Generates rich, interactive user interfaces that open directly in the browser, providing over 40 specialized tools for creating charts, diagrams, visualizations, forms, calendars, and data tables with fully interactive, editable, and exportable outputs using secure temporary URLs.
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 uidriver MCP server exposes 6 tools, focused primarily on general-purpose capabilities. Its published description reads: "Generates rich, interactive user interfaces that open directly in the browser, providing over 40 specialized tools for creating charts, diagrams, visualizations, forms, calendars,…". It communicates over Streamable HTTP using the 2025-06-18 protocol revision, and does not require authorization to connect. MCPGrade currently rates uidriver F — a critical issue was found and the server should not be connected as-is. Its most notable findings include "Hidden instructions in a tool description" 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 uidriver's advertised tools, transport security, and authorization posture before connecting an autonomous agent or sharing sensitive context with it.
Add uidriver to an MCP client using the endpoint below. Review the grade and findings above before granting an autonomous agent access.
MCP endpoint
https://mcp.uidriver.com/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.
A tool displaying a form for selecting dates and date ranges
A tool for displaying interactive charts with support for multiple chart types. Supports line, bar, pie, doughnut, polar area, radar, scatter, bubble, area, histogram, box, heatmap, 3D plots, financia
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: (server instructions)
A tool description contains imperative text aimed at the model (e.g. "ignore previous", "before answering read …").
in browsers. IMPORTANT: When any tool returns a URL, you MUST explicitlRecommendationRemove model-directed instructions from tool descriptions.
tool: create_calendar
A tool description tries to alter the model’s use of another tool.
RecommendationDescriptions must describe only their own tool.
tool: create_calendar
The text tells the model WHEN to call this tool relative to others ("always call first", "before any other tool", "chain to X tool") — a toxic-flow injection that hijacks the agent’s orchestration rather than describing the tool.
f not provided, automatically uses the date of the first event.","default":""}},"required":["events"],"aRecommendationTool metadata must describe only the tool, never sequence the agent’s calls.
tool: (server instructions)
A tool description tries to alter the model’s use of another tool.
sponse Tool** (`get_form_response`) Retrieves user responses from previously submRecommendationDescriptions 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: (server instructions)
Role tokens or delimiter abuse steer the model rather than describe the tool.
RRECT Format:** ```json { "labels": ["Company", "Engineering", "FRecommendationWrite neutral, descriptive tool metadata.
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.
A tool for displaying interactive calendars with events using FullCalendar
A tool that dynamically generates forms based on field definitions
A tool that waits for a from response from a previous form tool call
Create interactive diagrams using JointJS with various shapes, connectors, and layouts