Loading…
Build, migrate, and audit Contentstack Marketplace apps with AI coding agents via a remotely hosted MCP server.
Do not connect
A critical issue was found. Do not connect this server as-is.
Scanned 1 month ago Due for re-check
A server can change after it's graded. Re-run the automated scan to refresh this report.
This grade is deterministic and reproducible: the same server surface always yields the same grade under a given algorithm version. It is a real automated assessment computed by the MCPGrade engine from what the probe actually observed — not a fabricated or opinion score. It is not a manual human pentest, so it can miss context-specific risks.
Every signal below was measured directly by the automated probe. The grade is derived only from evidence like this — nothing is assumed.
The mcp-typescript server on vercel MCP server exposes 8 tools, focused primarily on general-purpose capabilities. Its published description reads: "Build, migrate, and audit Contentstack Marketplace apps with AI coding agents via a remotely hosted MCP server". It communicates over Streamable HTTP using the 2025-06-18 protocol revision, and does not require authorization to connect. MCPGrade currently rates mcp-typescript server on vercel F — a critical issue was found and the server should not be connected as-is. Its most notable findings include "Cross-tool shadowing" and "Cross-tool shadowing". This report is a deterministic, reproducible automated assessment: the same observed surface always yields the same grade under a given algorithm version, and it is refreshed as new scans arrive and free to read — but it is not a substitute for a manual human security review. Always re-check mcp-typescript server on vercel's advertised tools, transport security, and authorization posture before connecting an autonomous agent or sharing sensitive context with it.
Add mcp-typescript server on vercel to an MCP client using the endpoint below. Review the grade and findings above before granting an autonomous agent access.
MCP endpoint
https://contentstack-app-mcp-remote.contentstackapps.com/api/mcpStreamable HTTP transport. This is the MCP endpoint, not a website — paste it into your MCP client server list rather than a browser.
Captured passively during the read-only scan. Click any value to find servers that match it.
The tools this server advertises via tools/list — names, purposes, and the parameters each accepts, exactly as enumerated read-only.
Step 3 of the create workflow. Validates a structured app spec and infers security tier + permissions. Call after drafting spec, before cs_plan. Read cs://spec-schema before calling. Input: { spec: ob
Step 4 of the create workflow. Stateless confirmation gate — validates spec and returns a confirmation_prompt. Call after cs_preflight. Show confirmation_prompt to user and WAIT for approval before pr
Step 5 of the create workflow. Generates manifest.json in Developer Hub format from a spec. Call after user approves cs_plan output. Read cs://manifest for format reference. Input: { spec: object, bas
Sorted worst-first. Each finding shows its severity, what it means, its OWASP MCP Top-10 mapping, and a recommended fix — the check id links to the exact methodology row that produced it.
tool: cs_preflight
A tool description tries to alter the model’s use of another tool.
ng spec, before cs_plan. Read cs://spec-schema before calling. Input: {RecommendationDescriptions must describe only their own tool.
tool: cs_plan
A tool description tries to alter the model’s use of another tool.
mpt. Call after cs_preflight. Show confirmation_prompt to user and WAIT forRecommendationDescriptions must describe only their own tool.
tool: cs_manifest
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "base_url"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: cs_manifest
A tool description tries to alter the model’s use of another tool.
r user approves cs_plan output. Read cs://manifest for format referenceRecommendationDescriptions must describe only their own tool.
tool: cs_scaffold
Tools that execute commands / write files / make arbitrary requests are exposed without annotations or guards.
ies first, then write files. {"type":"object","properties":{"spec":{"type":RecommendationAnnotate destructive tools and require human approval.
tool: cs_scaffold
A tool description tries to alter the model’s use of another tool.
ocations) after cs_manifest. Read cs://patterns before calling. Input: { spRecommendationDescriptions must describe only their own tool.
tool: cs_migrate
Tools that execute commands / write files / make arbitrary requests are exposed without annotations or guards.
only — does NOT modify files. Input: { analysis: object } (output of cs_analRecommendationAnnotate destructive tools and require human approval.
tool: cs_migrate
A tool description tries to alter the model’s use of another tool.
ation plan from cs_analyze output. Call with the output of cs_analyze. RetRecommendationDescriptions must describe only their own tool.
tool: cs_venus_resolve
A tool description tries to alter the model’s use of another tool.
les. Call after cs_scaffold, before cs_verify. Input: { ui_elements: stringRecommendationDescriptions must describe only their own tool.
The server accepts tool enumeration (and likely invocation) with no authentication.
RecommendationRequire OAuth 2.1 authorization for any server exposing non-public tools.
tool: cs_preflight
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "cs_preflight"RecommendationScope tools to the minimum needed.
tool: cs_plan
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "cs_plan"RecommendationScope tools to the minimum needed.
tool: cs_manifest
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "cs_manifest"RecommendationScope tools to the minimum needed.
tool: cs_scaffold
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "cs_scaffold"RecommendationScope tools to the minimum needed.
tool: cs_scaffold
One tool both accesses the filesystem and reaches the network. Combining two capability classes in a single tool widens its blast radius and is the substrate for confused-deputy and exfiltration abuse.
}] } Agent MUST create all directories first, then write files. {"type":"object","propRecommendationSeparate filesystem and network capabilities into distinct, independently-scoped tools.
tool: cs_migrate
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "cs_migrate"RecommendationScope tools to the minimum needed.
tool: cs_migrate
One tool both accesses the filesystem and reaches the network. Combining two capability classes in a single tool widens its blast radius and is the substrate for confused-deputy and exfiltration abuse.
only — does NOT modify files. Input: { analysis: object } (output of cs_analRecommendationSeparate filesystem and network capabilities into distinct, independently-scoped tools.
tool: cs_venus_resolve
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "cs_venus_resolve"RecommendationScope tools to the minimum needed.
tool: cs_verify
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "cs_verify"RecommendationScope tools to the minimum needed.
Vantaj uptime monitoring via MCP — manage monitors, heartbeats, incidents, and status pages.
Unified gateway to Algeria's TKAWEN ecosystem: commerce, certification, and AI tools.
Provides access to the Cohereon Doctrine AI safety framework with governance components, tiered access, and agent onboarding.
Agentic rails for complex workflows with receipts, fees, and MCP tool access.
Structural TC39 spec lookup for ECMA-262 and ECMA-402 in AI agents, SHA-pinned and offline-first.
Structural TC39 spec lookup for ECMA-262 and ECMA-402 in AI agents, SHA-pinned and offline-first.
Steps 6a-6c of the create workflow. Generates source files by category with directory structure. Call 3 times (infrastructure → routing → locations) after cs_manifest. Read cs://patterns before callin
Migration workflow step 1. Audits an existing Contentstack app repo against best practices. Call when user wants to audit, migrate, refactor, or fix an existing app. Read cs://maintenance for the chec
Migration workflow step 2. Generates an ordered migration plan from cs_analyze output. Call with the output of cs_analyze. Returns instructions only — does NOT modify files. Input: { analysis: object
Step 7 of the create workflow. Resolves UI element names to exact Venus component names, props, imports, and usage examples. Call after cs_scaffold, before cs_verify. Input: { ui_elements: string[], p
Step 8 of the create workflow. Post-generation verification. Audits the scaffolded project for structural, Venus compliance, security, and consistency issues. Call after writing all files. Repeat unti