
Agent Never Give Up
This is a metacognitive toolkit for AI coding agents that need to break out of loops without human intervention. It exposes seven core MCP tools like logic-is-too-complex, bug-fix-always-failed, and missing-requirements, plus extended scenarios accessible via list_scenarios and get_prompt. Each tool returns a structured markdown protocol with concrete steps to re-anchor goals, summarize what failed, and pivot strategy. It's built for agentic environments like Cursor, Windsurf, and Claude Desktop where an agent might spiral on circular reasoning or repeated failed attempts. The prompts live in markdown files under prompts/core and prompts/extended, making it straightforward to contribute new recovery patterns. Hosted on Cloudflare Workers, so no local setup required.
- GitHub stars
- 5
- tools
- 9
- transport
- STDIO
- last updated
- Nov 27, 2025
Tools
9 toolsPublic tool metadata for what this MCP can expose to an agent.
logic-is-too-complexFor circular reasoning or over-complicated logic
For circular reasoning or over-complicated logic
No parameter schema in public metadata yet.
bug-fix-always-failedFor repeated failed bug fix attempts
For repeated failed bug fix attempts
No parameter schema in public metadata yet.
missing-requirementsFor unclear or missing requirements
For unclear or missing requirements
No parameter schema in public metadata yet.
lost-main-objectiveFor when current actions feel disconnected from the original goal
For when current actions feel disconnected from the original goal
No parameter schema in public metadata yet.
scope-creep-during-taskFor when changes expand beyond the original task scope
For when changes expand beyond the original task scope
No parameter schema in public metadata yet.
long-goal-partially-doneFor multi-step tasks where remaining work is forgotten
For multi-step tasks where remaining work is forgotten
No parameter schema in public metadata yet.
strategy-not-workingFor when the same approach fails repeatedly
For when the same approach fails repeatedly
No parameter schema in public metadata yet.
list_scenariosList all scenarios with their tier (core/extended)
List all scenarios with their tier (core/extended)
No parameter schema in public metadata yet.
get_promptAccess any scenario (core or extended)
Access any scenario (core or extended)
No parameter schema in public metadata yet.
Sponsors
Readme
Agent Never Give Up MCP
This is a MCP server that acts as a "escape guide" for AI coding agents.
It provides structured thinking protocols to help agents unstuck themselves without human help.
The diagram below illustrates when an agent should call this server and what it receives in return:
graph TD
%% 1. The Normal Loop
UserLoop["<b>User Query & Agent Loop</b><br/>(Claude Code / Windsurf / Cursor)<br/>Agent executing tasks..."]
%% 2. The Problem (Triggers)
subgraph Triggers ["Agent Gets Stuck (Trigger State)"]
direction TB
S1["Circular Reasoning"]
S2["Bug Fix Fails"]
S3["Missing Info"]
S4["Analysis Paralysis"]
S5["Unclear 'Done' State"]
end
%% Flow: Loop -> Stuck
UserLoop -.->|"⚠️ Detects Issue<br/>(Inner Loop Stall)"| Triggers
%% 3. The Solution (MCP Call)
subgraph MCP ["Agent Never Give Up MCP"]
direction TB
T1(logic-is-too-complex)
T2(bug-fix-always-failed)
T3(missing-requirements)
T4(analysis-too-long)
T5(unclear-acceptance-criteria)
end
Details
- Repository
- github.com/askman-dev/agent-never-give-up-mcp
- Category
- AI & LLM Tools
- Package
agent-never-give-up-mcp- Transport
- STDIO
- Registry
- MCP registry, active