A remote MCP server that fingerprints agent steps and flags repeated failing tool calls, letting an assistant halt a looping run instead of retrying.
What you can do
Report each step after a tool call, with what was done and whether it failed, and receive a verdict of ok, loop_detected or halted based on a fingerprint of tool, normalized arguments and error. Inspect a run's loops so far, whether it is halted, and its last 10 steps. Draft a plain-English weekly report of runs, loops caught, wasted repeat steps and worst offenders. Check today's usage for a key or IP and see upgrade information.
When to use it
Useful for long or autonomous agent runs where the same failing tool call might repeat and waste time or calls. It gives the assistant a signal to stop and tell the user what repeated rather than retrying indefinitely.
Requirements
A remote streamable HTTP endpoint; no packages, environment variables or headers are declared. No authentication is declared, and usage is tracked by key or IP.
Before you install
The server receives a description of each step, including tool names, arguments and errors, so avoid sending secrets or sensitive data in those reports. It can return a halt verdict that stops a run, and it advertises a paid upgrade; the free tier is limited to 500 calls per day.
Enable the server for the chats that should use its tools.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Use with an agent
Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.
Read https://sourceweft.com/mcp/com.botrecipe%2Floop/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.
Call AFTER each tool call or agent step with what you just did and whether it failed. Loop Breaker fingerprints the call (tool + normalized args + error) and returns verdict ok, loop_detected or halted. Pro: on a loop, halt=true; stop the run, do not retry, and tell your user what repeated. Free watch-only: never halts, returns would_halt and logs it for the weekly report.
Show a run's loops so far, whether it is halted, and its last 10 steps.
Parametersrun_idrequired
weekly_report
Draft a plain-English report of the last 7 days for your key (or IP): runs, loops caught, wasted repeat steps, and the worst offenders. Read-only; sends nothing. Show it to your user.
Takes no parameters.
usage_and_upgrade
Show today's usage for your key or IP and the $49/month All Access upgrade link (cloudforbots.com/offer). Free tier: 500 calls/day. Not metered.
Takes no parameters.
Version history
1
v1.0.0LatestOct 15, 2026
Score
72%
72% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
Reached in the last 30 daysRequired25 pts
Auth declaredRequired10 pts
Tools listedRequired15 pts
DescriptionRequired15 pts
Logo10 pts
Publish an icon in the registry entry.
Documentation15 pts
Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.
LicenseNot applicable
A hosted service is used under its provider's terms, so no license is expected here. This check is left out of the percentage.