Loading…
Provisions real SIM-backed phone numbers for OTP verification, with automatic code parsing and session management.
Do not connect
A critical issue was found. Do not connect this server as-is.
Scanned 8 days 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 AgentSIM MCP server exposes 5 tools, focused primarily on communication capabilities. Its published description reads: "Provisions real SIM-backed phone numbers for OTP verification, with automatic code parsing and session management". It communicates over Streamable HTTP using the 2025-06-18 protocol revision, and does not require authorization to connect. MCPGrade currently rates AgentSIM 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 AgentSIM's advertised tools, transport security, and authorization posture before connecting an autonomous agent or sharing sensitive context with it.
Add AgentSIM to an MCP client using the endpoint below. Review the grade and findings above before granting an autonomous agent access.
MCP endpoint
https://mcp.agentsim.dev/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.
Lease a temporary programmable phone number for receiving SMS OTP codes. Returns the phone number (e164 format) and a session_id needed for all subsequent calls. The number is reserved for your sessio
Block until an SMS OTP arrives for this session, then return the code. Polls the AgentSIM API for up to `timeout_seconds`. Returns the OTP code and the message it was extracted from. If the OTP does n
List all SMS messages received in this session without consuming the OTP. Use this to inspect raw messages or check if an SMS arrived before calling wait_for_otp. Does NOT mark the OTP as consumed.
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: provision_number
A tool description tries to alter the model’s use of another tool.
RecommendationDescriptions must describe only their own tool.
tool: wait_for_otp
A tool description tries to alter the model’s use of another tool.
g. Always call `release_number` after you have used the OTP.RecommendationDescriptions must describe only their own tool.
tool: get_messages
A tool description tries to alter the model’s use of another tool.
before calling wait_for_otp. Does NOT mark the OTP as consumed.RecommendationDescriptions must describe only their own tool.
tool: release_number
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.
k to the pool. Always call this when you are done with the session — even on erRecommendationTool 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.
d of assuming parser failure. 5. Call `release_number` to return the numbeRecommendationDescriptions 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.
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.
Release a provisioned number back to the pool. Always call this when you are done with the session — even on error — to avoid consuming pool capacity unnecessarily.
List active sessions, optionally filtered by agent_id. Use this to check for leaked sessions or inspect what numbers are currently active in your account.