Loading…
Structured thinking tools to help coding agents recover from stuck states
Do not connect
The assessed surface is high-risk. Remediate the findings before connecting.
Scanned 7 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 agent-never-give-up-mcp MCP server exposes 9 tools, focused primarily on AI capabilities. Its published description reads: "Structured thinking tools to help coding agents recover from stuck states". It communicates over Streamable HTTP using the 2025-06-18 protocol revision, and does not require authorization to connect. MCPGrade currently rates agent-never-give-up-mcp D+ — the assessed surface is high-risk and should be remediated before use. Its most notable findings include "Metadata dictates tool-call ordering" 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 agent-never-give-up-mcp's advertised tools, transport security, and authorization posture before connecting an autonomous agent or sharing sensitive context with it.
Add agent-never-give-up-mcp to an MCP client using the endpoint below. Review the grade and findings above before granting an autonomous agent access.
MCP endpoint
https://agent-never-give-up-mcp.askman.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.
List all available stuck-agent scenarios with their tier (core/extended). Core scenarios are also directly available as individual tools.
Use this when your bug fix attempts keep failing, and you need to break out of the loop with a fresh debugging strategy.
Use this when your reasoning is getting long, tangled, or circular, and you need a simple, structured way to reset and move forward.
Use this when working on a multi-step task and you have only completed part of it, risking that remaining steps are forgotten.
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: bug-fix-always-failed
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.
bug-fix-always-failed Use this when your bug fix attempts keep failing, and yoRecommendationTool metadata must describe only the tool, never sequence the agent’s calls.
tool: get_prompt
A tool description tries to alter the model’s use of another tool.
ional mode. Use list_scenarios to discover available scenario IDs.RecommendationDescriptions 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.
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.
Real-time and historical market data for forex, stocks, crypto, indices, and metals via the TickDB API.
Use this when you remember the original goal but your current actions feel disconnected from it, and you need to realign your work with the main objective.
Use this when you cannot proceed because requirements are missing or unclear, and you need to identify what information is needed.
Use this when your changes are expanding beyond the original task scope, and you need to refocus on what was actually requested.
Use this when you have tried the same approach multiple times without success, and you need to step back and consider a fundamentally different strategy.
Get prompt template for any scenario (core or extended) with optional mode. Use list_scenarios to discover available scenario IDs.