage buckets exist in config.json, includes MinIO (S3-compatible storage) on ports 9000 (API) + 9001 (console) with a minio-init job that auto-creates buckets.

generate_kong

Regenerate Kong gateway config from OpenAPI specs. Run after adding/changing API endpoints or decorators.

generate_secrets

Regenerate local secrets files. Run after editing .secrets.user.json or after adding/removing storage buckets. Preserves existing JWT keys and passwords. When storage buckets exist, generates STORAGE_ENDPOINT, STORAGE_ACCESS_KEY, STORAGE_SECRET_KEY (for MinIO), and STORAGE_BUCKET_{NAME} for each buc

infra_bootstrap

Bootstrap cloud project (enable APIs, add roles). One-time setup per environment.

infra_build_docker

Build Docker images with BuildKit. Usually called internally by deploy. Supports --service for single build, --tag for custom tag (defaults to git SHA).

infra_build_kong

Build Kong Docker image. Usually called internally by deploy-kong.

infra_deploy

Full deployment: Terraform infra (VPC, DB, Redis, storage buckets) + build + push + deploy all services + Kong + LB. Required when adding new services or new storage buckets. Terraform creates cloud buckets (S3/GCS/Azure Blob) and post-Terraform sync pushes STORAGE_BUCKET_* secrets to cloud secret m

infra_destroy

Destroy ALL cloud infrastructure for an environment. Permanently deletes databases, services, and all data. Cannot be undone. Use with extreme caution.

infra_generate_ci

Regenerate CI workflows from ci.json. No credentials required.

infra_generate_docker

Generate Dockerfiles for services. Usually called internally by deploy. Supports optional service filter.

infra_generate_kong

Generate Kong declarative config from OpenAPI specs for cloud deployment. Usually called internally by deploy-kong.

infra_generate

Generate Terraform files from config. Usually called internally by deploy, but useful for previewing generated output.

infra_init_ci

Initialize CI/CD workflows (GitHub Actions). No credentials required.

infra_init

Initialize infrastructure (creates Terraform state bucket). One-time setup per environment.

infra_push_docker

Push Docker images to registry. Usually called internally by deploy. Supports --service for single push.

register_detached_worker

Register a detached worker in config.json. Only updates config — does NOT scaffold files. User must create worker.ts, worker.module.ts, and processor files manually using nest-common's startWorker(). After registering, run sync then infra_deploy.

remove_bucket_storage

Remove a storage bucket from the project configuration. What it does locally: - Removes bucket from storage.buckets in config.json - Regenerates docker-compose.yml (removes MinIO entirely if last bucket) - Regenerates secrets (removes STORAGE_* secrets if last bucket) - Does NOT delete any data fro

remove_detached_worker

Remove a detached worker from cloud. Cannot be undone.

remove_messaging_topic

Remove an async messaging topic from the project. What it does: - Removes topic from messaging.topics in config.json - Runs sync Does NOT delete stream data in Redis — existing messages are unaffected and get trimmed naturally via MAXLEN as new messages push old entries out.

remove_scheduler

Remove a single scheduled job from cloud. Cannot be undone.

remove_service_cloud

Remove a service from cloud (deletes container, secrets, database). Cannot be undone. Data is permanently lost. Follow-up (suggest to the user): if the removed service was a backend (nestjs), Kong still holds stale routes pointing to the deleted service. Run deploy_kong with the same env afterward

remove_service

Remove a service from the local project (deletes files, updates config). Does NOT remove from cloud — use remove_service_cloud for that.

run_db_migrate

Apply pending Prisma migrations for a service in cloud. Run plan_db_migrate first to preview changes.

sync

Regenerate all local config: secrets, docker-compose, kong, migrations. Run after adding services or changing secrets.

unregister_detached_worker

Remove a detached worker entry from config.json. Does NOT remove from cloud — use remove_detached_worker for that.

update_messaging_topic

Sets the publishers and subscribers for a topic. Values replace the current list entirely — pass all desired services, not just additions. For example, if a topic currently has subscribers ["offers-service", "notifications-service"] and you call this with subscribers "offers-service", the result wi

validate_service

Validate a service follows naming conventions and structure.

diff_secrets

Compare local secret names vs cloud — shows what's missing or extra. Run before deploying to catch mismatches.

get_infrastructure_config

Per-environment infrastructure settings: DB tiers, domains, scaling, custom overrides. This is a user-created file.

get_project_config

Full project configuration including service names, types, and workspace setup.

get_secret

Get a single secret value from cloud. Use to check if a secret is set (e.g., DOMAIN). Returns the value — use with care.

get_service_status

Cloud resource status for a specific service (running, image tag, URL, health).

infra_plan

Terraform plan — preview infrastructure changes without applying. Always run before `infra_deploy`.

infra_status

Check if infrastructure configuration is in sync (Terraform state vs config files).

list_deployed_services

All deployed services in a cloud environment with their current status.

list_environments

List configured cloud environments (dev, staging, prod) and their providers.

list_schedulers

Scheduled jobs (cron tasks) and their deployment status.

list_secrets

Secret names stored in a cloud environment's secret manager. Does NOT return values.

list_services

List all services in the project with their types and ports. Use this first to understand the project.

plan_db_migrate

Show pending Prisma database migrations for a service. Run before `run_db_migrate` to preview changes.

// known CVEs in dependencies3 high

Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.

high@modelcontextprotocol/sdk@1.12.1GHSA-345p-7cg4-v4c7

@modelcontextprotocol/sdk has cross-client data leak via shared server/transport instance reuse

high@modelcontextprotocol/sdk@1.12.1GHSA-8r9q-7v3j-jr4g

Anthropic's MCP TypeScript SDK has a ReDoS vulnerability

high@modelcontextprotocol/sdk@1.12.1GHSA-w48q-cv73-mx4w

Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default

Depend on this server? Get alerted when its CVEs change.Watch this server free →
// quality suggestions

Tool inputs are validated

44/54 tool handlers declare input schemas (81%)

Declare an inputSchema with zod/joi/yup on every tool definition.

Tool handlers catch errors

Only 4/54 tool handlers wrap calls in try/catch (7%)

Wrap each tool handler body in try/catch and return a structured error response.

Production dependencies are patched

0 critical, 3 high severity in production deps — @modelcontextprotocol/sdk@1.12.1 (high), @modelcontextprotocol/sdk@1.12.1 (high)

Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.

Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.

// full audit trail
The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.
// improvement guidance — verified publishers only
We have 3 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.
// embed badge in your README
[![M8ven Verified](https://m8ven.ai/badge/mcp/tsdevstack/cli-mcp?variant=verified)](https://m8ven.ai/mcp/tsdevstack/cli-mcp)
Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.
commit: e8ada378492f26fccce7469d923cbf96cfc3631e
code hash: 3715313182ba4847350a3aa872e45c9ac8f79c775daaf45f9196c6ee0de71ca9
view raw JSON →
Check MCPs from inside your assistant
Tool Check · MCP

Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.

https://m8ven.ai/api/mcp/tool-check
check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern
How to add it →Free · no account needed · works in any MCP client