$ loading_
Stops coding agents from repeating failed fixes until they perform web search.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "unstuck-mcp" yet — see the docs or source repo.
When fixing this build error, track attempted solutions. If a similar fix has already failed, use your web search tool first before proposing another solution.
The agent avoids repeating failed fixes and performs a search before continuing.
In this code-fixing workflow, block repeated patch attempts. Only allow new fixes after you complete a web search.
The fixing workflow is blocked after repeated failures and redirected to search for external information first.
If you find yourself repeatedly trying similar code fixes, stop making changes and use your web search tool to look up the error and possible solutions before suggesting next steps.
The agent stops inefficient repetition and then suggests next steps based on search results.
When a developer uses an AI coding assistant and it keeps repeating similar patches, this tool can block further attempts and push the agent to search for external information first.
In automated code-fixing or debugging workflows, it can track failed attempts and prevent the agent from repeating the same kind of fix without new information.
It suits teams or individuals who want agents to actively search the web when stuck, making retrieval a prerequisite before continuing the fix.
It prevents coding agents from repeatedly attempting the same failed fix. It tracks attempts and blocks further fixes until the agent uses its own web search tool.
Based on the description, the agent needs its own web search tool, because this tool requires a search before further fixing. Other installation or runtime requirements are not provided; see the source repository.
Its focus is not directly generating fixes, but constraining the agent's fixing behavior. It identifies repeated failed fix paths and forces the agent to gather new external information first.
Detects agent infinite loops and provides safeguards with recovery recommendations.
Detect retry loops and iteration patterns to improve debugging and repair attempts.
Helps AI coding agents inspect codebase structure, symbols, and modules faster.
Analyze and fix test failures with plain-language guidance in IDE and Slack.
Inspect legacy repos and set up better Copilot guidance foundations.
Forward MCP tools to coding agents for session-based development tasks.