Loading…
Push notifications and human-in-the-loop approvals for AI agents, with a cross-agent audit trail.
Do not connect
A critical issue was found. Do not connect this server as-is.
Scanned 6 days ago
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 Pushary MCP server exposes 5 tools, focused primarily on communication capabilities. Its published description reads: "Push notifications and human-in-the-loop approvals for AI agents, with a cross-agent audit trail". It communicates over Streamable HTTP using the 2025-06-18 protocol revision, and does not require authorization to connect. MCPGrade currently rates Pushary F — a critical issue was found and the server should not be connected as-is. Its most notable findings include "Data-exfiltration parameters" 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 Pushary's advertised tools, transport security, and authorization posture before connecting an autonomous agent or sharing sensitive context with it.
Add Pushary to an MCP client using the endpoint below. Review the grade and findings above before granting an autonomous agent access.
MCP endpoint
https://pushary.com/api/mcp/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.
Send a one-way push notification to the user's phone and browser. Nothing is awaited; use ask_user instead when you need an answer back. Reach for this when a long-running task finishes and the user a
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: send_notification
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "url"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: send_notification
A tool description tries to alter the model’s use of another tool.
is awaited; use ask_user instead when you need an answer back. Reach forRecommendationDescriptions must describe only their own tool.
tool: ask_user
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
h/apply_patch), secret-redacted and size-capped. Rendered as a collapsRecommendationRemove side-channel parameters; constrain tool inputs.
tool: ask_user
Tools that execute commands / write files / make arbitrary requests are exposed without annotations or guards.
is for (e.g. \"Bash\"), so the user can choose to always-allow it."RecommendationAnnotate destructive tools and require human approval.
tool: ask_user
A tool description tries to alter the model’s use of another tool.
nting for it. Works from Claude Code, Codex, Cursor, Hermes, or any MCP clRecommendationDescriptions must describe only their own tool.
tool: propose_scope
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
uch, e.g. [\"**/.env*\", \"infra/**\"]. These win wherever they overRecommendationRemove side-channel parameters; constrain tool inputs.
tool: propose_scope
Tools that execute commands / write files / make arbitrary requests are exposed without annotations or guards.
**/*.test.ts"). Shell commands are NOT scoped here, they stay governeRecommendationAnnotate destructive tools and require human approval.
tool: propose_scope
A tool description tries to alter the model’s use of another tool.
ent approval, so you are asked once about the boundary rather than repeateRecommendationDescriptions must describe only their own tool.
tool: wait_for_answer
A tool description tries to alter the model’s use of another tool.
lationId from a send_notification that embedded an askQuestion. Each call blocksRecommendationDescriptions must describe only their own tool.
tool: (server instructions)
A tool description tries to alter the model’s use of another tool.
t resolve, call send_notification so the user knows. Use cancel_question to retraRecommendationDescriptions 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: send_notification
The server advertises open-world / broadly-scoped capabilities.
annotations.destructiveHint = trueRecommendationScope tools to the minimum needed.
tool: ask_user
The server advertises open-world / broadly-scoped capabilities.
annotations.destructiveHint = trueRecommendationScope tools to the minimum needed.
tool: propose_scope
The server advertises open-world / broadly-scoped capabilities.
annotations.destructiveHint = trueRecommendationScope 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.
Ask the user a question as a push notification on their phone and block until they answer. Reach for this whenever you need the user's decision and they may be away from the terminal: approving a risk
Propose what this run will touch and block until the user ratifies it. Call ONCE at the start of a multi-step run, before doing work. The user sees the paths you intend to change, the areas you promis
Poll for the user's answer to a previously created question. Use it in three cases: after ask_user with wait set to false, after an ask_user call that returned timedOut, or with the linkedCorrelationI
Retract a pending question so it can no longer be answered. Use this when a question became irrelevant before the user replied: the agent found the answer itself, the task was aborted, or a newer ques