Loading…
Multi-step AI agent workflow orchestration API, deployed via Cloudflare Workers with REST and MCP interfaces.
Do not connect
The assessed surface is high-risk. Remediate the findings before connecting.
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 agent-workflow-engine MCP server exposes 5 tools, focused primarily on developer capabilities. Its published description reads: "Multi-step AI agent workflow orchestration API, deployed via Cloudflare Workers with REST and MCP interfaces". It communicates over Streamable HTTP using the 2026-07-28 protocol revision, and does not require authorization to connect. MCPGrade currently rates agent-workflow-engine D+ — the assessed surface is high-risk and should be remediated before use. Its most notable findings include "Data-exfiltration parameters" and "No authorization on a public remote server". 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 agent-workflow-engine's advertised tools, transport security, and authorization posture before connecting an autonomous agent or sharing sensitive context with it.
Add agent-workflow-engine to an MCP client using the endpoint below. Review the grade and findings above before granting an autonomous agent access.
MCP endpoint
https://api.lazy-mac.com/agent-workflow-engine/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.
Create a new multi-agent workflow. Returns a workflow_token encoding the full state — pass it to all subsequent calls.
Update agent execution state. Returns updated workflow_token.
Decode a workflow_token and return full status summary.
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: set_conditional_branch
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
urrent workflow token"},"step_index":{"type":"integer","description":RecommendationRemove side-channel parameters; constrain tool inputs.
The server accepts tool enumeration (and likely invocation) with no authentication.
RecommendationRequire OAuth 2.1 authorization for any server exposing non-public tools.
tool: create_workflow
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "create_workflow"RecommendationScope tools to the minimum needed.
tool: track_agent_state
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "track_agent_state"RecommendationScope tools to the minimum needed.
AWS's official fully managed remote server that provides real-time access to comprehensive AWS documentation, API references, troubleshooting guides, and architectural guidance across multiple knowledge sources including What's New posts, Builder Center content, blog posts, and Well-Architected frameworks for building applications, managing infrastructure, and learning AWS services through natural language queries.
Search live events, conference weeks, host cities, venues, and artist tour schedules.
Live verifiable on-chain data for the $BOBAI token on BNB Chain.
Identity certification, public registry, reputation scoring, and x402 micropayments for AI agents built on Base and Solana.
Search 11M+ products across SG, SEA, and US. Agent-native catalog for AI shopping agents.
Data extraction server on Cloudflare Workers with REST and MCP JSON-RPC interfaces, free tier available.
AI API cost optimization API, deployed via Cloudflare Workers with REST and MCP interfaces.
AI-powered changelog generation API, deployed via Cloudflare Workers with REST and MCP interfaces.
Persistent key-value scratchpad for AI agents with session checkpointing and diff support. Tool documentation in Korean.
AI agent execution trace auditing API, deployed via Cloudflare Workers with REST and MCP interfaces.
Persistent key-value memory store for AI agents, deployed via Cloudflare Workers with REST and MCP interfaces.
Advance to the next workflow step, evaluating conditional branches. Returns next_agent and updated workflow_token.
Attach a conditional branch to a step. Operator is evaluated against agent output when routing. Returns updated workflow_token.